1. 同步MediaCrawler为最新版本
2. 修复数据库not null错误 3. 支持PG数据库 4. 规范环境变量及配置使用 5. 规范为uv安装 6. 使用loggru
This commit is contained in:
Doiiars
@@ -17,9 +17,8 @@ from typing import List
|
||||
import config
|
||||
from var import source_keyword_var
|
||||
|
||||
from . import xhs_store_impl
|
||||
from .xhs_store_media import *
|
||||
from .xhs_store_impl import *
|
||||
from ._store_impl import *
|
||||
|
||||
|
||||
class XhsStoreFactory:
|
||||
@@ -28,13 +27,14 @@ class XhsStoreFactory:
|
||||
"db": XhsDbStoreImplement,
|
||||
"json": XhsJsonStoreImplement,
|
||||
"sqlite": XhsSqliteStoreImplement,
|
||||
"postgresql": XhsDbStoreImplement,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def create_store() -> AbstractStore:
|
||||
store_class = XhsStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
|
||||
if not store_class:
|
||||
raise ValueError("[XhsStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
|
||||
raise ValueError("[XhsStoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite or postgresql ...")
|
||||
return store_class()
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,260 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : persist1@126.com
|
||||
# @Time : 2025/9/5 19:34
|
||||
# @Desc : 小红书存储实现类
|
||||
import json
|
||||
import os
|
||||
from datetime import datetime
|
||||
from typing import List, Dict, Any
|
||||
|
||||
from sqlalchemy import select, update, delete
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from base.base_crawler import AbstractStore
|
||||
from database.db_session import get_session
|
||||
from database.models import XhsNote, XhsNoteComment, XhsCreator
|
||||
|
||||
from tools.async_file_writer import AsyncFileWriter
|
||||
from tools.time_util import get_current_timestamp
|
||||
from var import crawler_type_var
|
||||
|
||||
class XhsCsvStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="xhs", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
store content data to csv file
|
||||
:param content_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
store comment data to csv file
|
||||
:param comment_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_to_csv(item_type="comments", item=comment_item)
|
||||
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
pass
|
||||
|
||||
def flush(self):
|
||||
pass
|
||||
|
||||
|
||||
class XhsJsonStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
self.writer = AsyncFileWriter(platform="xhs", crawler_type=crawler_type_var.get())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
store content data to json file
|
||||
:param content_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="contents", item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
store comment data to json file
|
||||
:param comment_item:
|
||||
:return:
|
||||
"""
|
||||
await self.writer.write_single_item_to_json(item_type="comments", item=comment_item)
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
pass
|
||||
|
||||
def flush(self):
|
||||
"""
|
||||
flush data to json file
|
||||
:return:
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
|
||||
class XhsDbStoreImplement(AbstractStore):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
note_id = content_item.get("note_id")
|
||||
if not note_id:
|
||||
return
|
||||
async with get_session() as session:
|
||||
if await self.content_is_exist(session, note_id):
|
||||
await self.update_content(session, content_item)
|
||||
else:
|
||||
await self.add_content(session, content_item)
|
||||
|
||||
async def add_content(self, session: AsyncSession, content_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
note = XhsNote(
|
||||
user_id=content_item.get("user_id"),
|
||||
nickname=content_item.get("nickname"),
|
||||
avatar=content_item.get("avatar"),
|
||||
ip_location=content_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
note_id=content_item.get("note_id"),
|
||||
type=content_item.get("type"),
|
||||
title=content_item.get("title"),
|
||||
desc=content_item.get("desc"),
|
||||
video_url=content_item.get("video_url"),
|
||||
time=content_item.get("time"),
|
||||
last_update_time=content_item.get("last_update_time"),
|
||||
liked_count=str(content_item.get("liked_count")),
|
||||
collected_count=str(content_item.get("collected_count")),
|
||||
comment_count=str(content_item.get("comment_count")),
|
||||
share_count=str(content_item.get("share_count")),
|
||||
image_list=json.dumps(content_item.get("image_list")),
|
||||
tag_list=json.dumps(content_item.get("tag_list")),
|
||||
note_url=content_item.get("note_url"),
|
||||
source_keyword=content_item.get("source_keyword", ""),
|
||||
xsec_token=content_item.get("xsec_token", "")
|
||||
)
|
||||
session.add(note)
|
||||
|
||||
async def update_content(self, session: AsyncSession, content_item: Dict):
|
||||
note_id = content_item.get("note_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"liked_count": str(content_item.get("liked_count")),
|
||||
"collected_count": str(content_item.get("collected_count")),
|
||||
"comment_count": str(content_item.get("comment_count")),
|
||||
"share_count": str(content_item.get("share_count")),
|
||||
"last_update_time": content_item.get("last_update_time"),
|
||||
}
|
||||
stmt = update(XhsNote).where(XhsNote.note_id == note_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def content_is_exist(self, session: AsyncSession, note_id: str) -> bool:
|
||||
stmt = select(XhsNote).where(XhsNote.note_id == note_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
if not comment_item:
|
||||
return
|
||||
async with get_session() as session:
|
||||
comment_id = comment_item.get("comment_id")
|
||||
if not comment_id:
|
||||
return
|
||||
if await self.comment_is_exist(session, comment_id):
|
||||
await self.update_comment(session, comment_item)
|
||||
else:
|
||||
await self.add_comment(session, comment_item)
|
||||
|
||||
async def add_comment(self, session: AsyncSession, comment_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
comment = XhsNoteComment(
|
||||
user_id=comment_item.get("user_id"),
|
||||
nickname=comment_item.get("nickname"),
|
||||
avatar=comment_item.get("avatar"),
|
||||
ip_location=comment_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
comment_id=comment_item.get("comment_id"),
|
||||
create_time=comment_item.get("create_time"),
|
||||
note_id=comment_item.get("note_id"),
|
||||
content=comment_item.get("content"),
|
||||
sub_comment_count=comment_item.get("sub_comment_count"),
|
||||
pictures=json.dumps(comment_item.get("pictures")),
|
||||
parent_comment_id=comment_item.get("parent_comment_id"),
|
||||
like_count=str(comment_item.get("like_count"))
|
||||
)
|
||||
session.add(comment)
|
||||
|
||||
async def update_comment(self, session: AsyncSession, comment_item: Dict):
|
||||
comment_id = comment_item.get("comment_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"like_count": str(comment_item.get("like_count")),
|
||||
"sub_comment_count": comment_item.get("sub_comment_count"),
|
||||
}
|
||||
stmt = update(XhsNoteComment).where(XhsNoteComment.comment_id == comment_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def comment_is_exist(self, session: AsyncSession, comment_id: str) -> bool:
|
||||
stmt = select(XhsNoteComment).where(XhsNoteComment.comment_id == comment_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def store_creator(self, creator_item: Dict):
|
||||
user_id = creator_item.get("user_id")
|
||||
if not user_id:
|
||||
return
|
||||
async with get_session() as session:
|
||||
if await self.creator_is_exist(session, user_id):
|
||||
await self.update_creator(session, creator_item)
|
||||
else:
|
||||
await self.add_creator(session, creator_item)
|
||||
|
||||
async def add_creator(self, session: AsyncSession, creator_item: Dict):
|
||||
add_ts = int(get_current_timestamp())
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
creator = XhsCreator(
|
||||
user_id=creator_item.get("user_id"),
|
||||
nickname=creator_item.get("nickname"),
|
||||
avatar=creator_item.get("avatar"),
|
||||
ip_location=creator_item.get("ip_location"),
|
||||
add_ts=add_ts,
|
||||
last_modify_ts=last_modify_ts,
|
||||
desc=creator_item.get("desc"),
|
||||
gender=creator_item.get("gender"),
|
||||
follows=str(creator_item.get("follows")),
|
||||
fans=str(creator_item.get("fans")),
|
||||
interaction=str(creator_item.get("interaction")),
|
||||
tag_list=json.dumps(creator_item.get("tag_list"))
|
||||
)
|
||||
session.add(creator)
|
||||
|
||||
async def update_creator(self, session: AsyncSession, creator_item: Dict):
|
||||
user_id = creator_item.get("user_id")
|
||||
last_modify_ts = int(get_current_timestamp())
|
||||
update_data = {
|
||||
"last_modify_ts": last_modify_ts,
|
||||
"nickname": creator_item.get("nickname"),
|
||||
"avatar": creator_item.get("avatar"),
|
||||
"desc": creator_item.get("desc"),
|
||||
"follows": str(creator_item.get("follows")),
|
||||
"fans": str(creator_item.get("fans")),
|
||||
"interaction": str(creator_item.get("interaction")),
|
||||
"tag_list": json.dumps(creator_item.get("tag_list"))
|
||||
}
|
||||
stmt = update(XhsCreator).where(XhsCreator.user_id == user_id).values(**update_data)
|
||||
await session.execute(stmt)
|
||||
|
||||
async def creator_is_exist(self, session: AsyncSession, user_id: str) -> bool:
|
||||
stmt = select(XhsCreator).where(XhsCreator.user_id == user_id)
|
||||
result = await session.execute(stmt)
|
||||
return result.first() is not None
|
||||
|
||||
async def get_all_content(self) -> List[Dict]:
|
||||
async with get_session() as session:
|
||||
stmt = select(XhsNote)
|
||||
result = await session.execute(stmt)
|
||||
return [item.__dict__ for item in result.scalars().all()]
|
||||
|
||||
async def get_all_comments(self) -> List[Dict]:
|
||||
async with get_session() as session:
|
||||
stmt = select(XhsNoteComment)
|
||||
result = await session.execute(stmt)
|
||||
return [item.__dict__ for item in result.scalars().all()]
|
||||
|
||||
|
||||
class XhsSqliteStoreImplement(XhsDbStoreImplement):
|
||||
def __init__(self, **kwargs):
|
||||
super().__init__(**kwargs)
|
||||
@@ -1,318 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/1/14 16:58
|
||||
# @Desc : 小红书存储实现类
|
||||
import asyncio
|
||||
import csv
|
||||
import json
|
||||
import os
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractStore
|
||||
from tools import utils, words
|
||||
from var import crawler_type_var
|
||||
|
||||
|
||||
def calculate_number_of_files(file_store_path: str) -> int:
|
||||
"""计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
|
||||
Args:
|
||||
file_store_path;
|
||||
Returns:
|
||||
file nums
|
||||
"""
|
||||
if not os.path.exists(file_store_path):
|
||||
return 1
|
||||
try:
|
||||
return max([int(file_name.split("_")[0])for file_name in os.listdir(file_store_path)])+1
|
||||
except ValueError:
|
||||
return 1
|
||||
|
||||
|
||||
class XhsCsvStoreImplement(AbstractStore):
|
||||
csv_store_path: str = "data/xhs"
|
||||
file_count:int=calculate_number_of_files(csv_store_path)
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> str:
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: contents or comments
|
||||
|
||||
Returns: eg: data/xhs/search_comments_20240114.csv ...
|
||||
|
||||
"""
|
||||
return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
|
||||
|
||||
async def save_data_to_csv(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in CSV format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns: no returns
|
||||
|
||||
"""
|
||||
pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name = self.make_save_file_name(store_type=store_type)
|
||||
async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
|
||||
f.fileno()
|
||||
writer = csv.writer(f)
|
||||
if await f.tell() == 0:
|
||||
await writer.writerow(save_item.keys())
|
||||
await writer.writerow(save_item.values())
|
||||
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content CSV storage implementation
|
||||
Args:
|
||||
content_item: note item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=content_item, store_type="contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu comment CSV storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=comment_item, store_type="comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content CSV storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_csv(save_item=creator, store_type="creator")
|
||||
|
||||
|
||||
class XhsDbStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content DB storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_creator, query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
|
||||
|
||||
class XhsJsonStoreImplement(AbstractStore):
|
||||
json_store_path: str = "data/xhs/json"
|
||||
words_store_path: str = "data/xhs/words"
|
||||
lock = asyncio.Lock()
|
||||
file_count:int=calculate_number_of_files(json_store_path)
|
||||
WordCloud = words.AsyncWordCloudGenerator()
|
||||
|
||||
def make_save_file_name(self, store_type: str) -> (str,str):
|
||||
"""
|
||||
make save file name by store type
|
||||
Args:
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
return (
|
||||
f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
|
||||
f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
|
||||
)
|
||||
|
||||
async def save_data_to_json(self, save_item: Dict, store_type: str):
|
||||
"""
|
||||
Below is a simple way to save it in json format.
|
||||
Args:
|
||||
save_item: save content dict info
|
||||
store_type: Save type contains content and comments（contents | comments）
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
|
||||
pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
|
||||
save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
|
||||
save_data = []
|
||||
|
||||
async with self.lock:
|
||||
if os.path.exists(save_file_name):
|
||||
async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
|
||||
save_data = json.loads(await file.read())
|
||||
|
||||
save_data.append(save_item)
|
||||
async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
|
||||
await file.write(json.dumps(save_data, ensure_ascii=False, indent=4))
|
||||
|
||||
if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
|
||||
try:
|
||||
await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
|
||||
except:
|
||||
pass
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
content JSON storage implementation
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(content_item, "contents")
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
comment JSON storage implementation
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(comment_item, "comments")
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu content JSON storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
await self.save_data_to_json(creator, "creator")
|
||||
|
||||
|
||||
class XhsSqliteStoreImplement(AbstractStore):
|
||||
async def store_content(self, content_item: Dict):
|
||||
"""
|
||||
Xiaohongshu content SQLite storage implementation
|
||||
Args:
|
||||
content_item: content item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_content,
|
||||
query_content_by_content_id,
|
||||
update_content_by_content_id)
|
||||
note_id = content_item.get("note_id")
|
||||
note_detail: Dict = await query_content_by_content_id(content_id=note_id)
|
||||
if not note_detail:
|
||||
content_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_content(content_item)
|
||||
else:
|
||||
await update_content_by_content_id(note_id, content_item=content_item)
|
||||
|
||||
async def store_comment(self, comment_item: Dict):
|
||||
"""
|
||||
Xiaohongshu comment SQLite storage implementation
|
||||
Args:
|
||||
comment_item: comment item dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_comment,
|
||||
query_comment_by_comment_id,
|
||||
update_comment_by_comment_id)
|
||||
comment_id = comment_item.get("comment_id")
|
||||
comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
|
||||
if not comment_detail:
|
||||
comment_item["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_comment(comment_item)
|
||||
else:
|
||||
await update_comment_by_comment_id(comment_id, comment_item=comment_item)
|
||||
|
||||
async def store_creator(self, creator: Dict):
|
||||
"""
|
||||
Xiaohongshu creator SQLite storage implementation
|
||||
Args:
|
||||
creator: creator dict
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
from .xhs_store_sql import (add_new_creator, query_creator_by_user_id,
|
||||
update_creator_by_user_id)
|
||||
user_id = creator.get("user_id")
|
||||
user_detail: Dict = await query_creator_by_user_id(user_id)
|
||||
if not user_detail:
|
||||
creator["add_ts"] = utils.get_current_timestamp()
|
||||
await add_new_creator(creator)
|
||||
else:
|
||||
await update_creator_by_user_id(user_id, creator)
|
||||
@@ -1,160 +0,0 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : relakkes@gmail.com
|
||||
# @Time : 2024/4/6 15:30
|
||||
# @Desc : sql接口集合
|
||||
|
||||
from typing import Dict, List, Union
|
||||
|
||||
from async_db import AsyncMysqlDB
|
||||
from async_sqlite_db import AsyncSqliteDB
|
||||
from var import media_crawler_db_var
|
||||
|
||||
|
||||
async def query_content_by_content_id(content_id: str) -> Dict:
|
||||
"""
|
||||
查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_note where note_id = '{content_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_content(content_item: Dict) -> int:
|
||||
"""
|
||||
新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_note", content_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
|
||||
"""
|
||||
更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
|
||||
Args:
|
||||
content_id:
|
||||
content_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_note", content_item, "note_id", content_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
|
||||
async def query_comment_by_comment_id(comment_id: str) -> Dict:
|
||||
"""
|
||||
查询一条评论内容
|
||||
Args:
|
||||
comment_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_note_comment where comment_id = '{comment_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_comment(comment_item: Dict) -> int:
|
||||
"""
|
||||
新增一条评论记录
|
||||
Args:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_note_comment", comment_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
|
||||
"""
|
||||
更新增一条评论记录
|
||||
Args:
|
||||
comment_id:
|
||||
comment_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_note_comment", comment_item, "comment_id", comment_id)
|
||||
return effect_row
|
||||
|
||||
|
||||
async def query_creator_by_user_id(user_id: str) -> Dict:
|
||||
"""
|
||||
查询一条创作者记录
|
||||
Args:
|
||||
user_id:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
sql: str = f"select * from xhs_creator where user_id = '{user_id}'"
|
||||
rows: List[Dict] = await async_db_conn.query(sql)
|
||||
if len(rows) > 0:
|
||||
return rows[0]
|
||||
return dict()
|
||||
|
||||
|
||||
async def add_new_creator(creator_item: Dict) -> int:
|
||||
"""
|
||||
新增一条创作者信息
|
||||
Args:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
last_row_id: int = await async_db_conn.item_to_table("xhs_creator", creator_item)
|
||||
return last_row_id
|
||||
|
||||
|
||||
async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
|
||||
"""
|
||||
更新一条创作者信息
|
||||
Args:
|
||||
user_id:
|
||||
creator_item:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
async_db_conn: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
|
||||
effect_row: int = await async_db_conn.update_table("xhs_creator", creator_item, "user_id", user_id)
|
||||
return effect_row
|
||||
Reference in New Issue
Block a user