From c6270b2ed5be9e83bcb8114511641f9c5ad9008d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 4 Jan 2016 03:49:18 +0600 Subject: [PATCH] [ivi:compilation] Fix extraction --- youtube_dl/extractor/ivi.py | 15 ++++++++++----- 1 file 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'(?:[^<]+)' % 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']+data-id="\1"' % compilation_id, html)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -155,7 +158,8 @@ def _real_extract(self, url): 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 @@ def _real_extract(self, url): 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'[^<]+' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + seasons = re.findall( + r'