diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-09-09 19:56:16 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-09-09 19:56:16 +0200 |
| commit | 6d2d21f713614141cba09310cb60d2edd76c79ca (patch) | |
| tree | a59ef99ecfc07e7ba23c7bba844ff87b72bf91d9 | |
| parent | 061b2889a9a5a13c6c180932ea742975cdb02948 (diff) | |
| download | youtube-dl-6d2d21f713614141cba09310cb60d2edd76c79ca.tar.xz | |
[sohu] add support for my.tv.sohu.com urls (fixes #1398)
| -rw-r--r-- | youtube_dl/extractor/sohu.py | 16 |
1 files changed, 10 insertions, 6 deletions
diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index 77bb0a8dc..2b9bf0cb7 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -8,7 +8,7 @@ from ..utils import ExtractorError class SohuIE(InfoExtractor): - _VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?' + _VALID_URL = r'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?' _TEST = { u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', @@ -21,8 +21,11 @@ class SohuIE(InfoExtractor): def _real_extract(self, url): - def _fetch_data(vid_id): - base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' + def _fetch_data(vid_id, mytv=False): + if mytv: + base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' + else: + base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' data_url = base_data_url + str(vid_id) data_json = self._download_webpage( data_url, video_id, @@ -31,15 +34,16 @@ class SohuIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + mytv = mobj.group('mytv') is not None webpage = self._download_webpage(url, video_id) raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>', webpage, u'video title') title = raw_title.partition('-')[0].strip() - vid = self._html_search_regex(r'var vid="(\d+)"', webpage, + vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage, u'video path') - data = _fetch_data(vid) + data = _fetch_data(vid, mytv) QUALITIES = ('ori', 'super', 'high', 'nor') vid_ids = [data['data'][q + 'Vid'] @@ -51,7 +55,7 @@ class SohuIE(InfoExtractor): # For now, we just pick the highest available quality vid_id = vid_ids[-1] - format_data = data if vid == vid_id else _fetch_data(vid_id) + format_data = data if vid == vid_id else _fetch_data(vid_id, mytv) part_count = format_data['data']['totalBlocks'] allot = format_data['allot'] prot = format_data['prot'] |