mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-09-21 17:08:11 +08:00
旧实现只覆盖 4 个平台,且把整个文件读进内存、无重试与完整性校验,
代码按平台复制粘贴了 4 份。本次用统一下载器替换:
- 新增 media_downloader/:流式写入、Range 续传、指数退避重试、大小校验、
路径穿越防护;B 站 DASH 音视频分轨下载后交由 ffmpeg 无损合流
- 新增 media_platform/<平台>/media.py:从平台原始响应提取媒体地址,
与下载器解耦;快手首次接入下载能力
- 开关:config.ENABLE_GET_MEDIA 与 --get_media,并打通 API/WebUI;
同时修正旧配置项 ENABLE_GET_MEIDAS 的拼写
- 落盘按帖子聚合:{SAVE_DATA_PATH 或 data}/{platform}/media/{内容ID}/
- B 站装好 ffmpeg 时走 DASH 最高画质,否则降级 mp4 直链(产物 video-durl.mp4,
避免低清文件阻塞后续的高清路径)
- 删除 4 个 *_store_media.py、AbstractStoreImage/Video 及各 client 的媒体 GET 方法
媒体下载失败只记录日志,不中断爬取主流程。
174 lines
7.5 KiB
Python
174 lines
7.5 KiB
Python
# -*- coding: utf-8 -*-
|
|
# Copyright (c) 2025 relakkes@gmail.com
|
|
#
|
|
# This file is part of MediaCrawler project.
|
|
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/store/bilibili/__init__.py
|
|
# GitHub: https://github.com/NanmiCoder
|
|
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
|
|
#
|
|
|
|
# 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 tools.user_hash import anonymize_user_id, mask_nickname
|
|
|
|
from ._store_impl import *
|
|
|
|
|
|
class BiliStoreFactory:
|
|
STORES = {
|
|
"csv": BiliCsvStoreImplement,
|
|
"db": BiliDbStoreImplement,
|
|
"postgres": BiliDbStoreImplement,
|
|
"json": BiliJsonStoreImplement,
|
|
"jsonl": BiliJsonlStoreImplement,
|
|
"sqlite": BiliSqliteStoreImplement,
|
|
"mongodb": BiliMongoStoreImplement,
|
|
"excel": BiliExcelStoreImplement,
|
|
}
|
|
|
|
@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 or mongodb or excel ...")
|
|
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"),
|
|
"creator_hash": anonymize_user_id(video_user_info.get("mid")), # 创作者匿名哈希(不存原始 mid)
|
|
"nickname": mask_nickname(video_user_info.get("name")), # 用户昵称(已脱敏)
|
|
"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):
|
|
# 教学版:UP 主个人资料(昵称/性别/签名/头像/粉丝数等)不再落库,防骚扰。
|
|
return
|
|
|
|
|
|
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"),
|
|
"creator_hash": anonymize_user_id(user_info.get("mid")), # 创作者匿名哈希(不存原始 mid)
|
|
"nickname": mask_nickname(user_info.get("uname")), # 用户昵称(已脱敏)
|
|
"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 batch_update_bilibili_creator_fans(creator_info: Dict, fans_list: List[Dict]):
|
|
# 教学版:不再采集/存储粉丝列表(其他用户的个人信息),防骚扰。
|
|
return
|
|
|
|
|
|
async def batch_update_bilibili_creator_followings(creator_info: Dict, followings_list: List[Dict]):
|
|
# 教学版:不再采集/存储关注列表(其他用户的个人信息),防骚扰。
|
|
return
|
|
|
|
|
|
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):
|
|
# 教学版:UP-粉丝关系表已移除,不再存储联系人信息。
|
|
return
|
|
|
|
|
|
async def update_bilibili_creator_dynamic(creator_info: Dict, dynamic_info: Dict):
|
|
save_dynamic_item = {
|
|
"dynamic_id": dynamic_info["dynamic_id"],
|
|
"creator_hash": anonymize_user_id(creator_info.get("id")), # 创作者匿名哈希(不存原始 ID)
|
|
"user_name": mask_nickname(creator_info.get("name")), # 用户名称(已脱敏)
|
|
"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)
|