aboutsummaryrefslogtreecommitdiffhomepage
path: root/youtube_dl/extractor/anvato.py
diff options
context:
space:
mode:
authorSergey M․ <[email protected]>2016-11-04 21:17:56 +0700
committerSergey M․ <[email protected]>2016-11-04 21:17:56 +0700
commitf93ac1d17571d6ddf9cfb56f0bb51bdef6a04799 (patch)
treef397fb7f3c6eea163e1912c773c456db9aa90fe1 /youtube_dl/extractor/anvato.py
parentc4c9b8440cd19838a1ef283cc54ebf0630905698 (diff)
downloadyoutube-dl-f93ac1d17571d6ddf9cfb56f0bb51bdef6a04799.tar.gz
youtube-dl-f93ac1d17571d6ddf9cfb56f0bb51bdef6a04799.zip
[anvato] Extract more metadata
Diffstat (limited to 'youtube_dl/extractor/anvato.py')
-rw-r--r--youtube_dl/extractor/anvato.py21
1 files changed, 13 insertions, 8 deletions
diff --git a/youtube_dl/extractor/anvato.py b/youtube_dl/extractor/anvato.py
index cb29cf111..46ca1899e 100644
--- a/youtube_dl/extractor/anvato.py
+++ b/youtube_dl/extractor/anvato.py
@@ -157,14 +157,7 @@ class AnvatoIE(InfoExtractor):
video_data_url, video_id, transform_source=strip_jsonp,
data=json.dumps(payload).encode('utf-8'))
- def _extract_anvato_videos(self, webpage, video_id):
- anvplayer_data = self._parse_json(self._html_search_regex(
- r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
- 'Anvato player data'), video_id)
-
- video_id = anvplayer_data['video']
- access_key = anvplayer_data['accessKey']
-
+ def _get_anvato_videos(self, access_key, video_id):
video_data = self._get_video_json(access_key, video_id)
formats = []
@@ -218,7 +211,19 @@ class AnvatoIE(InfoExtractor):
'formats': formats,
'title': video_data.get('def_title'),
'description': video_data.get('def_description'),
+ 'tags': video_data.get('def_tags', '').split(','),
'categories': video_data.get('categories'),
'thumbnail': video_data.get('thumbnail'),
+ 'timestamp': int_or_none(video_data.get(
+ 'ts_published') or video_data.get('ts_added')),
+ 'uploader': video_data.get('mcp_id'),
+ 'duration': int_or_none(video_data.get('duration')),
'subtitles': subtitles,
}
+
+ def _extract_anvato_videos(self, webpage, video_id):
+ anvplayer_data = self._parse_json(self._html_search_regex(
+ r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
+ 'Anvato player data'), video_id)
+ return self._get_anvato_videos(
+ anvplayer_data['accessKey'], anvplayer_data['video'])