mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-09-20 03:17:55 +08:00
0ca7b29cf0
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。
112 lines
3.2 KiB
Python
112 lines
3.2 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/base/base_crawler.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。
|
|
|
|
from abc import ABC, abstractmethod
|
|
from typing import Dict, Optional
|
|
|
|
from playwright.async_api import BrowserContext, BrowserType, Playwright
|
|
|
|
|
|
class AbstractCrawler(ABC):
|
|
|
|
@abstractmethod
|
|
async def start(self):
|
|
"""
|
|
start crawler
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def search(self):
|
|
"""
|
|
search
|
|
"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def launch_browser(self, chromium: BrowserType, playwright_proxy: Optional[Dict], user_agent: Optional[str], headless: bool = True) -> BrowserContext:
|
|
"""
|
|
launch browser
|
|
:param chromium: chromium browser
|
|
:param playwright_proxy: playwright proxy
|
|
:param user_agent: user agent
|
|
:param headless: headless mode
|
|
:return: browser context
|
|
"""
|
|
pass
|
|
|
|
async def launch_browser_with_cdp(self, playwright: Playwright, playwright_proxy: Optional[Dict], user_agent: Optional[str], headless: bool = True) -> BrowserContext:
|
|
"""
|
|
Launch browser using CDP mode (optional implementation)
|
|
:param playwright: playwright instance
|
|
:param playwright_proxy: playwright proxy configuration
|
|
:param user_agent: user agent
|
|
:param headless: headless mode
|
|
:return: browser context
|
|
"""
|
|
# Default implementation: fallback to standard mode
|
|
return await self.launch_browser(playwright.chromium, playwright_proxy, user_agent, headless)
|
|
|
|
|
|
class AbstractLogin(ABC):
|
|
|
|
@abstractmethod
|
|
async def begin(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def login_by_qrcode(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def login_by_mobile(self):
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def login_by_cookies(self):
|
|
pass
|
|
|
|
|
|
class AbstractStore(ABC):
|
|
|
|
@abstractmethod
|
|
async def store_content(self, content_item: Dict):
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def store_comment(self, comment_item: Dict):
|
|
pass
|
|
|
|
# TODO support all platform
|
|
# only xhs is supported, so @abstractmethod is commented
|
|
@abstractmethod
|
|
async def store_creator(self, creator: Dict):
|
|
pass
|
|
|
|
|
|
class AbstractApiClient(ABC):
|
|
|
|
@abstractmethod
|
|
async def request(self, method, url, **kwargs):
|
|
pass
|
|
|
|
@abstractmethod
|
|
async def update_cookies(self, browser_context: BrowserContext):
|
|
pass
|