Uploading the AI Crawler System: MindSpider
This commit is contained in:
戒酒的李白
@@ -0,0 +1,241 @@
|
||||
# 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})
|
||||
@@ -0,0 +1,318 @@
|
||||
# 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)
|
||||
@@ -0,0 +1,115 @@
|
||||
# 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 ...")
|
||||
@@ -0,0 +1,160 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
# @Author : 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