minhngoc25a
/
yt-dlc
mirror of https://github.com/blackjack4494/yt-dlc
1
0
Fork 1
Code Issues Releases Wiki Activity

[imdb] Fix extraction in python 2.6 

Using a regular expression because the html cannot be parsed.
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-11-28 13:49:00 +01:00
parent d8d6148628
commit b03d0d064c
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/imdb.py
View File

@ -38,8 +38,9 @@ class ImdbIE(InfoExtractor):
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
u'Downloading info for %s format' % f_id)
json_data = get_element_by_attribute('class', 'imdb-player-data',
format_page)
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, u'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
formats.append({