aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/animeondemand.py
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2016-03-18 00:02:34 +0600
committerSergey M․ <dstftw@gmail.com>2016-03-18 00:02:34 +0600
commit85e8f26b827e77cbed6a83268787d450ab2bea3b (patch)
treef95ea7f64b86356081eee04df417f0f087e487c4 /youtube_dl/extractor/animeondemand.py
parentb57fecfdddc78b5ef5cfd1c3302f7b79ab1bf64f (diff)
[animeondemand] Improve extraction
Diffstat (limited to 'youtube_dl/extractor/animeondemand.py')
-rw-r--r--youtube_dl/extractor/animeondemand.py24
1 files changed, 18 insertions, 6 deletions
diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py
index 6cb3a84f9..3631c2451 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)<h3[^>]+class="episodebox-title".+?>Episodeninhalt<', webpage):
- m = re.search(
- r'class="episodebox-title"[^>]+title="(?:Episode|Film)\s*(?P<number>\d+)\s*-\s*(?P<title>.+?)"', 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 = {