mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-10-31 22:55:26 +00:00
[tmz:article] Fix extraction (closes #11052)
This commit is contained in:
parent
ebc7ab1e23
commit
5d47b38cf5
2 changed files with 9 additions and 8 deletions
|
@ -1,6 +1,7 @@
|
||||||
version <unreleased>
|
version <unreleased>
|
||||||
|
|
||||||
Extractors
|
Extractors
|
||||||
|
* [tmz:article] Fix extraction (#11052)
|
||||||
* [mitele] Fix extraction after website redesign (#10824)
|
* [mitele] Fix extraction after website redesign (#10824)
|
||||||
|
|
||||||
|
|
||||||
|
|
|
@ -32,12 +32,15 @@ class TMZArticleIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
|
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
|
'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
|
||||||
'md5': 'e482a414a38db73087450e3a6ce69d00',
|
'md5': '3316ff838ae5bb7f642537825e1e90d2',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '0_6snoelag',
|
'id': '0_6snoelag',
|
||||||
'ext': 'mp4',
|
'ext': 'mov',
|
||||||
'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
|
'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
|
||||||
'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
|
'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
|
||||||
|
'timestamp': 1429467813,
|
||||||
|
'upload_date': '20150419',
|
||||||
|
'uploader_id': 'batchUser',
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -45,12 +48,9 @@ class TMZArticleIE(InfoExtractor):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
embedded_video_info_str = self._html_search_regex(
|
embedded_video_info = self._parse_json(self._html_search_regex(
|
||||||
r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
|
r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
|
||||||
|
video_id)
|
||||||
embedded_video_info = self._parse_json(
|
|
||||||
embedded_video_info_str, video_id,
|
|
||||||
transform_source=lambda s: s.replace('\\', ''))
|
|
||||||
|
|
||||||
return self.url_result(
|
return self.url_result(
|
||||||
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])
|
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])
|
||||||
|
|
Loading…
Reference in a new issue