mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-10-02 09:58:12 +08:00
feat(media): 重构媒体下载,支持 xhs/dy/ks/bili/wb 五平台
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。
This commit is contained in:
@@ -29,7 +29,6 @@ from var import source_keyword_var
|
||||
from tools.user_hash import anonymize_user_id, mask_nickname
|
||||
|
||||
from ._store_impl import *
|
||||
from .bilibilli_store_media import *
|
||||
|
||||
|
||||
class BiliStoreFactory:
|
||||
@@ -116,21 +115,6 @@ async def update_bilibili_video_comment(video_id: str, comment_item: Dict):
|
||||
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]):
|
||||
# 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
|
||||
|
||||
@@ -1,82 +0,0 @@
|
||||
# -*- 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/bilibilli_store_media.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 : helloteemo
|
||||
# @Time : 2024/7/12 20:01
|
||||
# @Desc : Bilibili media storage
|
||||
import pathlib
|
||||
from typing import Dict
|
||||
|
||||
import aiofiles
|
||||
|
||||
from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
|
||||
from tools import utils
|
||||
import config
|
||||
|
||||
|
||||
class BilibiliVideo(AbstractStoreVideo):
|
||||
def __init__(self):
|
||||
if config.SAVE_DATA_PATH:
|
||||
self.video_store_path = f"{config.SAVE_DATA_PATH}/bili/videos"
|
||||
else:
|
||||
self.video_store_path = "data/bili/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 ...")
|
||||
Reference in New Issue
Block a user