[^<]+?]+?>([^<]+?)',
# Looking for official user
r'<(?:span|a) .*?rel="author".*?>([^<]+?)'],
- webpage, 'video uploader')
+ webpage, 'video uploader', fatal=False)
+ age_limit = self._rta_search(webpage)
video_upload_date = None
mobj = re.search(r'([0-9]{2})-([0-9]{2})-([0-9]{4})
', webpage)
@@ -55,56 +114,115 @@ class DailymotionIE(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
-
- 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]:
- max_quality = key
- self.to_screen(u'Using %s' % key)
- break
- else:
+ if info.get('error') is not None:
+ msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
+ raise ExtractorError(msg, expected=True)
+
+ formats = []
+ for (key, format_id) in self._FORMATS:
+ video_url = info.get(key)
+ if video_url is not None:
+ m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
+ if m_size is not None:
+ width, height = m_size.group(1), m_size.group(2)
+ else:
+ width, height = None, None
+ formats.append({
+ 'url': video_url,
+ 'ext': 'mp4',
+ 'format_id': format_id,
+ 'width': width,
+ 'height': height,
+ })
+ if not formats:
raise ExtractorError(u'Unable to extract video URL')
- video_url = info[max_quality]
- return [{
+ # subtitles
+ video_subtitles = self.extract_subtitles(video_id, webpage)
+ if self._downloader.params.get('listsubtitles', False):
+ self._list_available_subtitles(video_id, webpage)
+ return
+
+ return {
'id': video_id,
- 'url': video_url,
+ 'formats': formats,
'uploader': video_uploader,
'upload_date': video_upload_date,
'title': self._og_search_title(webpage),
- 'ext': video_extension,
- 'thumbnail': info['thumbnail_url']
- }]
-
+ 'subtitles': video_subtitles,
+ 'thumbnail': info['thumbnail_url'],
+ 'age_limit': age_limit,
+ }
-class DailymotionPlaylistIE(InfoExtractor):
+ def _get_available_subtitles(self, video_id, webpage):
+ 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(DailymotionBaseInfoExtractor):
+ IE_NAME = u'dailymotion:playlist'
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P.+?)/'
_MORE_PAGES_INDICATOR = r''
+ _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- playlist_id = mobj.group('id')
+ def _extract_entries(self, 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)
+ request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
+ webpage = self._download_webpage(request,
+ 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))
+ video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
break
+ return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
+ for video_id in orderedSet(video_ids)]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ playlist_id = mobj.group('id')
+ webpage = self._download_webpage(url, playlist_id)
- 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,
+ 'entries': self._extract_entries(playlist_id),
}
+
+
+class DailymotionUserIE(DailymotionPlaylistIE):
+ IE_NAME = u'dailymotion:user'
+ _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P[^/]+)'
+ _MORE_PAGES_INDICATOR = r''
+ _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user = mobj.group('user')
+ webpage = self._download_webpage(url, user)
+ full_user = self._html_search_regex(
+ r'(.*?)' % re.escape(user),
+ webpage, u'user', flags=re.DOTALL)
+
+ return {
+ '_type': 'playlist',
+ 'id': user,
+ 'title': full_user,
+ 'entries': self._extract_entries(user),
+ }