The framework has been restructured again, and the Flask framework has been abandoned.
This commit is contained in:
戒酒的李白
@@ -1,15 +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 17:29
|
||||
# @Desc :
|
||||
@@ -1,220 +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 :
|
||||
|
||||
from typing import List
|
||||
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .bilibili_store_impl import *
|
||||
from .bilibilli_store_media import *
|
||||
|
||||
|
||||
class BiliStoreFactory:
|
||||
STORES = {
|
||||
"csv": BiliCsvStoreImplement,
|
||||
"db": BiliDbStoreImplement,
|
||||
"json": BiliJsonStoreImplement,
|
||||
"sqlite": BiliSqliteStoreImplement,
|
||||
}
|
||||
|
||||
@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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
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"))
|
||||
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")),
|
||||
"nickname": video_user_info.get("name"),
|
||||
"avatar": video_user_info.get("face", ""),
|
||||
"liked_count": str(video_item_stat.get("like", "")),
|
||||
"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", "")),
|
||||
"video_share_count": str(video_item_stat.get("share", "")),
|
||||
"video_coin_count": str(video_item_stat.get("coin", "")),
|
||||
"video_danmaku": str(video_item_stat.get("danmaku", "")),
|
||||
"video_comment": str(video_item_stat.get("reply", "")),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"video_url": f"https://www.bilibili.com/video/av{video_id}",
|
||||
"video_cover_url": video_item_view.get("pic", ""),
|
||||
"source_keyword": source_keyword_var.get(),
|
||||
}
|
||||
utils.logger.info(f"[store.bilibili.update_bilibili_video] bilibili video id:{video_id}, title:{save_content_item.get('title')}")
|
||||
await BiliStoreFactory.create_store().store_content(content_item=save_content_item)
|
||||
|
||||
|
||||
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")
|
||||
saver_up_info = {
|
||||
"user_id": str(video_item_card.get("mid")),
|
||||
"nickname": video_item_card.get("name"),
|
||||
"sex": video_item_card.get("sex"),
|
||||
"sign": video_item_card.get("sign"),
|
||||
"avatar": video_item_card.get("face"),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"total_fans": video_item_card.get("fans"),
|
||||
"total_liked": video_item_card_list.get("like_num"),
|
||||
"user_rank": video_item_card.get("level_info").get("current_level"),
|
||||
"is_official": video_item_card.get("official_verify").get("type"),
|
||||
}
|
||||
utils.logger.info(f"[store.bilibili.update_up_info] bilibili user_id:{video_item_card.get('mid')}")
|
||||
await BiliStoreFactory.create_store().store_creator(creator=saver_up_info)
|
||||
|
||||
|
||||
async def batch_update_bilibili_video_comments(video_id: str, comments: List[Dict]):
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_bilibili_video_comment(video_id, comment_item)
|
||||
|
||||
|
||||
async def update_bilibili_video_comment(video_id: str, comment_item: Dict):
|
||||
comment_id = str(comment_item.get("rpid"))
|
||||
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)
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"parent_comment_id": parent_comment_id,
|
||||
"create_time": comment_item.get("ctime"),
|
||||
"video_id": str(video_id),
|
||||
"content": content.get("message"),
|
||||
"user_id": user_info.get("mid"),
|
||||
"nickname": user_info.get("uname"),
|
||||
"sex": user_info.get("sex"),
|
||||
"sign": user_info.get("sign"),
|
||||
"avatar": user_info.get("avatar"),
|
||||
"sub_comment_count": str(comment_item.get("rcount", 0)),
|
||||
"like_count": like_count,
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(f"[store.bilibili.update_bilibili_video_comment] Bilibili video comment: {comment_id}, content: {save_comment_item.get('content')}")
|
||||
await BiliStoreFactory.create_store().store_comment(comment_item=save_comment_item)
|
||||
|
||||
|
||||
async def store_video(aid, video_content, extension_file_name):
|
||||
"""
|
||||
video video storage implementation
|
||||
Args:
|
||||
aid:
|
||||
video_content:
|
||||
extension_file_name:
|
||||
"""
|
||||
await BilibiliVideo().store_video({
|
||||
"aid": aid,
|
||||
"video_content": video_content,
|
||||
"extension_file_name": extension_file_name,
|
||||
})
|
||||
|
||||
|
||||
async def batch_update_bilibili_creator_fans(creator_info: Dict, fans_list: List[Dict]):
|
||||
if not fans_list:
|
||||
return
|
||||
for fan_item in fans_list:
|
||||
fan_info: Dict = {
|
||||
"id": fan_item.get("mid"),
|
||||
"name": fan_item.get("uname"),
|
||||
"sign": fan_item.get("sign"),
|
||||
"avatar": fan_item.get("face"),
|
||||
}
|
||||
await update_bilibili_creator_contact(creator_info=creator_info, fan_info=fan_info)
|
||||
|
||||
|
||||
async def batch_update_bilibili_creator_followings(creator_info: Dict, followings_list: List[Dict]):
|
||||
if not followings_list:
|
||||
return
|
||||
for following_item in followings_list:
|
||||
following_info: Dict = {
|
||||
"id": following_item.get("mid"),
|
||||
"name": following_item.get("uname"),
|
||||
"sign": following_item.get("sign"),
|
||||
"avatar": following_item.get("face"),
|
||||
}
|
||||
await update_bilibili_creator_contact(creator_info=following_info, fan_info=creator_info)
|
||||
|
||||
|
||||
async def batch_update_bilibili_creator_dynamics(creator_info: Dict, dynamics_list: List[Dict]):
|
||||
if not dynamics_list:
|
||||
return
|
||||
for dynamic_item in dynamics_list:
|
||||
dynamic_id: str = dynamic_item["id_str"]
|
||||
dynamic_text: str = ""
|
||||
if dynamic_item["modules"]["module_dynamic"].get("desc"):
|
||||
dynamic_text = dynamic_item["modules"]["module_dynamic"]["desc"]["text"]
|
||||
dynamic_type: str = dynamic_item["type"].split("_")[-1]
|
||||
dynamic_pub_ts: str = dynamic_item["modules"]["module_author"]["pub_ts"]
|
||||
dynamic_stat: Dict = dynamic_item["modules"]["module_stat"]
|
||||
dynamic_comment: int = dynamic_stat["comment"]["count"]
|
||||
dynamic_forward: int = dynamic_stat["forward"]["count"]
|
||||
dynamic_like: int = dynamic_stat["like"]["count"]
|
||||
dynamic_info: Dict = {
|
||||
"dynamic_id": dynamic_id,
|
||||
"text": dynamic_text,
|
||||
"type": dynamic_type,
|
||||
"pub_ts": dynamic_pub_ts,
|
||||
"total_comments": dynamic_comment,
|
||||
"total_forwards": dynamic_forward,
|
||||
"total_liked": dynamic_like,
|
||||
}
|
||||
await update_bilibili_creator_dynamic(creator_info=creator_info, dynamic_info=dynamic_info)
|
||||
|
||||
|
||||
async def update_bilibili_creator_contact(creator_info: Dict, fan_info: Dict):
|
||||
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"],
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
|
||||
await BiliStoreFactory.create_store().store_contact(contact_item=save_contact_item)
|
||||
|
||||
|
||||
async def update_bilibili_creator_dynamic(creator_info: Dict, dynamic_info: Dict):
|
||||
save_dynamic_item = {
|
||||
"dynamic_id": dynamic_info["dynamic_id"],
|
||||
"user_id": creator_info["id"],
|
||||
"user_name": creator_info["name"],
|
||||
"text": dynamic_info["text"],
|
||||
"type": dynamic_info["type"],
|
||||
"pub_ts": dynamic_info["pub_ts"],
|
||||
"total_comments": dynamic_info["total_comments"],
|
||||
"total_forwards": dynamic_info["total_forwards"],
|
||||
"total_liked": dynamic_info["total_liked"],
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
|
||||
await BiliStoreFactory.create_store().store_dynamic(dynamic_item=save_dynamic_item)
|
||||
@@ -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
|
||||
@@ -1,68 +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 : helloteemo
|
||||
# @Time : 2024/7/12 20:01
|
||||
# @Desc : bilibili 媒体保存
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
|
||||
|
||||
class BilibiliVideo(AbstractStoreVideo):
|
||||
video_store_path: str = "data/bilibili/videos"
|
||||
|
||||
async def store_video(self, video_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
video_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_video(video_content_item.get("aid"), video_content_item.get("video_content"), video_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, aid: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
aid: aid
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.video_store_path}/{aid}/{extension_file_name}"
|
||||
|
||||
async def save_video(self, aid: int, video_content: str, extension_file_name="mp4"):
|
||||
"""
|
||||
save video to local
|
||||
|
||||
Args:
|
||||
aid: aid
|
||||
video_content: video content
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.video_store_path + "/" + str(aid)).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(str(aid), extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(video_content)
|
||||
utils.logger.info(f"[BilibiliVideoImplement.save_video] save save_video {save_file_name} success ...")
|
||||
@@ -1,266 +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 :
|
||||
from typing import List
|
||||
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .douyin_store_impl import *
|
||||
from .douyin_store_media import *
|
||||
|
||||
|
||||
class DouyinStoreFactory:
|
||||
STORES = {
|
||||
"csv": DouyinCsvStoreImplement,
|
||||
"db": DouyinDbStoreImplement,
|
||||
"json": DouyinJsonStoreImplement,
|
||||
"sqlite": DouyinSqliteStoreImplement,
|
||||
}
|
||||
|
||||
@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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
def _extract_note_image_list(aweme_detail: Dict) -> List[str]:
|
||||
"""
|
||||
提取笔记图片列表
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音内容详情
|
||||
|
||||
Returns:
|
||||
List[str]: 笔记图片列表
|
||||
"""
|
||||
images_res: List[str] = []
|
||||
images: List[Dict] = aweme_detail.get("images", [])
|
||||
|
||||
if not images:
|
||||
return []
|
||||
|
||||
for image in images:
|
||||
image_url_list = image.get("url_list", []) # download_url_list 为带水印的图片，url_list 为无水印的图片
|
||||
if image_url_list:
|
||||
images_res.append(image_url_list[-1])
|
||||
|
||||
return images_res
|
||||
|
||||
|
||||
def _extract_comment_image_list(comment_item: Dict) -> List[str]:
|
||||
"""
|
||||
提取评论图片列表
|
||||
|
||||
Args:
|
||||
comment_item (Dict): 抖音评论
|
||||
|
||||
Returns:
|
||||
List[str]: 评论图片列表
|
||||
"""
|
||||
images_res: List[str] = []
|
||||
image_list: List[Dict] = comment_item.get("image_list", [])
|
||||
|
||||
if not image_list:
|
||||
return []
|
||||
|
||||
for image in image_list:
|
||||
image_url_list = image.get("origin_url", {}).get("url_list", [])
|
||||
if image_url_list and len(image_url_list) > 1:
|
||||
images_res.append(image_url_list[1])
|
||||
|
||||
return images_res
|
||||
|
||||
|
||||
def _extract_content_cover_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取视频封面地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音内容详情
|
||||
|
||||
Returns:
|
||||
str: 视频封面地址
|
||||
"""
|
||||
res_cover_url = ""
|
||||
|
||||
video_item = aweme_detail.get("video", {})
|
||||
raw_cover_url_list = (video_item.get("raw_cover", {}) or video_item.get("origin_cover", {})).get("url_list", [])
|
||||
if raw_cover_url_list and len(raw_cover_url_list) > 1:
|
||||
res_cover_url = raw_cover_url_list[1]
|
||||
|
||||
return res_cover_url
|
||||
|
||||
|
||||
def _extract_video_download_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取视频下载地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音视频
|
||||
|
||||
Returns:
|
||||
str: 视频下载地址
|
||||
"""
|
||||
video_item = aweme_detail.get("video", {})
|
||||
url_h264_list = video_item.get("play_addr_h264", {}).get("url_list", [])
|
||||
url_256_list = video_item.get("play_addr_256", {}).get("url_list", [])
|
||||
url_list = video_item.get("play_addr", {}).get("url_list", [])
|
||||
actual_url_list = url_h264_list or url_256_list or url_list
|
||||
if not actual_url_list or len(actual_url_list) < 2:
|
||||
return ""
|
||||
return actual_url_list[-1]
|
||||
|
||||
|
||||
def _extract_music_download_url(aweme_detail: Dict) -> str:
|
||||
"""
|
||||
提取音乐下载地址
|
||||
|
||||
Args:
|
||||
aweme_detail (Dict): 抖音视频
|
||||
|
||||
Returns:
|
||||
str: 音乐下载地址
|
||||
"""
|
||||
music_item = aweme_detail.get("music", {})
|
||||
play_url = music_item.get("play_url", {})
|
||||
music_url = play_url.get("uri", "")
|
||||
return music_url
|
||||
|
||||
|
||||
async def update_douyin_aweme(aweme_item: Dict):
|
||||
aweme_id = aweme_item.get("aweme_id")
|
||||
user_info = aweme_item.get("author", {})
|
||||
interact_info = aweme_item.get("statistics", {})
|
||||
save_content_item = {
|
||||
"aweme_id": aweme_id,
|
||||
"aweme_type": str(aweme_item.get("aweme_type")),
|
||||
"title": aweme_item.get("desc", ""),
|
||||
"desc": aweme_item.get("desc", ""),
|
||||
"create_time": aweme_item.get("create_time"),
|
||||
"user_id": user_info.get("uid"),
|
||||
"sec_uid": user_info.get("sec_uid"),
|
||||
"short_user_id": user_info.get("short_id"),
|
||||
"user_unique_id": user_info.get("unique_id"),
|
||||
"user_signature": user_info.get("signature"),
|
||||
"nickname": user_info.get("nickname"),
|
||||
"avatar": user_info.get("avatar_thumb", {}).get("url_list", [""])[0],
|
||||
"liked_count": str(interact_info.get("digg_count")),
|
||||
"collected_count": str(interact_info.get("collect_count")),
|
||||
"comment_count": str(interact_info.get("comment_count")),
|
||||
"share_count": str(interact_info.get("share_count")),
|
||||
"ip_location": aweme_item.get("ip_label", ""),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"aweme_url": f"https://www.douyin.com/video/{aweme_id}",
|
||||
"cover_url": _extract_content_cover_url(aweme_item),
|
||||
"video_download_url": _extract_video_download_url(aweme_item),
|
||||
"music_download_url": _extract_music_download_url(aweme_item),
|
||||
"note_download_url": ",".join(_extract_note_image_list(aweme_item)),
|
||||
"source_keyword": source_keyword_var.get(),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.update_douyin_aweme] douyin aweme id:{aweme_id}, title:{save_content_item.get('title')}")
|
||||
await DouyinStoreFactory.create_store().store_content(content_item=save_content_item)
|
||||
|
||||
|
||||
async def batch_update_dy_aweme_comments(aweme_id: str, comments: List[Dict]):
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_dy_aweme_comment(aweme_id, comment_item)
|
||||
|
||||
|
||||
async def update_dy_aweme_comment(aweme_id: str, comment_item: Dict):
|
||||
comment_aweme_id = comment_item.get("aweme_id")
|
||||
if aweme_id != comment_aweme_id:
|
||||
utils.logger.error(f"[store.douyin.update_dy_aweme_comment] comment_aweme_id: {comment_aweme_id} != aweme_id: {aweme_id}")
|
||||
return
|
||||
user_info = comment_item.get("user", {})
|
||||
comment_id = comment_item.get("cid")
|
||||
parent_comment_id = comment_item.get("reply_id", "0")
|
||||
avatar_info = (user_info.get("avatar_medium", {}) or user_info.get("avatar_300x300", {}) or user_info.get("avatar_168x168", {}) or user_info.get("avatar_thumb", {}) or {})
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"create_time": comment_item.get("create_time"),
|
||||
"ip_location": comment_item.get("ip_label", ""),
|
||||
"aweme_id": aweme_id,
|
||||
"content": comment_item.get("text"),
|
||||
"user_id": user_info.get("uid"),
|
||||
"sec_uid": user_info.get("sec_uid"),
|
||||
"short_user_id": user_info.get("short_id"),
|
||||
"user_unique_id": user_info.get("unique_id"),
|
||||
"user_signature": user_info.get("signature"),
|
||||
"nickname": user_info.get("nickname"),
|
||||
"avatar": avatar_info.get("url_list", [""])[0],
|
||||
"sub_comment_count": str(comment_item.get("reply_comment_total", 0)),
|
||||
"like_count": (comment_item.get("digg_count") if comment_item.get("digg_count") else 0),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"parent_comment_id": parent_comment_id,
|
||||
"pictures": ",".join(_extract_comment_image_list(comment_item)),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.update_dy_aweme_comment] douyin aweme comment: {comment_id}, content: {save_comment_item.get('content')}")
|
||||
|
||||
await DouyinStoreFactory.create_store().store_comment(comment_item=save_comment_item)
|
||||
|
||||
|
||||
async def save_creator(user_id: str, creator: Dict):
|
||||
user_info = creator.get("user", {})
|
||||
gender_map = {0: "未知", 1: "男", 2: "女"}
|
||||
avatar_uri = user_info.get("avatar_300x300", {}).get("uri")
|
||||
local_db_item = {
|
||||
"user_id": user_id,
|
||||
"nickname": user_info.get("nickname"),
|
||||
"gender": gender_map.get(user_info.get("gender"), "未知"),
|
||||
"avatar": f"https://p3-pc.douyinpic.com/img/{avatar_uri}" + r"~c5_300x300.jpeg?from=2956013662",
|
||||
"desc": user_info.get("signature"),
|
||||
"ip_location": user_info.get("ip_location"),
|
||||
"follows": user_info.get("following_count", 0),
|
||||
"fans": user_info.get("max_follower_count", 0),
|
||||
"interaction": user_info.get("total_favorited", 0),
|
||||
"videos_count": user_info.get("aweme_count", 0),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(f"[store.douyin.save_creator] creator:{local_db_item}")
|
||||
await DouyinStoreFactory.create_store().store_creator(local_db_item)
|
||||
|
||||
|
||||
async def update_dy_aweme_image(aweme_id, pic_content, extension_file_name):
|
||||
"""
|
||||
更新抖音笔记图片
|
||||
Args:
|
||||
aweme_id:
|
||||
pic_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await DouYinImage().store_image({"aweme_id": aweme_id, "pic_content": pic_content, "extension_file_name": extension_file_name})
|
||||
|
||||
|
||||
async def update_dy_aweme_video(aweme_id, video_content, extension_file_name):
|
||||
"""
|
||||
更新抖音短视频
|
||||
Args:
|
||||
aweme_id:
|
||||
video_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await DouYinVideo().store_video({"aweme_id": aweme_id, "video_content": video_content, "extension_file_name": extension_file_name})
|
||||
@@ -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)
|
||||
@@ -1,111 +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。
|
||||
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
|
||||
|
||||
class DouYinImage(AbstractStoreImage):
|
||||
image_store_path: str = "data/douyin/images"
|
||||
|
||||
async def store_image(self, image_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
image_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_image(image_content_item.get("aweme_id"), image_content_item.get("pic_content"), image_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, aweme_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.image_store_path}/{aweme_id}/{extension_file_name}"
|
||||
|
||||
async def save_image(self, aweme_id: str, pic_content: str, extension_file_name):
|
||||
"""
|
||||
save image to local
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
pic_content: image content
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.image_store_path + "/" + aweme_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(aweme_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(pic_content)
|
||||
utils.logger.info(f"[DouYinImageStoreImplement.save_image] save image {save_file_name} success ...")
|
||||
|
||||
|
||||
class DouYinVideo(AbstractStoreVideo):
|
||||
video_store_path: str = "data/douyin/videos"
|
||||
|
||||
async def store_video(self, video_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
video_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_video(video_content_item.get("aweme_id"), video_content_item.get("video_content"), video_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, aweme_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.video_store_path}/{aweme_id}/{extension_file_name}"
|
||||
|
||||
async def save_video(self, aweme_id: str, video_content: str, extension_file_name):
|
||||
"""
|
||||
save video to local
|
||||
|
||||
Args:
|
||||
aweme_id: aweme id
|
||||
video_content: video content
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.video_store_path + "/" + aweme_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(aweme_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(video_content)
|
||||
utils.logger.info(f"[DouYinVideoStoreImplement.save_video] save video {save_file_name} success ...")
|
||||
@@ -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
|
||||
@@ -1,111 +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 :
|
||||
from typing import List
|
||||
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from .kuaishou_store_impl import *
|
||||
|
||||
|
||||
class KuaishouStoreFactory:
|
||||
STORES = {
|
||||
"csv": KuaishouCsvStoreImplement,
|
||||
"db": KuaishouDbStoreImplement,
|
||||
"json": KuaishouJsonStoreImplement,
|
||||
"sqlite": KuaishouSqliteStoreImplement
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
async def update_kuaishou_video(video_item: Dict):
|
||||
photo_info: Dict = video_item.get("photo", {})
|
||||
video_id = photo_info.get("id")
|
||||
if not video_id:
|
||||
return
|
||||
user_info = video_item.get("author", {})
|
||||
save_content_item = {
|
||||
"video_id": video_id,
|
||||
"video_type": str(video_item.get("type")),
|
||||
"title": photo_info.get("caption", "")[:500],
|
||||
"desc": photo_info.get("caption", "")[:500],
|
||||
"create_time": photo_info.get("timestamp"),
|
||||
"user_id": user_info.get("id"),
|
||||
"nickname": user_info.get("name"),
|
||||
"avatar": user_info.get("headerUrl", ""),
|
||||
"liked_count": str(photo_info.get("realLikeCount")),
|
||||
"viewd_count": str(photo_info.get("viewCount")),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"video_url": f"https://www.kuaishou.com/short-video/{video_id}",
|
||||
"video_cover_url": photo_info.get("coverUrl", ""),
|
||||
"video_play_url": photo_info.get("photoUrl", ""),
|
||||
"source_keyword": source_keyword_var.get(),
|
||||
}
|
||||
utils.logger.info(
|
||||
f"[store.kuaishou.update_kuaishou_video] Kuaishou video id:{video_id}, title:{save_content_item.get('title')}")
|
||||
await KuaishouStoreFactory.create_store().store_content(content_item=save_content_item)
|
||||
|
||||
|
||||
async def batch_update_ks_video_comments(video_id: str, comments: List[Dict]):
|
||||
utils.logger.info(f"[store.kuaishou.batch_update_ks_video_comments] video_id:{video_id}, comments:{comments}")
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_ks_video_comment(video_id, comment_item)
|
||||
|
||||
|
||||
async def update_ks_video_comment(video_id: str, comment_item: Dict):
|
||||
comment_id = comment_item.get("commentId")
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"create_time": comment_item.get("timestamp"),
|
||||
"video_id": video_id,
|
||||
"content": comment_item.get("content"),
|
||||
"user_id": comment_item.get("authorId"),
|
||||
"nickname": comment_item.get("authorName"),
|
||||
"avatar": comment_item.get("headurl"),
|
||||
"sub_comment_count": str(comment_item.get("subCommentCount", 0)),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(
|
||||
f"[store.kuaishou.update_ks_video_comment] Kuaishou video comment: {comment_id}, content: {save_comment_item.get('content')}")
|
||||
await KuaishouStoreFactory.create_store().store_comment(comment_item=save_comment_item)
|
||||
|
||||
async def save_creator(user_id: str, creator: Dict):
|
||||
ownerCount = creator.get('ownerCount', {})
|
||||
profile = creator.get('profile', {})
|
||||
|
||||
local_db_item = {
|
||||
'user_id': user_id,
|
||||
'nickname': profile.get('user_name'),
|
||||
'gender': '女' if profile.get('gender') == "F" else '男',
|
||||
'avatar': profile.get('headurl'),
|
||||
'desc': profile.get('user_text'),
|
||||
'ip_location': "",
|
||||
'follows': ownerCount.get("follow"),
|
||||
'fans': ownerCount.get("fan"),
|
||||
'interaction': ownerCount.get("photo_public"),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(f"[store.kuaishou.save_creator] creator:{local_db_item}")
|
||||
await KuaishouStoreFactory.create_store().store_creator(local_db_item)
|
||||
@@ -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
|
||||
@@ -1,115 +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 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 *
|
||||
|
||||
|
||||
class TieBaStoreFactory:
|
||||
STORES = {
|
||||
"csv": TieBaCsvStoreImplement,
|
||||
"db": TieBaDbStoreImplement,
|
||||
"json": TieBaJsonStoreImplement,
|
||||
"sqlite": TieBaSqliteStoreImplement
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
async def batch_update_tieba_notes(note_list: List[TiebaNote]):
|
||||
"""
|
||||
Batch update tieba notes
|
||||
Args:
|
||||
note_list:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not note_list:
|
||||
return
|
||||
for note_item in note_list:
|
||||
await update_tieba_note(note_item)
|
||||
|
||||
|
||||
async def update_tieba_note(note_item: TiebaNote):
|
||||
"""
|
||||
Add or Update tieba note
|
||||
Args:
|
||||
note_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
note_item.source_keyword = source_keyword_var.get()
|
||||
save_note_item = note_item.model_dump()
|
||||
save_note_item.update({"last_modify_ts": utils.get_current_timestamp()})
|
||||
utils.logger.info(f"[store.tieba.update_tieba_note] tieba note: {save_note_item}")
|
||||
|
||||
await TieBaStoreFactory.create_store().store_content(save_note_item)
|
||||
|
||||
|
||||
async def batch_update_tieba_note_comments(note_id: str, comments: List[TiebaComment]):
|
||||
"""
|
||||
Batch update tieba note comments
|
||||
Args:
|
||||
note_id:
|
||||
comments:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_tieba_note_comment(note_id, comment_item)
|
||||
|
||||
|
||||
async def update_tieba_note_comment(note_id: str, comment_item: TiebaComment):
|
||||
"""
|
||||
Update tieba note comment
|
||||
Args:
|
||||
note_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
save_comment_item = comment_item.model_dump()
|
||||
save_comment_item.update({"last_modify_ts": utils.get_current_timestamp()})
|
||||
utils.logger.info(f"[store.tieba.update_tieba_note_comment] tieba note id: {note_id} comment:{save_comment_item}")
|
||||
await TieBaStoreFactory.create_store().store_comment(save_comment_item)
|
||||
|
||||
|
||||
async def save_creator(user_info: TiebaCreator):
|
||||
"""
|
||||
Save creator information to local
|
||||
Args:
|
||||
user_info:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
local_db_item = user_info.model_dump()
|
||||
local_db_item["last_modify_ts"] = utils.get_current_timestamp()
|
||||
utils.logger.info(f"[store.tieba.save_creator] creator:{local_db_item}")
|
||||
await TieBaStoreFactory.create_store().store_creator(local_db_item)
|
||||
@@ -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
|
||||
@@ -1,190 +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 21:34
|
||||
# @Desc :
|
||||
|
||||
import re
|
||||
from typing import List
|
||||
|
||||
from var import source_keyword_var
|
||||
|
||||
from .weibo_store_media import *
|
||||
from .weibo_store_impl import *
|
||||
|
||||
|
||||
class WeibostoreFactory:
|
||||
STORES = {
|
||||
"csv": WeiboCsvStoreImplement,
|
||||
"db": WeiboDbStoreImplement,
|
||||
"json": WeiboJsonStoreImplement,
|
||||
"sqlite": WeiboSqliteStoreImplement,
|
||||
}
|
||||
|
||||
@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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
async def batch_update_weibo_notes(note_list: List[Dict]):
|
||||
"""
|
||||
Batch update weibo notes
|
||||
Args:
|
||||
note_list:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not note_list:
|
||||
return
|
||||
for note_item in note_list:
|
||||
await update_weibo_note(note_item)
|
||||
|
||||
|
||||
async def update_weibo_note(note_item: Dict):
|
||||
"""
|
||||
Update weibo note
|
||||
Args:
|
||||
note_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not note_item:
|
||||
return
|
||||
|
||||
mblog: Dict = note_item.get("mblog")
|
||||
user_info: Dict = mblog.get("user")
|
||||
note_id = mblog.get("id")
|
||||
content_text = mblog.get("text")
|
||||
clean_text = re.sub(r"<.*?>", "", content_text)
|
||||
save_content_item = {
|
||||
# 微博信息
|
||||
"note_id": note_id,
|
||||
"content": clean_text,
|
||||
"create_time": utils.rfc2822_to_timestamp(mblog.get("created_at")),
|
||||
"create_date_time": str(utils.rfc2822_to_china_datetime(mblog.get("created_at"))),
|
||||
"liked_count": str(mblog.get("attitudes_count", 0)),
|
||||
"comments_count": str(mblog.get("comments_count", 0)),
|
||||
"shared_count": str(mblog.get("reposts_count", 0)),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"note_url": f"https://m.weibo.cn/detail/{note_id}",
|
||||
"ip_location": mblog.get("region_name", "").replace("发布于 ", ""),
|
||||
|
||||
# 用户信息
|
||||
"user_id": str(user_info.get("id")),
|
||||
"nickname": user_info.get("screen_name", ""),
|
||||
"gender": user_info.get("gender", ""),
|
||||
"profile_url": user_info.get("profile_url", ""),
|
||||
"avatar": user_info.get("profile_image_url", ""),
|
||||
"source_keyword": source_keyword_var.get(),
|
||||
}
|
||||
utils.logger.info(f"[store.weibo.update_weibo_note] weibo note id:{note_id}, title:{save_content_item.get('content')[:24]} ...")
|
||||
await WeibostoreFactory.create_store().store_content(content_item=save_content_item)
|
||||
|
||||
|
||||
async def batch_update_weibo_note_comments(note_id: str, comments: List[Dict]):
|
||||
"""
|
||||
Batch update weibo note comments
|
||||
Args:
|
||||
note_id:
|
||||
comments:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_weibo_note_comment(note_id, comment_item)
|
||||
|
||||
|
||||
async def update_weibo_note_comment(note_id: str, comment_item: Dict):
|
||||
"""
|
||||
Update weibo note comment
|
||||
Args:
|
||||
note_id: weibo note id
|
||||
comment_item: weibo comment item
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not comment_item or not note_id:
|
||||
return
|
||||
comment_id = str(comment_item.get("id"))
|
||||
user_info: Dict = comment_item.get("user")
|
||||
content_text = comment_item.get("text")
|
||||
clean_text = re.sub(r"<.*?>", "", content_text)
|
||||
save_comment_item = {
|
||||
"comment_id": comment_id,
|
||||
"create_time": utils.rfc2822_to_timestamp(comment_item.get("created_at")),
|
||||
"create_date_time": str(utils.rfc2822_to_china_datetime(comment_item.get("created_at"))),
|
||||
"note_id": note_id,
|
||||
"content": clean_text,
|
||||
"sub_comment_count": str(comment_item.get("total_number", 0)),
|
||||
"comment_like_count": str(comment_item.get("like_count", 0)),
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
"ip_location": comment_item.get("source", "").replace("来自", ""),
|
||||
"parent_comment_id": comment_item.get("rootid", ""),
|
||||
|
||||
# 用户信息
|
||||
"user_id": str(user_info.get("id")),
|
||||
"nickname": user_info.get("screen_name", ""),
|
||||
"gender": user_info.get("gender", ""),
|
||||
"profile_url": user_info.get("profile_url", ""),
|
||||
"avatar": user_info.get("profile_image_url", ""),
|
||||
}
|
||||
utils.logger.info(f"[store.weibo.update_weibo_note_comment] Weibo note comment: {comment_id}, content: {save_comment_item.get('content', '')[:24]} ...")
|
||||
await WeibostoreFactory.create_store().store_comment(comment_item=save_comment_item)
|
||||
|
||||
|
||||
async def update_weibo_note_image(picid: str, pic_content, extension_file_name):
|
||||
"""
|
||||
Save weibo note image to local
|
||||
Args:
|
||||
picid:
|
||||
pic_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await WeiboStoreImage().store_image({"pic_id": picid, "pic_content": pic_content, "extension_file_name": extension_file_name})
|
||||
|
||||
|
||||
async def save_creator(user_id: str, user_info: Dict):
|
||||
"""
|
||||
Save creator information to local
|
||||
Args:
|
||||
user_id:
|
||||
user_info:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
local_db_item = {
|
||||
'user_id': user_id,
|
||||
'nickname': user_info.get('screen_name'),
|
||||
'gender': '女' if user_info.get('gender') == "f" else '男',
|
||||
'avatar': user_info.get('avatar_hd'),
|
||||
'desc': user_info.get('description'),
|
||||
'ip_location': user_info.get("source", "").replace("来自", ""),
|
||||
'follows': user_info.get('follow_count', ''),
|
||||
'fans': user_info.get('followers_count', ''),
|
||||
'tag_list': '',
|
||||
"last_modify_ts": utils.get_current_timestamp(),
|
||||
}
|
||||
utils.logger.info(f"[store.weibo.save_creator] creator:{local_db_item}")
|
||||
await WeibostoreFactory.create_store().store_creator(local_db_item)
|
||||
@@ -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)
|
||||
@@ -1,68 +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 : Erm
|
||||
# @Time : 2024/4/9 17:35
|
||||
# @Desc : 微博媒体保存
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
|
||||
|
||||
class WeiboStoreImage(AbstractStoreImage):
|
||||
image_store_path: str = "data/weibo/images"
|
||||
|
||||
async def store_image(self, image_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
image_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_image(image_content_item.get("pic_id"), image_content_item.get("pic_content"), image_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, picid: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
picid: image id
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.image_store_path}/{picid}.{extension_file_name}"
|
||||
|
||||
async def save_image(self, picid: str, pic_content: str, extension_file_name="jpg"):
|
||||
"""
|
||||
save image to local
|
||||
|
||||
Args:
|
||||
picid: image id
|
||||
pic_content: image content
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.image_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(picid, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(pic_content)
|
||||
utils.logger.info(f"[WeiboImageStoreImplement.save_image] save image {save_file_name} success ...")
|
||||
@@ -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
|
||||
@@ -1,241 +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 17:34
|
||||
# @Desc :
|
||||
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 *
|
||||
|
||||
|
||||
class XhsStoreFactory:
|
||||
STORES = {
|
||||
"csv": XhsCsvStoreImplement,
|
||||
"db": XhsDbStoreImplement,
|
||||
"json": XhsJsonStoreImplement,
|
||||
"sqlite": XhsSqliteStoreImplement,
|
||||
}
|
||||
|
||||
@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 ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
def get_video_url_arr(note_item: Dict) -> List:
|
||||
"""
|
||||
获取视频url数组
|
||||
Args:
|
||||
note_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if note_item.get('type') != 'video':
|
||||
return []
|
||||
|
||||
videoArr = []
|
||||
originVideoKey = note_item.get('video').get('consumer').get('origin_video_key')
|
||||
if originVideoKey == '':
|
||||
originVideoKey = note_item.get('video').get('consumer').get('originVideoKey')
|
||||
# 降级有水印
|
||||
if originVideoKey == '':
|
||||
videos = note_item.get('video').get('media').get('stream').get('h264')
|
||||
if type(videos).__name__ == 'list':
|
||||
videoArr = [v.get('master_url') for v in videos]
|
||||
else:
|
||||
videoArr = [f"http://sns-video-bd.xhscdn.com/{originVideoKey}"]
|
||||
|
||||
return videoArr
|
||||
|
||||
|
||||
async def update_xhs_note(note_item: Dict):
|
||||
"""
|
||||
更新小红书笔记
|
||||
Args:
|
||||
note_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
note_id = note_item.get("note_id")
|
||||
user_info = note_item.get("user", {})
|
||||
interact_info = note_item.get("interact_info", {})
|
||||
image_list: List[Dict] = note_item.get("image_list", [])
|
||||
tag_list: List[Dict] = note_item.get("tag_list", [])
|
||||
|
||||
for img in image_list:
|
||||
if img.get('url_default') != '':
|
||||
img.update({'url': img.get('url_default')})
|
||||
|
||||
video_url = ','.join(get_video_url_arr(note_item))
|
||||
|
||||
local_db_item = {
|
||||
"note_id": note_item.get("note_id"), # 帖子id
|
||||
"type": note_item.get("type"), # 帖子类型
|
||||
"title": note_item.get("title") or note_item.get("desc", "")[:255], # 帖子标题
|
||||
"desc": note_item.get("desc", ""), # 帖子描述
|
||||
"video_url": video_url, # 帖子视频url
|
||||
"time": note_item.get("time"), # 帖子发布时间
|
||||
"last_update_time": note_item.get("last_update_time", 0), # 帖子最后更新时间
|
||||
"user_id": user_info.get("user_id"), # 用户id
|
||||
"nickname": user_info.get("nickname"), # 用户昵称
|
||||
"avatar": user_info.get("avatar"), # 用户头像
|
||||
"liked_count": interact_info.get("liked_count"), # 点赞数
|
||||
"collected_count": interact_info.get("collected_count"), # 收藏数
|
||||
"comment_count": interact_info.get("comment_count"), # 评论数
|
||||
"share_count": interact_info.get("share_count"), # 分享数
|
||||
"ip_location": note_item.get("ip_location", ""), # ip地址
|
||||
"image_list": ','.join([img.get('url', '') for img in image_list]), # 图片url
|
||||
"tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']), # 标签
|
||||
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
|
||||
"note_url": f"https://www.xiaohongshu.com/explore/{note_id}?xsec_token={note_item.get('xsec_token')}&xsec_source=pc_search", # 帖子url
|
||||
"source_keyword": source_keyword_var.get(), # 搜索关键词
|
||||
"xsec_token": note_item.get("xsec_token"), # xsec_token
|
||||
}
|
||||
utils.logger.info(f"[store.xhs.update_xhs_note] xhs note: {local_db_item}")
|
||||
await XhsStoreFactory.create_store().store_content(local_db_item)
|
||||
|
||||
|
||||
async def batch_update_xhs_note_comments(note_id: str, comments: List[Dict]):
|
||||
"""
|
||||
批量更新小红书笔记评论
|
||||
Args:
|
||||
note_id:
|
||||
comments:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not comments:
|
||||
return
|
||||
for comment_item in comments:
|
||||
await update_xhs_note_comment(note_id, comment_item)
|
||||
|
||||
|
||||
async def update_xhs_note_comment(note_id: str, comment_item: Dict):
|
||||
"""
|
||||
更新小红书笔记评论
|
||||
Args:
|
||||
note_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
user_info = comment_item.get("user_info", {})
|
||||
comment_id = comment_item.get("id")
|
||||
comment_pictures = [item.get("url_default", "") for item in comment_item.get("pictures", [])]
|
||||
target_comment = comment_item.get("target_comment", {})
|
||||
local_db_item = {
|
||||
"comment_id": comment_id, # 评论id
|
||||
"create_time": comment_item.get("create_time"), # 评论时间
|
||||
"ip_location": comment_item.get("ip_location"), # ip地址
|
||||
"note_id": note_id, # 帖子id
|
||||
"content": comment_item.get("content"), # 评论内容
|
||||
"user_id": user_info.get("user_id"), # 用户id
|
||||
"nickname": user_info.get("nickname"), # 用户昵称
|
||||
"avatar": user_info.get("image"), # 用户头像
|
||||
"sub_comment_count": comment_item.get("sub_comment_count", 0), # 子评论数
|
||||
"pictures": ",".join(comment_pictures), # 评论图片
|
||||
"parent_comment_id": target_comment.get("id", 0), # 父评论id
|
||||
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
|
||||
"like_count": comment_item.get("like_count", 0),
|
||||
}
|
||||
utils.logger.info(f"[store.xhs.update_xhs_note_comment] xhs note comment:{local_db_item}")
|
||||
await XhsStoreFactory.create_store().store_comment(local_db_item)
|
||||
|
||||
|
||||
async def save_creator(user_id: str, creator: Dict):
|
||||
"""
|
||||
保存小红书创作者
|
||||
Args:
|
||||
user_id:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
user_info = creator.get('basicInfo', {})
|
||||
|
||||
follows = 0
|
||||
fans = 0
|
||||
interaction = 0
|
||||
for i in creator.get('interactions'):
|
||||
if i.get('type') == 'follows':
|
||||
follows = i.get('count')
|
||||
elif i.get('type') == 'fans':
|
||||
fans = i.get('count')
|
||||
elif i.get('type') == 'interaction':
|
||||
interaction = i.get('count')
|
||||
|
||||
def get_gender(gender):
|
||||
if gender == 1:
|
||||
return '女'
|
||||
elif gender == 0:
|
||||
return '男'
|
||||
else:
|
||||
return None
|
||||
|
||||
local_db_item = {
|
||||
'user_id': user_id, # 用户id
|
||||
'nickname': user_info.get('nickname'), # 昵称
|
||||
'gender': get_gender(user_info.get('gender')), # 性别
|
||||
'avatar': user_info.get('images'), # 头像
|
||||
'desc': user_info.get('desc'), # 个人描述
|
||||
'ip_location': user_info.get('ipLocation'), # ip地址
|
||||
'follows': follows, # 关注数
|
||||
'fans': fans, # 粉丝数
|
||||
'interaction': interaction, # 互动数
|
||||
'tag_list': json.dumps({tag.get('tagType'): tag.get('name')
|
||||
for tag in creator.get('tags')}, ensure_ascii=False), # 标签
|
||||
"last_modify_ts": utils.get_current_timestamp(), # 最后更新时间戳（MediaCrawler程序生成的，主要用途在db存储的时候记录一条记录最新更新时间）
|
||||
}
|
||||
utils.logger.info(f"[store.xhs.save_creator] creator:{local_db_item}")
|
||||
await XhsStoreFactory.create_store().store_creator(local_db_item)
|
||||
|
||||
|
||||
async def update_xhs_note_image(note_id, pic_content, extension_file_name):
|
||||
"""
|
||||
更新小红书笔记图片
|
||||
Args:
|
||||
note_id:
|
||||
pic_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await XiaoHongShuImage().store_image({"notice_id": note_id, "pic_content": pic_content, "extension_file_name": extension_file_name})
|
||||
|
||||
|
||||
async def update_xhs_note_video(note_id, video_content, extension_file_name):
|
||||
"""
|
||||
更新小红书笔记视频
|
||||
Args:
|
||||
note_id:
|
||||
video_content:
|
||||
extension_file_name:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
await XiaoHongShuVideo().store_video({"notice_id": note_id, "video_content": video_content, "extension_file_name": extension_file_name})
|
||||
@@ -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)
|
||||
@@ -1,115 +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 : helloteemo
|
||||
# @Time : 2024/7/11 22:35
|
||||
# @Desc : 小红书媒体保存
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
|
||||
|
||||
class XiaoHongShuImage(AbstractStoreImage):
|
||||
image_store_path: str = "data/xhs/images"
|
||||
|
||||
async def store_image(self, image_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
image_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_image(image_content_item.get("notice_id"), image_content_item.get("pic_content"), image_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, notice_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
notice_id: notice id
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.image_store_path}/{notice_id}/{extension_file_name}"
|
||||
|
||||
async def save_image(self, notice_id: str, pic_content: str, extension_file_name):
|
||||
"""
|
||||
save image to local
|
||||
|
||||
Args:
|
||||
notice_id: notice id
|
||||
pic_content: image content
|
||||
extension_file_name: image filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.image_store_path + "/" + notice_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(notice_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(pic_content)
|
||||
utils.logger.info(f"[XiaoHongShuImageStoreImplement.save_image] save image {save_file_name} success ...")
|
||||
|
||||
|
||||
class XiaoHongShuVideo(AbstractStoreVideo):
|
||||
video_store_path: str = "data/xhs/videos"
|
||||
|
||||
async def store_video(self, video_content_item: Dict):
|
||||
"""
|
||||
store content
|
||||
|
||||
Args:
|
||||
video_content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_video(video_content_item.get("notice_id"), video_content_item.get("video_content"), video_content_item.get("extension_file_name"))
|
||||
|
||||
def make_save_file_name(self, notice_id: str, extension_file_name: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
|
||||
Args:
|
||||
notice_id: notice id
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
return f"{self.video_store_path}/{notice_id}/{extension_file_name}"
|
||||
|
||||
async def save_video(self, notice_id: str, video_content: str, extension_file_name):
|
||||
"""
|
||||
save video to local
|
||||
|
||||
Args:
|
||||
notice_id: notice id
|
||||
video_content: video content
|
||||
extension_file_name: video filename with extension
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.video_store_path + "/" + notice_id).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(notice_id, extension_file_name)
|
||||
async with aiofiles.open(save_file_name, 'wb') as f:
|
||||
await f.write(video_content)
|
||||
utils.logger.info(f"[XiaoHongShuVideoStoreImplement.save_video] save video {save_file_name} success ...")
|
||||
@@ -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
|
||||
@@ -1,117 +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 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,
|
||||
ZhihuDbStoreImplement,
|
||||
ZhihuJsonStoreImplement,
|
||||
ZhihuSqliteStoreImplement)
|
||||
from tools import utils
|
||||
from var import source_keyword_var
|
||||
|
||||
|
||||
class ZhihuStoreFactory:
|
||||
STORES = {
|
||||
"csv": ZhihuCsvStoreImplement,
|
||||
"db": ZhihuDbStoreImplement,
|
||||
"json": ZhihuJsonStoreImplement,
|
||||
"sqlite": ZhihuSqliteStoreImplement
|
||||
}
|
||||
|
||||
@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 ...")
|
||||
return store_class()
|
||||
|
||||
async def batch_update_zhihu_contents(contents: List[ZhihuContent]):
|
||||
"""
|
||||
批量更新知乎内容
|
||||
Args:
|
||||
contents:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not contents:
|
||||
return
|
||||
|
||||
for content_item in contents:
|
||||
await update_zhihu_content(content_item)
|
||||
|
||||
async def update_zhihu_content(content_item: ZhihuContent):
|
||||
"""
|
||||
更新知乎内容
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
content_item.source_keyword = source_keyword_var.get()
|
||||
local_db_item = content_item.model_dump()
|
||||
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
|
||||
utils.logger.info(f"[store.zhihu.update_zhihu_content] zhihu content: {local_db_item}")
|
||||
await ZhihuStoreFactory.create_store().store_content(local_db_item)
|
||||
|
||||
|
||||
|
||||
async def batch_update_zhihu_note_comments(comments: List[ZhihuComment]):
|
||||
"""
|
||||
批量更新知乎内容评论
|
||||
Args:
|
||||
comments:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not comments:
|
||||
return
|
||||
|
||||
for comment_item in comments:
|
||||
await update_zhihu_content_comment(comment_item)
|
||||
|
||||
|
||||
async def update_zhihu_content_comment(comment_item: ZhihuComment):
|
||||
"""
|
||||
更新知乎内容评论
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
local_db_item = comment_item.model_dump()
|
||||
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
|
||||
utils.logger.info(f"[store.zhihu.update_zhihu_note_comment] zhihu content comment:{local_db_item}")
|
||||
await ZhihuStoreFactory.create_store().store_comment(local_db_item)
|
||||
|
||||
|
||||
async def save_creator(creator: ZhihuCreator):
|
||||
"""
|
||||
保存知乎创作者信息
|
||||
Args:
|
||||
creator:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not creator:
|
||||
return
|
||||
local_db_item = creator.model_dump()
|
||||
local_db_item.update({"last_modify_ts": utils.get_current_timestamp()})
|
||||
await ZhihuStoreFactory.create_store().store_creator(local_db_item)
|
||||
@@ -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