aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-11-08 21:53:41 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-11-08 21:53:41 +0800
commit5d47b38cf5acb252e126ebdd81a21b5035256bed (patch)
treecae3eab8db03458a43b159c967165e76b86650ce
parentebc7ab1e231483f189290608425a23590cae6af9 (diff)
downloadyoutube-dl-5d47b38cf5acb252e126ebdd81a21b5035256bed.tar.xz
[tmz:article] Fix extraction (closes #11052)
-rw-r--r--ChangeLog1
-rw-r--r--youtube_dl/extractor/tmz.py16
2 files changed, 9 insertions, 8 deletions
diff --git a/ChangeLog b/ChangeLog
index 7ca72b3d7..78c78afcd 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,6 +1,7 @@
version <unreleased>
Extractors
+* [tmz:article] Fix extraction (#11052)
* [mitele] Fix extraction after website redesign (#10824)
diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py
index 979856e9a..419f9d92e 100644
--- a/youtube_dl/extractor/tmz.py
+++ b/youtube_dl/extractor/tmz.py
@@ -32,12 +32,15 @@ class TMZArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
_TEST = {
'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
- 'md5': 'e482a414a38db73087450e3a6ce69d00',
+ 'md5': '3316ff838ae5bb7f642537825e1e90d2',
'info_dict': {
'id': '0_6snoelag',
- 'ext': 'mp4',
+ 'ext': 'mov',
'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."',
+ 'timestamp': 1429467813,
+ 'upload_date': '20150419',
+ 'uploader_id': 'batchUser',
}
}
@@ -45,12 +48,9 @@ class TMZArticleIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
- embedded_video_info_str = self._html_search_regex(
- r'tmzVideoEmbedV2\("([^)]+)"\);', webpage, 'embedded video info')
-
- embedded_video_info = self._parse_json(
- embedded_video_info_str, video_id,
- transform_source=lambda s: s.replace('\\', ''))
+ embedded_video_info = self._parse_json(self._html_search_regex(
+ r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
+ video_id)
return self.url_result(
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])