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:
程序员阿江(Relakkes)
2026-09-18 17:23:20 +08:00
parent 1e1ae64cb4
commit c7e6c9fdc0
4 changed files with 132 additions and 0 deletions
+73
View File
@@ -0,0 +1,73 @@
# -*- coding: utf-8 -*-
# Copyright (c) 2025 relakkes@gmail.com
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/tests/test_kuaishou_url_parse.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
"""快手视频输入解析的回归测试。
覆盖三种输入形态:
1. 纯视频 ID
2. 标准视频页 ``/short-video/<id>``
3. 分享短链 ``/f/<share_token>`` —— 注意路径里是 **share_token 而不是视频 ID**,
必须跟随 302 重定向才能拿到真实 ID,所以只标记 ``url_type="short"`` 交给调用方。
这里只测纯函数,不发网络请求。
"""
from __future__ import annotations
import pytest
from media_platform.kuaishou.help import parse_video_info_from_url
def test_pure_video_id_is_normal():
info = parse_video_info_from_url("3xf8enb8dbj6uig")
assert info.video_id == "3xf8enb8dbj6uig"
assert info.url_type == "normal"
def test_short_video_url_is_normal():
info = parse_video_info_from_url(
"https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke"
"?authorId=3x84qugg4ch9zhs&streamSource=search&area=searchxxnull&searchKey=python"
)
assert info.video_id == "3x3zxz4mjrsc8ke"
assert info.url_type == "normal"
def test_share_short_link_is_marked_short():
"""分享短链必须标记为 short —— 路径里的 token 不是视频 ID"""
info = parse_video_info_from_url("https://www.kuaishou.com/f/X9Idt15MQb9L2cv")
assert info.video_id == "X9Idt15MQb9L2cv"
assert info.url_type == "short"
def test_share_short_link_with_dash_in_token():
info = parse_video_info_from_url("https://www.kuaishou.com/f/X-a8vLyTxvEvN2jg")
assert info.video_id == "X-a8vLyTxvEvN2jg"
assert info.url_type == "short"
def test_short_video_url_is_not_confused_with_share_link():
"""带 query 的标准视频页不能被误判成短链"""
info = parse_video_info_from_url(
"https://www.kuaishou.com/short-video/3xyziwesje8e9jg"
"?shareToken=X9Idt15MQb9L2cv&shareObjectId=3xyziwesje8e9jg"
)
assert info.video_id == "3xyziwesje8e9jg"
assert info.url_type == "normal"
def test_unparsable_url_raises():
with pytest.raises(ValueError):
parse_video_info_from_url("https://www.kuaishou.com/profile/3x84qugg4ch9zhs")