1. 同步MediaCrawler为最新版本
2. 修复数据库not null错误 3. 支持PG数据库 4. 规范环境变量及配置使用 5. 规范为uv安装 6. 使用loggru
This commit is contained in:
Doiiars
@@ -18,7 +18,7 @@ from typing import List
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .bilibili_store_impl import *
|
||||
from ._store_impl import *
|
||||
from .bilibilli_store_media import *
|
||||
|
||||
|
||||
@@ -28,13 +28,14 @@ class BiliStoreFactory:
|
||||
"db": BiliDbStoreImplement,
|
||||
"json": BiliJsonStoreImplement,
|
||||
"sqlite": BiliSqliteStoreImplement,
|
||||
"postgresql": BiliDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = BiliStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[BiliStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[BiliStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
@@ -42,17 +43,19 @@ async def update_bilibili_video(video_item: Dict):
|
||||
video_item_view: Dict = video_item.get("View")
|
||||
video_user_info: Dict = video_item_view.get("owner")
|
||||
video_item_stat: Dict = video_item_view.get("stat")
|
||||
video_id = str(video_item_view.get("aid"))
|
||||
# 保持 video_id 为整数类型，匹配数据库 BigInteger 字段
|
||||
video_id = int(video_item_view.get("aid"))
|
||||
save_content_item = {
|
||||
"video_id": video_id,
|
||||
"video_type": "video",
|
||||
"title": video_item_view.get("title", "")[:500],
|
||||
"desc": video_item_view.get("desc", "")[:500],
|
||||
"create_time": video_item_view.get("pubdate"),
|
||||
"user_id": str(video_user_info.get("mid")),
|
||||
# user_id 和 liked_count 需要保持为整数类型，匹配数据库 BigInteger/Integer 字段
|
||||
"user_id": int(video_user_info.get("mid")) if video_user_info.get("mid") else None,
|
||||
"nickname": video_user_info.get("name"),
|
||||
"avatar": video_user_info.get("face", ""),
|
||||
"liked_count": str(video_item_stat.get("like", "")),
|
||||
"liked_count": int(video_item_stat.get("like", 0)) if video_item_stat.get("like") else None,
|
||||
"disliked_count": str(video_item_stat.get("dislike", "")),
|
||||
"video_play_count": str(video_item_stat.get("view", "")),
|
||||
"video_favorite_count": str(video_item_stat.get("favorite", "")),
|
||||
@@ -72,8 +75,10 @@ async def update_bilibili_video(video_item: Dict):
|
||||
async def update_up_info(video_item: Dict):
|
||||
video_item_card_list: Dict = video_item.get("Card")
|
||||
video_item_card: Dict = video_item_card_list.get("card")
|
||||
# user_id 需要保持为整数类型，匹配数据库 BigInteger 字段
|
||||
mid_value = video_item_card.get("mid")
|
||||
saver_up_info = {
|
||||
"user_id": str(video_item_card.get("mid")),
|
||||
"user_id": int(mid_value) if mid_value else None,
|
||||
"nickname": video_item_card.get("name"),
|
||||
"sex": video_item_card.get("sex"),
|
||||
"sign": video_item_card.get("sign"),
|
||||
@@ -96,18 +101,25 @@ async def batch_update_bilibili_video_comments(video_id: str, comments: List[Dic
|
||||
|
||||
|
||||
async def update_bilibili_video_comment(video_id: str, comment_item: Dict):
|
||||
comment_id = str(comment_item.get("rpid"))
|
||||
# comment_id 和 video_id 需要保持为整数类型，匹配数据库 BigInteger 字段
|
||||
rpid_value = comment_item.get("rpid")
|
||||
comment_id = int(rpid_value) if rpid_value else None
|
||||
parent_comment_id = str(comment_item.get("parent", 0))
|
||||
content: Dict = comment_item.get("content")
|
||||
user_info: Dict = comment_item.get("member")
|
||||
like_count: int = comment_item.get("like", 0)
|
||||
# like_count 需要保持为字符串类型，匹配数据库 Text 字段
|
||||
like_count_value = comment_item.get("like", 0)
|
||||
like_count = str(like_count_value) if like_count_value is not None else "0"
|
||||
# 将 video_id 转换为整数类型，匹配数据库 BigInteger 字段
|
||||
video_id_int = int(video_id) if video_id else None
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"parent_comment_id": parent_comment_id,
|
||||
"create_time": comment_item.get("ctime"),
|
||||
"video_id": str(video_id),
|
||||
"video_id": video_id_int,
|
||||
"content": content.get("message"),
|
||||
"user_id": user_info.get("mid"),
|
||||
# user_id 需要保持为字符串类型，匹配数据库 String(255) 字段
|
||||
"user_id": str(user_info.get("mid")) if user_info.get("mid") else None,
|
||||
"nickname": user_info.get("uname"),
|
||||
"sex": user_info.get("sex"),
|
||||
"sign": user_info.get("sign"),
|
||||
@@ -188,15 +200,18 @@ async def batch_update_bilibili_creator_dynamics(creator_info: Dict, dynamics_li
|
||||
|
||||
|
||||
async def update_bilibili_creator_contact(creator_info: Dict, fan_info: Dict):
|
||||
# up_id 和 fan_id 需要保持为整数类型，匹配数据库 BigInteger 字段
|
||||
up_id_value = creator_info.get("id")
|
||||
fan_id_value = fan_info.get("id")
|
||||
save_contact_item = {
|
||||
"up_id": creator_info["id"],
|
||||
"fan_id": fan_info["id"],
|
||||
"up_name": creator_info["name"],
|
||||
"fan_name": fan_info["name"],
|
||||
"up_sign": creator_info["sign"],
|
||||
"fan_sign": fan_info["sign"],
|
||||
"up_avatar": creator_info["avatar"],
|
||||
"fan_avatar": fan_info["avatar"],
|
||||
"up_id": int(up_id_value) if up_id_value else None,
|
||||
"fan_id": int(fan_id_value) if fan_id_value else None,
|
||||
"up_name": creator_info.get("name"),
|
||||
"fan_name": fan_info.get("name"),
|
||||
"up_sign": creator_info.get("sign"),
|
||||
"fan_sign": fan_info.get("sign"),
|
||||
"up_avatar": creator_info.get("avatar"),
|
||||
"fan_avatar": fan_info.get("avatar"),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,313 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : B站存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import sessionmaker
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import BilibiliVideoComment, BilibiliVideo, BilibiliUpInfo, BilibiliUpDynamic, BilibiliContactInfo
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
class BiliCsvStoreImplement(AbstractStore):
|
||||
def __init__(self):
|
||||
self.file_writer = AsyncFileWriter(
|
||||
crawler_type=crawler_type_var.get(),
|
||||
platform="bili"
|
||||
)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content CSV storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=content_item,
|
||||
item_type="videos"
|
||||
)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment CSV storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=comment_item,
|
||||
item_type="comments"
|
||||
)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator CSV storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=creator,
|
||||
item_type="creators"
|
||||
)
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
creator contact CSV storage implementation
|
||||
Args:
|
||||
contact_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=contact_item,
|
||||
item_type="contacts"
|
||||
)
|
||||
|
||||
async def store_dynamic(self, dynamic_item: Dict):
|
||||
"""
|
||||
creator dynamic CSV storage implementation
|
||||
Args:
|
||||
dynamic_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=dynamic_item,
|
||||
item_type="dynamics"
|
||||
)
|
||||
|
||||
|
||||
class BiliDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Bilibili content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
"""
|
||||
video_id = content_item.get("video_id")
|
||||
# 确保 video_id 为整数类型，匹配数据库 BigInteger 字段
|
||||
if video_id is not None:
|
||||
video_id = int(video_id) if not isinstance(video_id, int) else video_id
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(BilibiliVideo).where(BilibiliVideo.video_id == video_id))
|
||||
video_detail = result.scalar_one_or_none()
|
||||
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_content = BilibiliVideo(**content_item)
|
||||
session.add(new_content)
|
||||
else:
|
||||
for key, value in content_item.items():
|
||||
setattr(video_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Bilibili comment DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
# 确保 comment_id 为整数类型，匹配数据库 BigInteger 字段
|
||||
if comment_id is not None:
|
||||
comment_id = int(comment_id) if not isinstance(comment_id, int) else comment_id
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(BilibiliVideoComment).where(BilibiliVideoComment.comment_id == comment_id))
|
||||
comment_detail = result.scalar_one_or_none()
|
||||
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_comment = BilibiliVideoComment(**comment_item)
|
||||
session.add(new_comment)
|
||||
else:
|
||||
for key, value in comment_item.items():
|
||||
setattr(comment_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Bilibili creator DB storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
"""
|
||||
creator_id = creator.get("user_id")
|
||||
# 确保 creator_id 为整数类型，匹配数据库 BigInteger 字段
|
||||
if creator_id is not None:
|
||||
creator_id = int(creator_id) if not isinstance(creator_id, int) else creator_id
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(BilibiliUpInfo).where(BilibiliUpInfo.user_id == creator_id))
|
||||
creator_detail = result.scalar_one_or_none()
|
||||
|
||||
if not creator_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
new_creator = BilibiliUpInfo(**creator)
|
||||
session.add(new_creator)
|
||||
else:
|
||||
for key, value in creator.items():
|
||||
setattr(creator_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
Bilibili contact DB storage implementation
|
||||
Args:
|
||||
contact_item: contact item dict
|
||||
"""
|
||||
up_id = contact_item.get("up_id")
|
||||
fan_id = contact_item.get("fan_id")
|
||||
# 确保 up_id 和 fan_id 为整数类型，匹配数据库 BigInteger 字段
|
||||
if up_id is not None:
|
||||
up_id = int(up_id) if not isinstance(up_id, int) else up_id
|
||||
if fan_id is not None:
|
||||
fan_id = int(fan_id) if not isinstance(fan_id, int) else fan_id
|
||||
async with get_session() as session:
|
||||
result = await session.execute(
|
||||
select(BilibiliContactInfo).where(BilibiliContactInfo.up_id == up_id, BilibiliContactInfo.fan_id == fan_id)
|
||||
)
|
||||
contact_detail = result.scalar_one_or_none()
|
||||
|
||||
if not contact_detail:
|
||||
contact_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_contact = BilibiliContactInfo(**contact_item)
|
||||
session.add(new_contact)
|
||||
else:
|
||||
for key, value in contact_item.items():
|
||||
setattr(contact_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_dynamic(self, dynamic_item):
|
||||
"""
|
||||
Bilibili dynamic DB storage implementation
|
||||
Args:
|
||||
dynamic_item: dynamic item dict
|
||||
"""
|
||||
dynamic_id = dynamic_item.get("dynamic_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(BilibiliUpDynamic).where(BilibiliUpDynamic.dynamic_id == dynamic_id))
|
||||
dynamic_detail = result.scalar_one_or_none()
|
||||
|
||||
if not dynamic_detail:
|
||||
dynamic_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_dynamic = BilibiliUpDynamic(**dynamic_item)
|
||||
session.add(new_dynamic)
|
||||
else:
|
||||
for key, value in dynamic_item.items():
|
||||
setattr(dynamic_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class BiliJsonStoreImplement(AbstractStore):
|
||||
def __init__(self):
|
||||
self.file_writer = AsyncFileWriter(
|
||||
crawler_type=crawler_type_var.get(),
|
||||
platform="bili"
|
||||
)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=content_item,
|
||||
item_type="contents"
|
||||
)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=comment_item,
|
||||
item_type="comments"
|
||||
)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator JSON storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=creator,
|
||||
item_type="creators"
|
||||
)
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
creator contact JSON storage implementation
|
||||
Args:
|
||||
contact_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=contact_item,
|
||||
item_type="contacts"
|
||||
)
|
||||
|
||||
async def store_dynamic(self, dynamic_item: Dict):
|
||||
"""
|
||||
creator dynamic JSON storage implementation
|
||||
Args:
|
||||
dynamic_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=dynamic_item,
|
||||
item_type="dynamics"
|
||||
)
|
||||
|
||||
|
||||
|
||||
class BiliSqliteStoreImplement(BiliDbStoreImplement):
|
||||
pass
|
||||
@@ -1,465 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 19:34
|
||||
# @Desc : B站存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0])for file_name in os.listdir(file_store_path)])+1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
class BiliCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/bilibili"
|
||||
file_count:int=calculate_number_of_files(csv_store_path)
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/bilibili/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Bilibili content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Bilibili comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Bilibili creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creators")
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
Bilibili contact CSV storage implementation
|
||||
Args:
|
||||
contact_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await self.save_data_to_csv(save_item=contact_item, store_type="contacts")
|
||||
|
||||
async def store_dynamic(self, dynamic_item: Dict):
|
||||
"""
|
||||
Bilibili dynamic CSV storage implementation
|
||||
Args:
|
||||
dynamic_item: creator's dynamic item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await self.save_data_to_csv(save_item=dynamic_item, store_type="dynamics")
|
||||
|
||||
|
||||
class BiliDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Bilibili content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
video_id = content_item.get("video_id")
|
||||
video_detail: Dict = await query_content_by_content_id(content_id=video_id)
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(video_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Bilibili content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Bilibili creator DB storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_creator,
|
||||
query_creator_by_creator_id,
|
||||
update_creator_by_creator_id)
|
||||
creator_id = creator.get("user_id")
|
||||
creator_detail: Dict = await query_creator_by_creator_id(creator_id=creator_id)
|
||||
if not creator_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_creator_id(creator_id,creator_item=creator)
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
Bilibili contact DB storage implementation
|
||||
Args:
|
||||
contact_item: contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_contact,
|
||||
query_contact_by_up_and_fan,
|
||||
update_contact_by_id, )
|
||||
|
||||
up_id = contact_item.get("up_id")
|
||||
fan_id = contact_item.get("fan_id")
|
||||
contact_detail: Dict = await query_contact_by_up_and_fan(up_id=up_id, fan_id=fan_id)
|
||||
if not contact_detail:
|
||||
contact_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_contact(contact_item)
|
||||
else:
|
||||
key_id = contact_detail.get("id")
|
||||
await update_contact_by_id(id=key_id, contact_item=contact_item)
|
||||
|
||||
async def store_dynamic(self, dynamic_item):
|
||||
"""
|
||||
Bilibili dynamic DB storage implementation
|
||||
Args:
|
||||
dynamic_item: dynamic item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_dynamic,
|
||||
query_dynamic_by_dynamic_id,
|
||||
update_dynamic_by_dynamic_id)
|
||||
|
||||
dynamic_id = dynamic_item.get("dynamic_id")
|
||||
dynamic_detail = await query_dynamic_by_dynamic_id(dynamic_id=dynamic_id)
|
||||
if not dynamic_detail:
|
||||
dynamic_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_dynamic(dynamic_item)
|
||||
else:
|
||||
await update_dynamic_by_dynamic_id(dynamic_id, dynamic_item=dynamic_item)
|
||||
|
||||
|
||||
class BiliJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/bilibili/json"
|
||||
words_store_path: str = "data/bilibili/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count:int=calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator JSON storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creators")
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
creator contact JSON storage implementation
|
||||
Args:
|
||||
contact_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await self.save_data_to_json(save_item=contact_item, store_type="contacts")
|
||||
|
||||
async def store_dynamic(self, dynamic_item: Dict):
|
||||
"""
|
||||
creator dynamic JSON storage implementation
|
||||
Args:
|
||||
dynamic_item: creator's contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await self.save_data_to_json(save_item=dynamic_item, store_type="dynamics")
|
||||
|
||||
|
||||
class BiliSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Bilibili content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
video_id = content_item.get("video_id")
|
||||
video_detail: Dict = await query_content_by_content_id(content_id=video_id)
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(video_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Bilibili comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Bilibili creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_creator,
|
||||
query_creator_by_creator_id,
|
||||
update_creator_by_creator_id)
|
||||
creator_id = creator.get("user_id")
|
||||
creator_detail: Dict = await query_creator_by_creator_id(creator_id=creator_id)
|
||||
if not creator_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_creator_id(creator_id, creator_item=creator)
|
||||
|
||||
async def store_contact(self, contact_item: Dict):
|
||||
"""
|
||||
Bilibili contact SQLite storage implementation
|
||||
Args:
|
||||
contact_item: contact item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_contact,
|
||||
query_contact_by_up_and_fan,
|
||||
update_contact_by_id, )
|
||||
|
||||
up_id = contact_item.get("up_id")
|
||||
fan_id = contact_item.get("fan_id")
|
||||
contact_detail: Dict = await query_contact_by_up_and_fan(up_id=up_id, fan_id=fan_id)
|
||||
if not contact_detail:
|
||||
contact_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_contact(contact_item)
|
||||
else:
|
||||
key_id = contact_detail.get("id")
|
||||
await update_contact_by_id(id=key_id, contact_item=contact_item)
|
||||
|
||||
async def store_dynamic(self, dynamic_item):
|
||||
"""
|
||||
Bilibili dynamic SQLite storage implementation
|
||||
Args:
|
||||
dynamic_item: dynamic item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .bilibili_store_sql import (add_new_dynamic,
|
||||
query_dynamic_by_dynamic_id,
|
||||
update_dynamic_by_dynamic_id)
|
||||
|
||||
dynamic_id = dynamic_item.get("dynamic_id")
|
||||
dynamic_detail = await query_dynamic_by_dynamic_id(dynamic_id=dynamic_id)
|
||||
if not dynamic_detail:
|
||||
dynamic_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_dynamic(dynamic_item)
|
||||
else:
|
||||
await update_dynamic_by_dynamic_id(dynamic_id, dynamic_item=dynamic_item)
|
||||
@@ -1,253 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from bilibili_video where video_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("bilibili_video", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("bilibili_video", content_item, "video_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from bilibili_video_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("bilibili_video_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("bilibili_video_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_creator_id(creator_id: str) -> Dict:
|
||||
"""
|
||||
查询up主信息
|
||||
Args:
|
||||
creator_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from bilibili_up_info where user_id = '{creator_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增up主信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("bilibili_up_info", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_creator_id(creator_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新up主信息
|
||||
Args:
|
||||
creator_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("bilibili_up_info", creator_item, "user_id", creator_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_contact_by_up_and_fan(up_id: str, fan_id: str) -> Dict:
|
||||
"""
|
||||
查询一条关联关系
|
||||
Args:
|
||||
up_id:
|
||||
fan_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from bilibili_contact_info where up_id = '{up_id}' and fan_id = '{fan_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_contact(contact_item: Dict) -> int:
|
||||
"""
|
||||
新增关联关系
|
||||
Args:
|
||||
contact_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("bilibili_contact_info", contact_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_contact_by_id(id: str, contact_item: Dict) -> int:
|
||||
"""
|
||||
更新关联关系
|
||||
Args:
|
||||
id:
|
||||
contact_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("bilibili_contact_info", contact_item, "id", id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_dynamic_by_dynamic_id(dynamic_id: str) -> Dict:
|
||||
"""
|
||||
查询一条动态信息
|
||||
Args:
|
||||
dynamic_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from bilibili_up_dynamic where dynamic_id = '{dynamic_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_dynamic(dynamic_item: Dict) -> int:
|
||||
"""
|
||||
新增动态信息
|
||||
Args:
|
||||
dynamic_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("bilibili_up_dynamic", dynamic_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_dynamic_by_dynamic_id(dynamic_id: str, dynamic_item: Dict) -> int:
|
||||
"""
|
||||
更新动态信息
|
||||
Args:
|
||||
dynamic_id:
|
||||
dynamic_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("bilibili_up_dynamic", dynamic_item, "dynamic_id", dynamic_id)
|
||||
return effect_row
|
||||
+1
-1
@@ -22,7 +22,7 @@ from tools import utils
|
||||
|
||||
|
||||
class BilibiliVideo(AbstractStoreVideo):
|
||||
video_store_path: str = "data/bilibili/videos"
|
||||
video_store_path: str = "data/bili/videos"
|
||||
|
||||
async def store_video(self, video_content_item: Dict):
|
||||
"""
|
||||
|
||||
@@ -17,7 +17,7 @@ from typing import List
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .douyin_store_impl import *
|
||||
from ._store_impl import *
|
||||
from .douyin_store_media import *
|
||||
|
||||
|
||||
@@ -27,13 +27,14 @@ class DouyinStoreFactory:
|
||||
"db": DouyinDbStoreImplement,
|
||||
"json": DouyinJsonStoreImplement,
|
||||
"sqlite": DouyinSqliteStoreImplement,
|
||||
"postgresql": DouyinDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = DouyinStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[DouyinStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[DouyinStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,198 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 抖音存储实现类
|
||||
import asyncio
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
from sqlalchemy import select
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import DouyinAweme, DouyinAwemeComment, DyCreator
|
||||
from tools import utils, words
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
class DouyinCsvStoreImplement(AbstractStore):
|
||||
def __init__(self):
|
||||
self.file_writer = AsyncFileWriter(
|
||||
crawler_type=crawler_type_var.get(),
|
||||
platform="douyin"
|
||||
)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=content_item,
|
||||
item_type="contents"
|
||||
)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=comment_item,
|
||||
item_type="comments"
|
||||
)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_to_csv(
|
||||
item=creator,
|
||||
item_type="creators"
|
||||
)
|
||||
|
||||
|
||||
class DouyinDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
"""
|
||||
aweme_id = content_item.get("aweme_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(DouyinAweme).where(DouyinAweme.aweme_id == aweme_id))
|
||||
aweme_detail = result.scalar_one_or_none()
|
||||
|
||||
if not aweme_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
if content_item.get("title"):
|
||||
new_content = DouyinAweme(**content_item)
|
||||
session.add(new_content)
|
||||
else:
|
||||
for key, value in content_item.items():
|
||||
setattr(aweme_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(DouyinAwemeComment).where(DouyinAwemeComment.comment_id == comment_id))
|
||||
comment_detail = result.scalar_one_or_none()
|
||||
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_comment = DouyinAwemeComment(**comment_item)
|
||||
session.add(new_comment)
|
||||
else:
|
||||
for key, value in comment_item.items():
|
||||
setattr(comment_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
"""
|
||||
user_id = creator.get("user_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(DyCreator).where(DyCreator.user_id == user_id))
|
||||
user_detail = result.scalar_one_or_none()
|
||||
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
new_creator = DyCreator(**creator)
|
||||
session.add(new_creator)
|
||||
else:
|
||||
for key, value in creator.items():
|
||||
setattr(user_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class DouyinJsonStoreImplement(AbstractStore):
|
||||
def __init__(self):
|
||||
self.file_writer = AsyncFileWriter(
|
||||
crawler_type=crawler_type_var.get(),
|
||||
platform="douyin"
|
||||
)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=content_item,
|
||||
item_type="contents"
|
||||
)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=comment_item,
|
||||
item_type="comments"
|
||||
)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator JSON storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.file_writer.write_single_item_to_json(
|
||||
item=creator,
|
||||
item_type="creators"
|
||||
)
|
||||
|
||||
|
||||
|
||||
class DouyinSqliteStoreImplement(DouyinDbStoreImplement):
|
||||
pass
|
||||
@@ -1,324 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 18:46
|
||||
# @Desc : 抖音存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class DouyinCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/douyin"
|
||||
file_count: int = calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/douyin/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class DouyinDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .douyin_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
aweme_id = content_item.get("aweme_id")
|
||||
aweme_detail: Dict = await query_content_by_content_id(content_id=aweme_id)
|
||||
if not aweme_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
if content_item.get("title"):
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(aweme_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
class DouyinJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/douyin/json"
|
||||
words_store_path: str = "data/douyin/words"
|
||||
|
||||
lock = asyncio.Lock()
|
||||
file_count: int = calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False, indent=4))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator CSV storage implementation
|
||||
Args:
|
||||
creator: creator item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class DouyinSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Douyin content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .douyin_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
aweme_id = content_item.get("aweme_id")
|
||||
aweme_detail: Dict = await query_content_by_content_id(content_id=aweme_id)
|
||||
if not aweme_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
if content_item.get("title"):
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(aweme_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Douyin comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Douyin creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .douyin_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,160 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from douyin_aweme where aweme_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("douyin_aweme", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("douyin_aweme", content_item, "aweme_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from douyin_aweme_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("douyin_aweme_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("douyin_aweme_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from dy_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("dy_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("dy_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
@@ -18,7 +18,7 @@ from typing import List
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .kuaishou_store_impl import *
|
||||
from ._store_impl import *
|
||||
|
||||
|
||||
class KuaishouStoreFactory:
|
||||
@@ -26,7 +26,8 @@ class KuaishouStoreFactory:
|
||||
"csv": KuaishouCsvStoreImplement,
|
||||
"db": KuaishouDbStoreImplement,
|
||||
"json": KuaishouJsonStoreImplement,
|
||||
"sqlite": KuaishouSqliteStoreImplement
|
||||
"sqlite": KuaishouSqliteStoreImplement,
|
||||
"postgresql": KuaishouDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
@@ -34,7 +35,7 @@ class KuaishouStoreFactory:
|
||||
store_class = KuaishouStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError(
|
||||
"[KuaishouStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
"[KuaishouStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,160 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 快手存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
|
||||
import aiofiles
|
||||
from sqlalchemy import select
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import KuaishouVideo, KuaishouVideoComment
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class KuaishouCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="kuaishou", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Kuaishou content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Kuaishou comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
|
||||
|
||||
class KuaishouDbStoreImplement(AbstractStore):
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Kuaishou content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
"""
|
||||
video_id = content_item.get("video_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(select(KuaishouVideo).where(KuaishouVideo.video_id == video_id))
|
||||
video_detail = result.scalar_one_or_none()
|
||||
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_content = KuaishouVideo(**content_item)
|
||||
session.add(new_content)
|
||||
else:
|
||||
for key, value in content_item.items():
|
||||
setattr(video_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Kuaishou comment DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
async with get_session() as session:
|
||||
result = await session.execute(
|
||||
select(KuaishouVideoComment).where(KuaishouVideoComment.comment_id == comment_id))
|
||||
comment_detail = result.scalar_one_or_none()
|
||||
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
new_comment = KuaishouVideoComment(**comment_item)
|
||||
session.add(new_comment)
|
||||
else:
|
||||
for key, value in comment_item.items():
|
||||
setattr(comment_detail, key, value)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class KuaishouJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="kuaishou", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
|
||||
|
||||
class KuaishouSqliteStoreImplement(KuaishouDbStoreImplement):
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
@@ -1,290 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 20:03
|
||||
# @Desc : 快手存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0])for file_name in os.listdir(file_store_path)])+1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class KuaishouCsvStoreImplement(AbstractStore):
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
|
||||
csv_store_path: str = "data/kuaishou"
|
||||
file_count:int=calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/douyin/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Kuaishou content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Kuaishou comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
|
||||
class KuaishouDbStoreImplement(AbstractStore):
|
||||
async def store_creator(self, creator: Dict):
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Kuaishou content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .kuaishou_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
video_id = content_item.get("video_id")
|
||||
video_detail: Dict = await query_content_by_content_id(content_id=video_id)
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(video_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Kuaishou content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .kuaishou_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
|
||||
class KuaishouJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/kuaishou/json"
|
||||
words_store_path: str = "data/kuaishou/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count:int=calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Kuaishou content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creator")
|
||||
|
||||
|
||||
class KuaishouSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Kuaishou content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .kuaishou_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
video_id = content_item.get("video_id")
|
||||
video_detail: Dict = await query_content_by_content_id(content_id=video_id)
|
||||
if not video_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(video_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Kuaishou comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .kuaishou_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Kuaishou creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pass
|
||||
@@ -1,114 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from kuaishou_video where video_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("kuaishou_video", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("kuaishou_video", content_item, "video_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from kuaishou_video_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("kuaishou_video_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("kuaishou_video_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
@@ -15,8 +15,7 @@ from typing import List
|
||||
from model.m_baidu_tieba import TiebaComment, TiebaCreator, TiebaNote
|
||||
from var import source_keyword_var
|
||||
|
||||
from . import tieba_store_impl
|
||||
from .tieba_store_impl import *
|
||||
from ._store_impl import *
|
||||
|
||||
|
||||
class TieBaStoreFactory:
|
||||
@@ -24,7 +23,8 @@ class TieBaStoreFactory:
|
||||
"csv": TieBaCsvStoreImplement,
|
||||
"db": TieBaDbStoreImplement,
|
||||
"json": TieBaJsonStoreImplement,
|
||||
"sqlite": TieBaSqliteStoreImplement
|
||||
"sqlite": TieBaSqliteStoreImplement,
|
||||
"postgresql": TieBaDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
@@ -32,7 +32,7 @@ class TieBaStoreFactory:
|
||||
store_class = TieBaStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError(
|
||||
"[TieBaStoreFactory.create_store] Invalid save option only supported csv or db or json ...")
|
||||
"[TieBaStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,192 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 贴吧存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.models import TiebaNote, TiebaComment, TiebaCreator
|
||||
from tools import utils, words
|
||||
from database.db_session import get_session
|
||||
from var import crawler_type_var
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class TieBaCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="tieba", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class TieBaDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
"""
|
||||
note_id = content_item.get("note_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(TiebaNote).where(TiebaNote.note_id == note_id)
|
||||
res = await session.execute(stmt)
|
||||
db_note = res.scalar_one_or_none()
|
||||
if db_note:
|
||||
for key, value in content_item.items():
|
||||
setattr(db_note, key, value)
|
||||
else:
|
||||
db_note = TiebaNote(**content_item)
|
||||
session.add(db_note)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(TiebaComment).where(TiebaComment.comment_id == comment_id)
|
||||
res = await session.execute(stmt)
|
||||
db_comment = res.scalar_one_or_none()
|
||||
if db_comment:
|
||||
for key, value in comment_item.items():
|
||||
setattr(db_comment, key, value)
|
||||
else:
|
||||
db_comment = TiebaComment(**comment_item)
|
||||
session.add(db_comment)
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
"""
|
||||
user_id = creator.get("user_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(TiebaCreator).where(TiebaCreator.user_id == user_id)
|
||||
res = await session.execute(stmt)
|
||||
db_creator = res.scalar_one_or_none()
|
||||
if db_creator:
|
||||
for key, value in creator.items():
|
||||
setattr(db_creator, key, value)
|
||||
else:
|
||||
db_creator = TiebaCreator(**creator)
|
||||
session.add(db_creator)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class TieBaJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="tieba", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content JSON storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba comment JSON storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class TieBaSqliteStoreImplement(TieBaDbStoreImplement):
|
||||
"""
|
||||
Tieba sqlite store implement
|
||||
"""
|
||||
pass
|
||||
@@ -1,318 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class TieBaCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/tieba"
|
||||
file_count: int = calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/tieba/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
f.fileno()
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class TieBaDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
|
||||
class TieBaJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/tieba/json"
|
||||
words_store_path: str = "data/tieba/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count: int = calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str, str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name, words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creator")
|
||||
|
||||
|
||||
class TieBaSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
tieba content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
tieba comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
tieba creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .tieba_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,156 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from tieba_note where note_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("tieba_note", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("tieba_note", content_item, "note_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from tieba_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("tieba_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("tieba_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from tieba_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("tieba_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("tieba_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
@@ -19,7 +19,7 @@ from typing import List
|
||||
from var import source_keyword_var
|
||||
|
||||
from .weibo_store_media import *
|
||||
from .weibo_store_impl import *
|
||||
from ._store_impl import *
|
||||
|
||||
|
||||
class WeibostoreFactory:
|
||||
@@ -28,13 +28,14 @@ class WeibostoreFactory:
|
||||
"db": WeiboDbStoreImplement,
|
||||
"json": WeiboJsonStoreImplement,
|
||||
"sqlite": WeiboSqliteStoreImplement,
|
||||
"postgresql": WeiboDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = WeibostoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[WeibotoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[WeibotoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,214 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 微博存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.models import WeiboCreator, WeiboNote, WeiboNoteComment
|
||||
from tools import utils, words
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from database.db_session import get_session
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class WeiboCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="weibo", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Weibo content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Weibo comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Weibo creator CSV storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class WeiboDbStoreImplement(AbstractStore):
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Weibo content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
note_id = content_item.get("note_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(WeiboNote).where(WeiboNote.note_id == note_id)
|
||||
res = await session.execute(stmt)
|
||||
db_note = res.scalar_one_or_none()
|
||||
if db_note:
|
||||
db_note.last_modify_ts = utils.get_current_timestamp()
|
||||
for key, value in content_item.items():
|
||||
if hasattr(db_note, key):
|
||||
setattr(db_note, key, value)
|
||||
else:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
content_item["last_modify_ts"] = utils.get_current_timestamp()
|
||||
db_note = WeiboNote(**content_item)
|
||||
session.add(db_note)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Weibo content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(WeiboNoteComment).where(WeiboNoteComment.comment_id == comment_id)
|
||||
res = await session.execute(stmt)
|
||||
db_comment = res.scalar_one_or_none()
|
||||
if db_comment:
|
||||
db_comment.last_modify_ts = utils.get_current_timestamp()
|
||||
for key, value in comment_item.items():
|
||||
if hasattr(db_comment, key):
|
||||
setattr(db_comment, key, value)
|
||||
else:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
comment_item["last_modify_ts"] = utils.get_current_timestamp()
|
||||
db_comment = WeiboNoteComment(**comment_item)
|
||||
session.add(db_comment)
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Weibo creator DB storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
user_id = creator.get("user_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(WeiboCreator).where(WeiboCreator.user_id == user_id)
|
||||
res = await session.execute(stmt)
|
||||
db_creator = res.scalar_one_or_none()
|
||||
if db_creator:
|
||||
db_creator.last_modify_ts = utils.get_current_timestamp()
|
||||
for key, value in creator.items():
|
||||
if hasattr(db_creator, key):
|
||||
setattr(db_creator, key, value)
|
||||
else:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
creator["last_modify_ts"] = utils.get_current_timestamp()
|
||||
db_creator = WeiboCreator(**creator)
|
||||
session.add(db_creator)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class WeiboJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="weibo", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator JSON storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class WeiboSqliteStoreImplement(WeiboDbStoreImplement):
|
||||
"""
|
||||
Weibo content SQLite storage implementation
|
||||
"""
|
||||
pass
|
||||
@@ -1,326 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 21:35
|
||||
# @Desc : 微博存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class WeiboCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/weibo"
|
||||
file_count: int = calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/bilibili/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
|
||||
return f"{self.csv_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Weibo content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Weibo comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Weibo creator CSV storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creators")
|
||||
|
||||
|
||||
class WeiboDbStoreImplement(AbstractStore):
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Weibo content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .weibo_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Weibo content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .weibo_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Weibo creator DB storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .weibo_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
|
||||
class WeiboJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/weibo/json"
|
||||
words_store_path: str = "data/weibo/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count: int = calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str, str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name, words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
creator JSON storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creators")
|
||||
|
||||
|
||||
class WeiboSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Weibo content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .weibo_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Weibo comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .weibo_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Weibo creator SQLite storage implementation
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
from .weibo_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,160 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from weibo_note where note_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("weibo_note", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("weibo_note", content_item, "note_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from weibo_note_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("weibo_note_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("weibo_note_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from weibo_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("weibo_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("weibo_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
@@ -17,9 +17,8 @@ from typing import List
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from . import xhs_store_impl
|
||||
from .xhs_store_media import *
|
||||
from .xhs_store_impl import *
|
||||
from ._store_impl import *
|
||||
|
||||
|
||||
class XhsStoreFactory:
|
||||
@@ -28,13 +27,14 @@ class XhsStoreFactory:
|
||||
"db": XhsDbStoreImplement,
|
||||
"json": XhsJsonStoreImplement,
|
||||
"sqlite": XhsSqliteStoreImplement,
|
||||
"postgresql": XhsDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = XhsStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[XhsStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[XhsStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,260 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 小红书存储实现类
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
from typing import List, Dict, Any
|
||||
|
||||
from sqlalchemy import select, update, delete
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import XhsNote, XhsNoteComment, XhsCreator
|
||||
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from tools.time_util import get_current_timestamp
|
||||
from var import crawler_type_var
|
||||
|
||||
class XhsCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="xhs", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
store content data to csv file
|
||||
:param content_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
store comment data to csv file
|
||||
:param comment_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
pass
|
||||
|
||||
def flush(self):
|
||||
pass
|
||||
|
||||
|
||||
class XhsJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="xhs", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
store content data to json file
|
||||
:param content_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
store comment data to json file
|
||||
:param comment_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
pass
|
||||
|
||||
def flush(self):
|
||||
"""
|
||||
flush data to json file
|
||||
:return:
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
|
||||
class XhsDbStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
note_id = content_item.get("note_id")
|
||||
if not note_id:
|
||||
return
|
||||
async with get_session() as session:
|
||||
if await self.content_is_exist(session, note_id):
|
||||
await self.update_content(session, content_item)
|
||||
else:
|
||||
await self.add_content(session, content_item)
|
||||
|
||||
async def add_content(self, session: AsyncSession, content_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
note = XhsNote(
|
||||
user_id=content_item.get("user_id"),
|
||||
nickname=content_item.get("nickname"),
|
||||
avatar=content_item.get("avatar"),
|
||||
ip_location=content_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
note_id=content_item.get("note_id"),
|
||||
type=content_item.get("type"),
|
||||
title=content_item.get("title"),
|
||||
desc=content_item.get("desc"),
|
||||
video_url=content_item.get("video_url"),
|
||||
time=content_item.get("time"),
|
||||
last_update_time=content_item.get("last_update_time"),
|
||||
liked_count=str(content_item.get("liked_count")),
|
||||
collected_count=str(content_item.get("collected_count")),
|
||||
comment_count=str(content_item.get("comment_count")),
|
||||
share_count=str(content_item.get("share_count")),
|
||||
image_list=json.dumps(content_item.get("image_list")),
|
||||
tag_list=json.dumps(content_item.get("tag_list")),
|
||||
note_url=content_item.get("note_url"),
|
||||
source_keyword=content_item.get("source_keyword", ""),
|
||||
xsec_token=content_item.get("xsec_token", "")
|
||||
)
|
||||
session.add(note)
|
||||
|
||||
async def update_content(self, session: AsyncSession, content_item: Dict):
|
||||
note_id = content_item.get("note_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"liked_count": str(content_item.get("liked_count")),
|
||||
"collected_count": str(content_item.get("collected_count")),
|
||||
"comment_count": str(content_item.get("comment_count")),
|
||||
"share_count": str(content_item.get("share_count")),
|
||||
"last_update_time": content_item.get("last_update_time"),
|
||||
}
|
||||
stmt = update(XhsNote).where(XhsNote.note_id == note_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def content_is_exist(self, session: AsyncSession, note_id: str) -> bool:
|
||||
stmt = select(XhsNote).where(XhsNote.note_id == note_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
if not comment_item:
|
||||
return
|
||||
async with get_session() as session:
|
||||
comment_id = comment_item.get("comment_id")
|
||||
if not comment_id:
|
||||
return
|
||||
if await self.comment_is_exist(session, comment_id):
|
||||
await self.update_comment(session, comment_item)
|
||||
else:
|
||||
await self.add_comment(session, comment_item)
|
||||
|
||||
async def add_comment(self, session: AsyncSession, comment_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
comment = XhsNoteComment(
|
||||
user_id=comment_item.get("user_id"),
|
||||
nickname=comment_item.get("nickname"),
|
||||
avatar=comment_item.get("avatar"),
|
||||
ip_location=comment_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
comment_id=comment_item.get("comment_id"),
|
||||
create_time=comment_item.get("create_time"),
|
||||
note_id=comment_item.get("note_id"),
|
||||
content=comment_item.get("content"),
|
||||
sub_comment_count=comment_item.get("sub_comment_count"),
|
||||
pictures=json.dumps(comment_item.get("pictures")),
|
||||
parent_comment_id=comment_item.get("parent_comment_id"),
|
||||
like_count=str(comment_item.get("like_count"))
|
||||
)
|
||||
session.add(comment)
|
||||
|
||||
async def update_comment(self, session: AsyncSession, comment_item: Dict):
|
||||
comment_id = comment_item.get("comment_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"like_count": str(comment_item.get("like_count")),
|
||||
"sub_comment_count": comment_item.get("sub_comment_count"),
|
||||
}
|
||||
stmt = update(XhsNoteComment).where(XhsNoteComment.comment_id == comment_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def comment_is_exist(self, session: AsyncSession, comment_id: str) -> bool:
|
||||
stmt = select(XhsNoteComment).where(XhsNoteComment.comment_id == comment_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
user_id = creator_item.get("user_id")
|
||||
if not user_id:
|
||||
return
|
||||
async with get_session() as session:
|
||||
if await self.creator_is_exist(session, user_id):
|
||||
await self.update_creator(session, creator_item)
|
||||
else:
|
||||
await self.add_creator(session, creator_item)
|
||||
|
||||
async def add_creator(self, session: AsyncSession, creator_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
creator = XhsCreator(
|
||||
user_id=creator_item.get("user_id"),
|
||||
nickname=creator_item.get("nickname"),
|
||||
avatar=creator_item.get("avatar"),
|
||||
ip_location=creator_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
desc=creator_item.get("desc"),
|
||||
gender=creator_item.get("gender"),
|
||||
follows=str(creator_item.get("follows")),
|
||||
fans=str(creator_item.get("fans")),
|
||||
interaction=str(creator_item.get("interaction")),
|
||||
tag_list=json.dumps(creator_item.get("tag_list"))
|
||||
)
|
||||
session.add(creator)
|
||||
|
||||
async def update_creator(self, session: AsyncSession, creator_item: Dict):
|
||||
user_id = creator_item.get("user_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"nickname": creator_item.get("nickname"),
|
||||
"avatar": creator_item.get("avatar"),
|
||||
"desc": creator_item.get("desc"),
|
||||
"follows": str(creator_item.get("follows")),
|
||||
"fans": str(creator_item.get("fans")),
|
||||
"interaction": str(creator_item.get("interaction")),
|
||||
"tag_list": json.dumps(creator_item.get("tag_list"))
|
||||
}
|
||||
stmt = update(XhsCreator).where(XhsCreator.user_id == user_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def creator_is_exist(self, session: AsyncSession, user_id: str) -> bool:
|
||||
stmt = select(XhsCreator).where(XhsCreator.user_id == user_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def get_all_content(self) -> List[Dict]:
|
||||
async with get_session() as session:
|
||||
stmt = select(XhsNote)
|
||||
result = await session.execute(stmt)
|
||||
return [item.__dict__ for item in result.scalars().all()]
|
||||
|
||||
async def get_all_comments(self) -> List[Dict]:
|
||||
async with get_session() as session:
|
||||
stmt = select(XhsNoteComment)
|
||||
result = await session.execute(stmt)
|
||||
return [item.__dict__ for item in result.scalars().all()]
|
||||
|
||||
|
||||
class XhsSqliteStoreImplement(XhsDbStoreImplement):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
@@ -1,318 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 16:58
|
||||
# @Desc : 小红书存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0])for file_name in os.listdir(file_store_path)])+1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class XhsCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/xhs"
|
||||
file_count:int=calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/xhs/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
f.fileno()
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class XhsDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_creator, query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
|
||||
class XhsJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/xhs/json"
|
||||
words_store_path: str = "data/xhs/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count:int=calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False, indent=4))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creator")
|
||||
|
||||
|
||||
class XhsSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_creator, query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,160 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_note where note_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_note", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_note", content_item, "note_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_note_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_note_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_note_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
@@ -15,7 +15,7 @@ from typing import List
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from model.m_zhihu import ZhihuComment, ZhihuContent, ZhihuCreator
|
||||
from store.zhihu.zhihu_store_impl import (ZhihuCsvStoreImplement,
|
||||
from ._store_impl import (ZhihuCsvStoreImplement,
|
||||
ZhihuDbStoreImplement,
|
||||
ZhihuJsonStoreImplement,
|
||||
ZhihuSqliteStoreImplement)
|
||||
@@ -28,14 +28,15 @@ class ZhihuStoreFactory:
|
||||
"csv": ZhihuCsvStoreImplement,
|
||||
"db": ZhihuDbStoreImplement,
|
||||
"json": ZhihuJsonStoreImplement,
|
||||
"sqlite": ZhihuSqliteStoreImplement
|
||||
"sqlite": ZhihuSqliteStoreImplement,
|
||||
"postgresql": ZhihuDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = ZhihuStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[ZhihuStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[ZhihuStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
async def batch_update_zhihu_contents(contents: List[ZhihuContent]):
|
||||
|
||||
@@ -0,0 +1,191 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 知乎存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import ZhihuContent, ZhihuComment, ZhihuCreator
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class ZhihuCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="zhihu", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Zhihu content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Zhihu comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class ZhihuDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
"""
|
||||
content_id = content_item.get("content_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(ZhihuContent).where(ZhihuContent.content_id == content_id)
|
||||
result = await session.execute(stmt)
|
||||
existing_content = result.scalars().first()
|
||||
if existing_content:
|
||||
for key, value in content_item.items():
|
||||
setattr(existing_content, key, value)
|
||||
else:
|
||||
new_content = ZhihuContent(**content_item)
|
||||
session.add(new_content)
|
||||
await session.commit()
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
"""
|
||||
comment_id = comment_item.get("comment_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(ZhihuComment).where(ZhihuComment.comment_id == comment_id)
|
||||
result = await session.execute(stmt)
|
||||
existing_comment = result.scalars().first()
|
||||
if existing_comment:
|
||||
for key, value in comment_item.items():
|
||||
setattr(existing_comment, key, value)
|
||||
else:
|
||||
new_comment = ZhihuComment(**comment_item)
|
||||
session.add(new_comment)
|
||||
await session.commit()
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
"""
|
||||
user_id = creator.get("user_id")
|
||||
async with get_session() as session:
|
||||
stmt = select(ZhihuCreator).where(ZhihuCreator.user_id == user_id)
|
||||
result = await session.execute(stmt)
|
||||
existing_creator = result.scalars().first()
|
||||
if existing_creator:
|
||||
for key, value in creator.items():
|
||||
setattr(existing_creator, key, value)
|
||||
else:
|
||||
new_creator = ZhihuCreator(**creator)
|
||||
session.add(new_creator)
|
||||
await session.commit()
|
||||
|
||||
|
||||
class ZhihuJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="zhihu", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="creators", item=creator)
|
||||
|
||||
|
||||
class ZhihuSqliteStoreImplement(ZhihuDbStoreImplement):
|
||||
"""
|
||||
Zhihu content SQLite storage implementation
|
||||
"""
|
||||
pass
|
||||
@@ -1,318 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0]) for file_name in os.listdir(file_store_path)]) + 1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class ZhihuCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/zhihu"
|
||||
file_count: int = calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/zhihu/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
f.fileno()
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Zhihu content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Zhihu comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class ZhihuDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
|
||||
class ZhihuJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/zhihu/json"
|
||||
words_store_path: str = "data/zhihu/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count: int = calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str, str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name, words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False, indent=4))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creator")
|
||||
|
||||
|
||||
class ZhihuSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Zhihu content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Zhihu comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Zhihu creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .zhihu_store_sql import (add_new_creator,
|
||||
query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,156 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（zhihu的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from zhihu_content where content_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（zhihu的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("zhihu_content", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（zhihu的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("zhihu_content", content_item, "content_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from zhihu_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("zhihu_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("zhihu_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from zhihu_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("zhihu_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("zhihu_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
Reference in New Issue
Block a user