mirror of
https://github.com/NanmiCoder/MediaCrawler.git
synced 2026-10-09 03:48:12 +08:00
feat(ks): 支持分享短链 /f/<token> 形式的视频输入
快手分享短链 https://www.kuaishou.com/f/X9Idt15MQb9L2cv 路径里是 share_token 而不是视频 ID,它只做 302 跳转,真实地址在 Location 里。原先的解析器只认 /short-video/<id> 和纯 ID,遇到短链会抛 ValueError 被 continue 掉——只有一行 ERROR 日志,看起来像"爬了但没数据"。 - help.py: 新增 /f/<token> 分支,返回 url_type="short"(token 不是视频 ID, 必须跟随重定向),并补上第三种形式的文档 - client.py: 新增 resolve_short_url,GET 时 follow_redirects=False,读 301/302/303/307/308 的 Location - core.py: url_type == "short" 时先解析短链再解析一次,失败则跳过该条 - 新增 tests/test_kuaishou_url_parse.py(6 条,不发网络请求) 验证:两条真实短链分别解析到 3xyziwesje8e9jg / 3xbbkdxtxqm8sae,详情均成功; 带 query 的标准视频页不会被误判成短链。
This commit is contained in:
@@ -204,6 +204,24 @@ class KuaishouCrawler(AbstractCrawler):
|
||||
for video_url in config.KS_SPECIFIED_ID_LIST:
|
||||
try:
|
||||
video_info = parse_video_info_from_url(video_url)
|
||||
|
||||
# 分享短链(/f/xxx)要先跟随 302 重定向,才能拿到 /short-video/<id>
|
||||
if video_info.url_type == "short":
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.get_specified_videos] Resolving short link: {video_url}"
|
||||
)
|
||||
resolved_url = await self.ks_client.resolve_short_url(video_url)
|
||||
if resolved_url:
|
||||
video_info = parse_video_info_from_url(resolved_url)
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.get_specified_videos] Short link resolved to video ID: {video_info.video_id}"
|
||||
)
|
||||
else:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.get_specified_videos] Failed to resolve short link: {video_url}"
|
||||
)
|
||||
continue
|
||||
|
||||
video_ids.append(video_info.video_id)
|
||||
utils.logger.info(f"Parsed video ID: {video_info.video_id} from {video_url}")
|
||||
except ValueError as e:
|
||||
|
||||
Reference in New Issue
Block a user