diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2014-09-21 16:32:38 +0200 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2014-09-21 16:32:38 +0200 |
commit | df8f53f752c0f01577dcc5d63c6d9a81d924770b (patch) | |
tree | 5c2f8cf8bd9584d8b31b6687d5cde74033d60a34 /youtube_dl | |
parent | 3ef7d11acdd7347f36b55b97930313fd26809c4d (diff) |
[thvideo] Support mobile URLs as well
Diffstat (limited to 'youtube_dl')
-rw-r--r-- | youtube_dl/extractor/thvideo.py | 20 |
1 files changed, 12 insertions, 8 deletions
diff --git a/youtube_dl/extractor/thvideo.py b/youtube_dl/extractor/thvideo.py index 9fa14d3c4..607e947bb 100644 --- a/youtube_dl/extractor/thvideo.py +++ b/youtube_dl/extractor/thvideo.py @@ -10,7 +10,7 @@ from ..utils import ( class THVideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?thvideo\.tv/v/th(?P<id>[0-9]+)' + _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)' _TEST = { 'url': 'http://thvideo.tv/v/th1987/', 'md5': 'fa107b1f73817e325e9433505a70db50', @@ -30,18 +30,22 @@ class THVideoIE(InfoExtractor): video_id = mobj.group('id') # extract download link from mobile player page - webpage_player = self._download_webpage('http://thvideo.tv/mobile.php?cid=%s-0' % video_id, video_id) - video_url = self._html_search_regex(r'<source src="(.*?)" type', webpage_player, 'video url') + webpage_player = self._download_webpage( + 'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id), + video_id, note='Downloading video source page') + video_url = self._html_search_regex( + r'<source src="(.*?)" type', webpage_player, 'video url') # extract video info from main page - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'http://thvideo.tv/v/th%s' % (video_id), video_id) title = self._og_search_title(webpage) display_id = 'th%s' % video_id thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage) - upload_date_raw = self._html_search_regex(r'span itemprop="datePublished" content="(.*?)">', webpage, - 'upload date', fatal=False) - upload_date = unified_strdate(upload_date_raw) + upload_date = unified_strdate(self._html_search_regex( + r'span itemprop="datePublished" content="(.*?)">', webpage, + 'upload date', fatal=False)) return { 'id': video_id, @@ -52,4 +56,4 @@ class THVideoIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, 'upload_date': upload_date - }
\ No newline at end of file + } |