diff options
| author | Jaime Marquínez Ferrándiz <[email protected]> | 2013-11-28 13:49:00 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <[email protected]> | 2013-11-28 13:49:00 +0100 |
| commit | b03d0d064c0e198aa281faacb2b5a74af7628b74 (patch) | |
| tree | f05746780cb7d5dd1eabebd1d863f08d90ed658a | |
| parent | d8d6148628b972b6998a8c2a5465f031a44f4004 (diff) | |
| download | youtube-dl-b03d0d064c0e198aa281faacb2b5a74af7628b74.tar.gz youtube-dl-b03d0d064c0e198aa281faacb2b5a74af7628b74.zip | |
[imdb] Fix extraction in python 2.6
Using a regular expression because the html cannot be parsed.
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 07e4f7d29..520edc7d0 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -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({ |