parsehub 2.2.2__tar.gz → 2.2.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {parsehub-2.2.2/src/parsehub.egg-info → parsehub-2.2.3}/PKG-INFO +1 -1
- {parsehub-2.2.2 → parsehub-2.2.3}/pyproject.toml +1 -1
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/__init__.py +2 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/xhs.py +8 -0
- {parsehub-2.2.2 → parsehub-2.2.3/src/parsehub.egg-info}/PKG-INFO +1 -1
- {parsehub-2.2.2 → parsehub-2.2.3}/test/test_core_offline.py +1 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/LICENSE +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/README.md +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/setup.cfg +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/cli.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/cli_config.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/config/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/config/config.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/errors.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/base/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/base/base.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/base/ytdlp.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/bilibili.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/coolapk.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/douban.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/douyin.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/facebook.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/instagram.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/kuaishou.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/pipix.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/snapchat.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/threads.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/tieba.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/tiktok.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/twitter.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/weibo.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/weixin.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/xiaoheihe.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/youtube.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/zhihu.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/parsers/parser/zuiyou.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/bilibili.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/coolapk.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/douban.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/douyin.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/instagram.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/kuaishou.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/pipix.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/threads.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/tieba.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/tiktok.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/twitter.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/weibo.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/weixin.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/xhs.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/xiaoheihe.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/zhihu.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/provider_api/zuiyou.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/__init__.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/callback.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/media_file.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/media_ref.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/platform.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/post.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/types/result.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/utils/downloader.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/utils/helpers.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub/utils/media_info.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub.egg-info/SOURCES.txt +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub.egg-info/dependency_links.txt +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub.egg-info/entry_points.txt +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub.egg-info/requires.txt +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/src/parsehub.egg-info/top_level.txt +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/test/test_cli.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/test/test_cli_config.py +0 -0
- {parsehub-2.2.2 → parsehub-2.2.3}/test/test_downloader.py +0 -0
|
@@ -24,6 +24,14 @@ class XHSParser(BaseParser):
|
|
|
24
24
|
__redirect_keywords__ = ["xhslink"]
|
|
25
25
|
__after_clean_parameters__ = ["xsec_token"]
|
|
26
26
|
|
|
27
|
+
async def get_raw_url(self, url: str, *, clean_all: bool = False, headers: dict | None = None) -> str:
|
|
28
|
+
url = await super().get_raw_url(url, clean_all=clean_all, headers=headers)
|
|
29
|
+
if "/login" in url:
|
|
30
|
+
raise ParseError("该帖子需要登录后查看")
|
|
31
|
+
elif "/404" in url:
|
|
32
|
+
raise ParseError("帖子不存在")
|
|
33
|
+
return url
|
|
34
|
+
|
|
27
35
|
async def _do_parse(self, raw_url: str) -> Union["VideoParseResult", "ImageParseResult", "MultimediaParseResult"]:
|
|
28
36
|
xhs = XHSAPI(proxy=self.proxy, cookie=self.cookie.get_value())
|
|
29
37
|
result = await xhs.extract(raw_url)
|
|
@@ -660,6 +660,7 @@ class TestPlatformUrlMatching(unittest.TestCase):
|
|
|
660
660
|
"https://www.zhihu.com/question/2057559076813510452",
|
|
661
661
|
"https://zhuanlan.zhihu.com/p/1989096494578558904",
|
|
662
662
|
"https://www.zhihu.com/question/597674895/answer/3004370705",
|
|
663
|
+
"https://daily.zhihu.com/story/9792555",
|
|
663
664
|
],
|
|
664
665
|
}
|
|
665
666
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|