5 from .common import InfoExtractor
8 get_element_by_attribute,
14 class DailymotionIE(InfoExtractor):
15 """Information Extractor for Dailymotion"""
17 _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
18 IE_NAME = u'dailymotion'
20 u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
21 u'file': u'x33vw9.mp4',
22 u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
24 u"uploader": u"Amphora Alex and Van .",
25 u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
29 def _real_extract(self, url):
30 # Extract id and simplified title from URL
31 mobj = re.match(self._VALID_URL, url)
33 video_id = mobj.group(1).split('_')[0].split('?')[0]
35 video_extension = 'mp4'
36 url = 'http://www.dailymotion.com/video/%s' % video_id
38 # Retrieve video webpage to extract further information
39 request = compat_urllib_request.Request(url)
40 request.add_header('Cookie', 'family_filter=off')
41 webpage = self._download_webpage(request, video_id)
43 # Extract URL, uploader and title from webpage
44 self.report_extraction(video_id)
46 video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
47 # Looking for official user
48 r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
49 webpage, 'video uploader')
51 video_upload_date = None
52 mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
54 video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
56 embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
57 embed_page = self._download_webpage(embed_url, video_id,
58 u'Downloading embed page')
59 info = self._search_regex(r'var info = ({.*?}),$', embed_page,
60 'video info', flags=re.MULTILINE)
61 info = json.loads(info)
63 # TODO: support choosing qualities
65 for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
66 'stream_h264_hq_url','stream_h264_url',
67 'stream_h264_ld_url']:
68 if info.get(key):#key in info and info[key]:
70 self.to_screen(u'Using %s' % key)
73 raise ExtractorError(u'Unable to extract video URL')
74 video_url = info[max_quality]
79 'uploader': video_uploader,
80 'upload_date': video_upload_date,
81 'title': self._og_search_title(webpage),
82 'ext': video_extension,
83 'thumbnail': info['thumbnail_url']
87 class DailymotionPlaylistIE(InfoExtractor):
88 _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
89 _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
91 def _real_extract(self, url):
92 mobj = re.match(self._VALID_URL, url)
93 playlist_id = mobj.group('id')
96 for pagenum in itertools.count(1):
97 webpage = self._download_webpage('https://www.dailymotion.com/playlist/%s/%s' % (playlist_id, pagenum),
98 playlist_id, u'Downloading page %s' % pagenum)
100 playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
101 video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
103 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
106 entries = [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
107 for video_id in video_ids]
108 return {'_type': 'playlist',
110 'title': get_element_by_id(u'playlist_name', webpage),