diff options
| author | dst <dstftw@gmail.com> | 2014-01-28 09:12:23 +0700 |
|---|---|---|
| committer | dst <dstftw@gmail.com> | 2014-01-28 09:12:23 +0700 |
| commit | a3978a615950af6e990313820f93baddce067ee4 (patch) | |
| tree | 977cbdc2af4bc8beeb80205621acaa659c711039 | |
| parent | 075911d48ebbf0a7ea54565b08db867c99187d0f (diff) | |
[imdb] Fix duplicated entries bug
| -rw-r--r-- | youtube_dl/extractor/imdb.py | 5 |
1 files changed, 1 insertions, 4 deletions
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 1763af020..7cee505c0 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -69,12 +69,9 @@ class ImdbListIE(InfoExtractor): list_id = mobj.group('id') webpage = self._download_webpage(url, list_id) - list_code = self._search_regex( - r'(?s)<div\s+class="list\sdetail">(.*?)class="see-more"', - webpage, 'list code') entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') - for m in re.findall(r'href="(/video/imdb/vi[^"]+)"', webpage)] + for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)] list_title = self._html_search_regex( r'<h1 class="header">(.*?)</h1>', webpage, 'list title') |