Merge remote-tracking branch 'gabeos/crunchyroll-show-playlist'

[youtube-dl] / youtube_dl / extractor / crunchyroll.py

diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py
index f99888ecc378ea2a5404fe42d8d32a6a8c4093fb..2dca5266000db8ed558f149142e3b235e267a910 100644 (file)
--- a/youtube_dl/extractor/crunchyroll.py
+++ b/youtube_dl/extractor/crunchyroll.py
@@ -24,6 +24,7 @@ from ..aes import (
     aes_cbc_decrypt,
     inc,
 )
+from .common import InfoExtractor
 
 
 class CrunchyrollIE(SubtitlesInfoExtractor):
@@ -39,6 +40,7 @@ class CrunchyrollIE(SubtitlesInfoExtractor):
             'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
             'uploader': 'Yomiuri Telecasting Corporation (YTV)',
             'upload_date': '20131013',
+            'url': 're:(?!.*&amp)',
         },
         'params': {
             # rtmp
@@ -237,12 +239,14 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format
             streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
             streamdata_req.add_header('Content-Length', str(len(streamdata_req.data)))
-            streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format)
-            video_url = self._search_regex(r'<host>([^<]+)', streamdata, 'video_url')
-            video_play_path = self._search_regex(r'<file>([^<]+)', streamdata, 'video_play_path')
+            streamdata = self._download_xml(
+                streamdata_req, video_id,
+                note='Downloading media info for %s' % video_format)
+            video_url = streamdata.find('.//host').text
+            video_play_path = streamdata.find('.//file').text
             formats.append({
                 'url': video_url,
-                'play_path':   video_play_path,
+                'play_path': video_play_path,
                 'ext': 'flv',
                 'format': video_format,
                 'format_id': video_format,
@@ -285,3 +289,38 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
             'subtitles':   subtitles,
             'formats':     formats,
         }
+
+
+class CrunchyrollShowPlaylistIE(InfoExtractor):
+    IE_NAME = "crunchyroll:playlist"
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<show>[\w\-]+))/?$'
+    _TITLE_EXTR = r'<span\s+itemprop="name">\s*(?P<showtitle>[\w\s]+)'
+
+    _TESTS = [{
+        'url' : 'http://www.crunchyroll.com/attack-on-titan',
+        'info_dict' : {
+            'title' : 'Attack on Titan'
+        },
+        'playlist_count' : 15
+    }]
+
+    def _extract_title_entries(self,id,webpage):
+        _EPISODE_ID_EXTR = r'id="showview_videos_media_(?P<vidid>\d+)".*?href="/{0}/(?P<vidurl>[\w\-]+-(?P=vidid))"'.format(id)
+        title = self._html_search_regex(self._TITLE_EXTR,webpage,"title",flags=re.UNICODE|re.MULTILINE)
+        episode_urls = [self.url_result('http://www.crunchyroll.com/{0}/{1}'.format(id, showmatch[1])) for
+                    showmatch in re.findall(_EPISODE_ID_EXTR, webpage,re.UNICODE|re.MULTILINE|re.DOTALL)]
+        episode_urls.reverse()
+        return title, episode_urls
+
+
+    def _real_extract(self, url):
+        url_match = re.match(self._VALID_URL,url)
+        show_id = url_match.group('show')
+        webpage = self._download_webpage(url,show_id)
+        (title,entries) = self._extract_title_entries(show_id,webpage)
+        return {
+            '_type' : 'playlist',
+            'id' : show_id,
+            'title' : title,
+            'entries' : entries
+        }
\ No newline at end of file