From 85e8f26b827e77cbed6a83268787d450ab2bea3b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 18 Mar 2016 00:02:34 +0600 Subject: [PATCH] [animeondemand] Improve extraction --- youtube_dl/extractor/animeondemand.py | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 6cb3a84f9f..3631c24516 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -30,6 +30,10 @@ class AnimeOnDemandIE(InfoExtractor): # Film wording is used instead of Episode 'url': 'https://www.anime-on-demand.de/anime/39', 'only_matching': True, + }, { + # Episodes without titles + 'url': 'https://www.anime-on-demand.de/anime/162', + 'only_matching': True, }] def _login(self): @@ -95,14 +99,22 @@ class AnimeOnDemandIE(InfoExtractor): entries = [] - for episode_html in re.findall(r'(?s)]+class="episodebox-title".+?>Episodeninhalt<', webpage): - m = re.search( - r'class="episodebox-title"[^>]+title="(?:Episode|Film)\s*(?P\d+)\s*-\s*(?P.+?)"', episode_html) - if not m: + for num, episode_html in enumerate(re.findall( + r'(?s)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage)): + episodebox_title = self._search_regex( + (r'class="episodebox-title"[^>]+title="(.+?)"', + r'class="episodebox-title"[^>]+>(.+?)<'), + webpage, 'episodebox title', default=None) + if not episodebox_title: continue - episode_number = int(m.group('number')) - episode_title = m.group('title') + episode_number = int(self._search_regex( + r'^(?:Episode|Film)\s*(\d+)', + episodebox_title, 'episode number', default=num)) + episode_title = self._search_regex( + r'(?:Episode|Film)\s*\d+\s*-\s*(?P<title>.+?)', + episodebox_title, 'episode title', default=None) + video_id = 'episode-%d' % episode_number common_info = {