diff options
| author | Sergey M․ <dstftw@gmail.com> | 2016-01-04 03:49:18 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-01-04 03:49:18 +0600 |
| commit | c6270b2ed5be9e83bcb8114511641f9c5ad9008d (patch) | |
| tree | 8e6852bdcf800f89444363c7cfdb4ade1215b690 /youtube_dl | |
| parent | ab3176af3472917537635bd96b860a974094b0af (diff) | |
[ivi:compilation] Fix extraction
Diffstat (limited to 'youtube_dl')
| -rw-r--r-- | youtube_dl/extractor/ivi.py | 15 |
1 files changed, 10 insertions, 5 deletions
diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 216c534b5..9ccfee173 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -146,8 +146,11 @@ class IviCompilationIE(InfoExtractor): }] def _extract_entries(self, html, compilation_id): - return [self.url_result('http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), 'Ivi') - for serie in re.findall(r'<strong><a href="/watch/%s/(\d+)">(?:[^<]+)</a></strong>' % compilation_id, html)] + return [ + self.url_result( + 'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key()) + for serie in re.findall( + r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -155,7 +158,8 @@ class IviCompilationIE(InfoExtractor): season_id = mobj.group('seasonid') if season_id is not None: # Season link - season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) + season_page = self._download_webpage( + url, compilation_id, 'Downloading season %s web page' % season_id) playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_title = self._html_search_meta('title', season_page, 'title') entries = self._extract_entries(season_page, compilation_id) @@ -163,8 +167,9 @@ class IviCompilationIE(InfoExtractor): compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') playlist_id = compilation_id playlist_title = self._html_search_meta('title', compilation_page, 'title') - seasons = re.findall(r'<a href="/watch/%s/season(\d+)">[^<]+</a>' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + seasons = re.findall( + r'<a href="/watch/%s/season(\d+)' % compilation_id, compilation_page) + if not seasons: # No seasons in this compilation entries = self._extract_entries(compilation_page, compilation_id) else: entries = [] |