github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-29 14:50:47 +00:00
Code Issues Projects Releases Packages Wiki Activity

[imdb] Fix extraction in python 2.6

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