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 5fd2221a798403ff4832bf6992b8724bdf74f964..f54ecc569cbe02714df09cdaf55c72ffd7129895 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,14 +1,39 @@
 import re
 import json
+import socket
 
 from .common import InfoExtractor
+from .subtitles import NoAutoSubtitlesIE
+
 from ..utils import (
+    compat_http_client,
+    compat_urllib_error,
     compat_urllib_request,
+    compat_str,
+    get_element_by_attribute,
+    get_element_by_id,
 
     ExtractorError,
 )
 
-class DailymotionIE(InfoExtractor):
+
+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)
+        try:
+            sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
+        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
+            self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
+            return {}
+        info = json.loads(sub_list)
+        if (info['total'] > 0):
+            sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
+            return sub_lang_list
+        self._downloader.report_warning(u'video doesn\'t have subtitles')
+        return {}
+
+class DailymotionIE(DailyMotionSubtitlesIE):
     """Information Extractor for Dailymotion"""
 
     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
@@ -18,7 +43,7 @@ class DailymotionIE(InfoExtractor):
         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\""
         }
     }
@@ -39,9 +64,6 @@ class DailymotionIE(InfoExtractor):
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
 
-        video_title = self._html_search_regex(r'<meta property="og:title" content="(.*?)" />',
-                                              webpage, 'title')
-
         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
                                              # Looking for official user
                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
@@ -63,20 +85,62 @@ class DailymotionIE(InfoExtractor):
         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'Using %s' % key)
+                self.to_screen(u'%s: Using %s' % (video_id, key))
                 break
         else:
             raise ExtractorError(u'Unable to extract video URL')
         video_url = info[max_quality]
 
+        # subtitles
+        video_subtitles = None
+        video_webpage = None
+
+        if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
+            video_subtitles = self._extract_subtitles(video_id)
+        elif self._downloader.params.get('writeautomaticsub', False):
+            video_subtitles = self._request_automatic_caption(video_id, video_webpage)
+
+        if self._downloader.params.get('listsubtitles', False):
+            self._list_available_subtitles(video_id)
+            return
+
         return [{
             'id':       video_id,
             'url':      video_url,
             'uploader': video_uploader,
             'upload_date':  video_upload_date,
-            'title':    video_title,
+            'title':    self._og_search_title(webpage),
             'ext':      video_extension,
+            '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,
+                }