Merge branch 'subtitles_rework' (closes PR #1326)

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

diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py
index 003b1d8c3e6233368b764e2866431cde13e032f3..360113f9c46840ad4e0f38a8cc9974f36d6a25c5 100644 (file)
--- a/youtube_dl/extractor/dailymotion.py
+++ b/youtube_dl/extractor/dailymotion.py
@@ -1,14 +1,11 @@
 import re
 import json
 import itertools
-import socket
 
 from .common import InfoExtractor
-from .subtitles import NoAutoSubtitlesIE
+from .subtitles import SubtitlesInfoExtractor
 
 from ..utils import (
-    compat_http_client,
-    compat_urllib_error,
     compat_urllib_request,
     compat_str,
     get_element_by_attribute,
@@ -18,33 +15,17 @@ from ..utils import (
 )
 
 
-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, InfoExtractor):
+class DailymotionIE(SubtitlesInfoExtractor):
     """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\""
         }
     }
@@ -56,6 +37,7 @@ class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
         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)
@@ -78,7 +60,8 @@ class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
         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
@@ -95,14 +78,7 @@ class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
         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)
-
+        video_subtitles = self.extract_subtitles(video_id)
         if self._downloader.params.get('listsubtitles', False):
             self._list_available_subtitles(video_id)
             return
@@ -118,6 +94,21 @@ class DailymotionIE(DailyMotionSubtitlesIE, InfoExtractor):
             'thumbnail': info['thumbnail_url']
         }]
 
+    def _get_available_subtitles(self, video_id):
+        try:
+            sub_list = self._download_webpage(
+                'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
+                video_id, note=False)
+        except ExtractorError 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 DailymotionPlaylistIE(InfoExtractor):
     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'