mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-10-04 05:38:11 +08:00
程序员阿江(Relakkes)
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。
74 lines
3.0 KiB
JSON
74 lines
3.0 KiB
JSON
{
|
|
"section": {
|
|
"targetMatrix": {
|
|
"title": "目标配置",
|
|
"description": "平台、模式与搜索参数"
|
|
},
|
|
"authMatrix": {
|
|
"title": "登录配置",
|
|
"description": "登录方式配置"
|
|
},
|
|
"outputConfig": {
|
|
"title": "输出配置",
|
|
"description": "保存格式与评论选项"
|
|
},
|
|
"runtime": {
|
|
"title": "运行参数",
|
|
"description": "运行时参数"
|
|
}
|
|
},
|
|
"field": {
|
|
"platform": "平台",
|
|
"platformPlaceholder": "选择平台",
|
|
"crawlType": "爬取类型",
|
|
"crawlTypePlaceholder": "选择类型",
|
|
"startPage": "起始页",
|
|
"keywords": "关键词",
|
|
"keywordsHint": "输入关键词后按回车添加",
|
|
"keywordsPlaceholder": "输入关键词，按回车添加...",
|
|
"specifiedIds": "帖子/视频 ID",
|
|
"specifiedIdsHint": "输入帖子或视频的ID/URL，每行一个或用逗号分隔",
|
|
"specifiedIdsPlaceholder": {
|
|
"bili": "示例:\nBV1xxxx\nhttps://www.bilibili.com/video/BV1xxxx",
|
|
"xhs": "示例:\nhttps://www.xiaohongshu.com/explore/xxx?xsec_token=xxx\n(必须包含xsec_token参数)",
|
|
"dy": "示例:\n7525538910311632128\nhttps://www.douyin.com/video/xxx\nhttps://v.douyin.com/xxx (短链接)",
|
|
"wb": "示例:\n4982041758140155\nhttps://weibo.com/xxx/xxx",
|
|
"ks": "示例:\n3xf8enb8dbj6uig\nhttps://www.kuaishou.com/short-video/xxx",
|
|
"default": "输入帖子/视频 ID 或 URL..."
|
|
},
|
|
"creatorIds": "创作者 ID",
|
|
"creatorIdsHint": "输入创作者的ID/URL，每行一个或用逗号分隔",
|
|
"creatorIdsPlaceholder": {
|
|
"bili": "示例:\n434377496\nhttps://space.bilibili.com/434377496",
|
|
"xhs": "示例:\nhttps://www.xiaohongshu.com/user/profile/xxx?xsec_token=xxx\n(必须包含xsec_token参数)",
|
|
"dy": "示例:\nMS4wLjABAAAAxxx\nhttps://www.douyin.com/user/MS4wLjABAAAAxxx",
|
|
"wb": "示例:\n5533390220\nhttps://weibo.com/u/5533390220",
|
|
"ks": "示例:\n3x84qugg4ch9zhs\nhttps://www.kuaishou.com/profile/xxx",
|
|
"default": "输入创作者 ID 或 URL..."
|
|
},
|
|
"loginMethod": "登录方式",
|
|
"loginMethodPlaceholder": "选择登录方式",
|
|
"cookies": "Cookies",
|
|
"cookiesHint": "粘贴 Cookie 字符串",
|
|
"cookiesPlaceholder": "在此粘贴 Cookies...",
|
|
"saveFormat": "保存格式",
|
|
"saveFormatPlaceholder": "选择格式",
|
|
"commentExtraction": "评论抓取",
|
|
"subComments": "子评论",
|
|
"downloadMedia": "下载媒体",
|
|
"downloadMediaHint": "下载封面与视频（图文笔记下载图片），支持小红书/抖音/快手/B站/微博",
|
|
"headlessMode": "无头模式",
|
|
"headlessModeHint": "无 GUI 运行浏览器"
|
|
},
|
|
"button": {
|
|
"initiateScan": "开始爬虫",
|
|
"initiating": "启动中...",
|
|
"terminate": "终止",
|
|
"stopping": "停止中..."
|
|
},
|
|
"warning": {
|
|
"cookieSlider": "[提示] 小红书和抖音平台不建议使用 Cookie 登录，因为可能会触发滑块验证",
|
|
"xhsToken": "[重要] 小红书 URL 必须包含 xsec_token 参数，请从浏览器复制完整 URL"
|
|
}
|
|
}
|