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 97003ee35d77b9018ca592e8bbb7c0589ee550f5..003b1d8c3e6233368b764e2866431cde13e032f3 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,9 +1,10 @@
 import re
 import json
+import itertools
 import socket
 
 from .common import InfoExtractor
-from .subtitles import SubtitlesIE
+from .subtitles import NoAutoSubtitlesIE
 
 from ..utils import (
     compat_http_client,
@@ -17,7 +18,7 @@ from ..utils import (
 )
 
 
-class DailyMotionSubtitlesIE(SubtitlesIE):
+class DailyMotionSubtitlesIE(NoAutoSubtitlesIE):
 
     def _get_available_subtitles(self, video_id):
         request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id)
@@ -33,12 +34,7 @@ class DailyMotionSubtitlesIE(SubtitlesIE):
         self._downloader.report_warning(u'video doesn\'t have subtitles')
         return {}
 
-    def _request_automatic_caption(self, video_id, webpage):
-        self._downloader.report_warning(u'Automatic Captions not supported by this server')
-        return {}
-
-
-class DailymotionIE(DailyMotionSubtitlesIE):
+class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
     """Information Extractor for Dailymotion"""
 
     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
@@ -48,7 +44,7 @@ class DailymotionIE(DailyMotionSubtitlesIE):
         u'file': u'x33vw9.mp4',
         u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
         u'info_dict': {
-            u"uploader": u"Alex and Van .",
+            u"uploader": u"Alex and Van .", 
             u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
         }
     }
@@ -87,12 +83,12 @@ class DailymotionIE(DailyMotionSubtitlesIE):
 
         # 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')
@@ -121,3 +117,31 @@ 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,
+                }