From b03d0d064c0e198aa281faacb2b5a74af7628b74 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 28 Nov 2013 13:49:00 +0100 Subject: [PATCH] [imdb] Fix extraction in python 2.6 Using a regular expression because the html cannot be parsed. --- youtube_dl/extractor/imdb.py | 5 +++-- 1 file 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 @@ def _real_extract(self, url): 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']+class="imdb-player-data"[^>]*?>(.*?)', + format_page, u'json data', flags=re.DOTALL) info = json.loads(json_data) format_info = info['videoPlayerObject']['video'] formats.append({