diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-29 13:42:08 +0200 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2013-08-29 13:42:08 +0200 |
| commit | 54fda45bace9d37135a4d29a03130b22ed272ce5 (patch) | |
| tree | 1554c485bc9faac1d1d6985d6221c5dc0db97081 | |
| parent | c7bf7366bc0d4d1c4fc9c81ee5d33bf3c3512aa5 (diff) | |
| parent | b5ba7b9dcfed5ded96c841a0ebbbf12132de838f (diff) | |
| download | youtube-dl-54fda45bace9d37135a4d29a03130b22ed272ce5.tar.gz youtube-dl-54fda45bace9d37135a4d29a03130b22ed272ce5.tar.xz youtube-dl-54fda45bace9d37135a4d29a03130b22ed272ce5.zip | |
Merge pull request #1342 from whydoubt/fix_mit_26
Fix MIT extractor for Python 2.6
| -rw-r--r-- | youtube_dl/extractor/mit.py | 16 |
1 files changed, 7 insertions, 9 deletions
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index d09d03e36..52be9232f 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -25,23 +25,21 @@ class TechTVMITIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage( + raw_page = self._download_webpage( 'http://techtv.mit.edu/videos/%s' % video_id, video_id) - embed_page = self._download_webpage( - 'http://techtv.mit.edu/embeds/%s/' % video_id, video_id, - note=u'Downloading embed page') + clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page) base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)', - embed_page, u'base url') - formats_json = self._search_regex(r'bitrates: (\[.+?\])', embed_page, + raw_page, u'base url') + formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page, u'video formats') formats = json.loads(formats_json) formats = sorted(formats, key=lambda f: f['bitrate']) - title = get_element_by_id('edit-title', webpage) - description = clean_html(get_element_by_id('edit-description', webpage)) + title = get_element_by_id('edit-title', clean_page) + description = clean_html(get_element_by_id('edit-description', clean_page)) thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'', - embed_page, u'thumbnail', flags=re.DOTALL) + raw_page, u'thumbnail', flags=re.DOTALL) return {'id': video_id, 'title': title, |