Merge branch 'master' into subtitles_rework

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

diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 8fab16005781c54012d0c048979193bd4a5bcb10..f7dffd4cce3a1fc2d04bd016111aa354717072a6 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,5 +1,6 @@
 import re
 import json
+import itertools
 import socket
 
 from .common import InfoExtractor
@@ -33,17 +34,17 @@ class DailyMotionSubtitlesIE(NoAutoSubtitlesIE):
         self._downloader.report_warning(u'video doesn\'t have subtitles')
         return {}
 
-class DailymotionIE(DailyMotionSubtitlesIE):
+class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
     """Information Extractor for Dailymotion"""
 
-    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
+    _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
     IE_NAME = u'dailymotion'
     _TEST = {
         u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
         u'file': u'x33vw9.mp4',
         u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
         u'info_dict': {
-            u"uploader": u"Alex and Van .",
+            u"uploader": u"Amphora Alex and Van .", 
             u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
         }
     }
@@ -55,6 +56,7 @@ class DailymotionIE(DailyMotionSubtitlesIE):
         video_id = mobj.group(1).split('_')[0].split('?')[0]
 
         video_extension = 'mp4'
+        url = 'http://www.dailymotion.com/video/%s' % video_id
 
         # Retrieve video webpage to extract further information
         request = compat_urllib_request.Request(url)
@@ -77,17 +79,18 @@ class DailymotionIE(DailyMotionSubtitlesIE):
         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
         embed_page = self._download_webpage(embed_url, video_id,
                                             u'Downloading embed page')
-        info = self._search_regex(r'var info = ({.*?}),', embed_page, 'video info')
+        info = self._search_regex(r'var info = ({.*?}),$', embed_page,
+            'video info', flags=re.MULTILINE)
         info = json.loads(info)
 
         # TODO: support choosing qualities
 
-        for key in ['stream_h264_hd1080_url', 'stream_h264_hd_url',
-                    'stream_h264_hq_url', 'stream_h264_url',
+        for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
+                    'stream_h264_hq_url','stream_h264_url',
                     'stream_h264_ld_url']:
-            if info.get(key):  # key in info and info[key]:
+            if info.get(key):#key in info and info[key]:
                 max_quality = key
-                self.to_screen(u'%s: Using %s' % (video_id, key))
+                self.to_screen(u'Using %s' % key)
                 break
         else:
             raise ExtractorError(u'Unable to extract video URL')
@@ -116,3 +119,31 @@ class DailymotionIE(DailyMotionSubtitlesIE):
             'subtitles':    video_subtitles,
             'thumbnail': info['thumbnail_url']
         }]
+
+
+class DailymotionPlaylistIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
+    _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        playlist_id =  mobj.group('id')
+        video_ids = []
+
+        for pagenum in itertools.count(1):
+            webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum),
+                                             playlist_id, u'Downloading page %s' % pagenum)
+
+            playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
+            video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
+
+            if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
+                break
+
+        entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+                   for video_id in video_ids]
+        return {'_type': 'playlist',
+                'id': playlist_id,
+                'title': get_element_by_id(u'playlist_name', webpage),
+                'entries': entries,
+                }