Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/dailymotion.py

   1 import re
   2 import json
   3 import itertools
   4
   5 from .common import InfoExtractor
   6 from .subtitles import SubtitlesInfoExtractor
   7
   8 from ..utils import (
   9     compat_urllib_request,
  10     compat_str,
  11     get_element_by_attribute,
  12     get_element_by_id,
  13     orderedSet,
  14
  15     ExtractorError,
  16 )
  17
  18 class DailymotionBaseInfoExtractor(InfoExtractor):
  19     @staticmethod
  20     def _build_request(url):
  21         """Build a request with the family filter disabled"""
  22         request = compat_urllib_request.Request(url)
  23         request.add_header('Cookie', 'family_filter=off')
  24         request.add_header('Cookie', 'ff=off')
  25         return request
  26
  27 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
  28     """Information Extractor for Dailymotion"""
  29
  30     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
  31     IE_NAME = u'dailymotion'
  32
  33     _FORMATS = [
  34         (u'stream_h264_ld_url', u'ld'),
  35         (u'stream_h264_url', u'standard'),
  36         (u'stream_h264_hq_url', u'hq'),
  37         (u'stream_h264_hd_url', u'hd'),
  38         (u'stream_h264_hd1080_url', u'hd180'),
  39     ]
  40
  41     _TESTS = [
  42         {
  43             u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
  44             u'file': u'x33vw9.mp4',
  45             u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
  46             u'info_dict': {
  47                 u"uploader": u"Amphora Alex and Van .",
  48                 u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
  49             }
  50         },
  51         # Vevo video
  52         {
  53             u'url': u'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
  54             u'file': u'USUV71301934.mp4',
  55             u'info_dict': {
  56                 u'title': u'Roar (Official)',
  57                 u'uploader': u'Katy Perry',
  58                 u'upload_date': u'20130905',
  59             },
  60             u'params': {
  61                 u'skip_download': True,
  62             },
  63             u'skip': u'VEVO is only available in some countries',
  64         },
  65         # age-restricted video
  66         {
  67             u'url': u'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
  68             u'file': u'xyh2zz.mp4',
  69             u'md5': u'0d667a7b9cebecc3c89ee93099c4159d',
  70             u'info_dict': {
  71                 u'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
  72                 u'uploader': 'HotWaves1012',
  73                 u'age_limit': 18,
  74             }
  75
  76         }
  77     ]
  78
  79     def _real_extract(self, url):
  80         # Extract id and simplified title from URL
  81         mobj = re.match(self._VALID_URL, url)
  82
  83         video_id = mobj.group(1).split('_')[0].split('?')[0]
  84
  85         url = 'http://www.dailymotion.com/video/%s' % video_id
  86
  87         # Retrieve video webpage to extract further information
  88         request = self._build_request(url)
  89         webpage = self._download_webpage(request, video_id)
  90
  91         # Extract URL, uploader and title from webpage
  92         self.report_extraction(video_id)
  93
  94         # It may just embed a vevo video:
  95         m_vevo = re.search(
  96             r'<link rel="video_src" href="[^"]*?vevo.com[^"]*?videoId=(?P<id>[\w]*)',
  97             webpage)
  98         if m_vevo is not None:
  99             vevo_id = m_vevo.group('id')
 100             self.to_screen(u'Vevo video detected: %s' % vevo_id)
 101             return self.url_result(u'vevo:%s' % vevo_id, ie='Vevo')
 102
 103         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
 104                                              # Looking for official user
 105                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
 106                                             webpage, 'video uploader', fatal=False)
 107         age_limit = self._rta_search(webpage)
 108
 109         video_upload_date = None
 110         mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
 111         if mobj is not None:
 112             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
 113
 114         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
 115         embed_page = self._download_webpage(embed_url, video_id,
 116                                             u'Downloading embed page')
 117         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
 118             'video info', flags=re.MULTILINE)
 119         info = json.loads(info)
 120         if info.get('error') is not None:
 121             msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
 122             raise ExtractorError(msg, expected=True)
 123
 124         formats = []
 125         for (key, format_id) in self._FORMATS:
 126             video_url = info.get(key)
 127             if video_url is not None:
 128                 m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
 129                 if m_size is not None:
 130                     width, height = m_size.group(1), m_size.group(2)
 131                 else:
 132                     width, height = None, None
 133                 formats.append({
 134                     'url': video_url,
 135                     'ext': 'mp4',
 136                     'format_id': format_id,
 137                     'width': width,
 138                     'height': height,
 139                 })
 140         if not formats:
 141             raise ExtractorError(u'Unable to extract video URL')
 142
 143         # subtitles
 144         video_subtitles = self.extract_subtitles(video_id, webpage)
 145         if self._downloader.params.get('listsubtitles', False):
 146             self._list_available_subtitles(video_id, webpage)
 147             return
 148
 149         return {
 150             'id':       video_id,
 151             'formats': formats,
 152             'uploader': video_uploader,
 153             'upload_date':  video_upload_date,
 154             'title':    self._og_search_title(webpage),
 155             'subtitles':    video_subtitles,
 156             'thumbnail': info['thumbnail_url'],
 157             'age_limit': age_limit,
 158         }
 159
 160     def _get_available_subtitles(self, video_id, webpage):
 161         try:
 162             sub_list = self._download_webpage(
 163                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
 164                 video_id, note=False)
 165         except ExtractorError as err:
 166             self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
 167             return {}
 168         info = json.loads(sub_list)
 169         if (info['total'] > 0):
 170             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
 171             return sub_lang_list
 172         self._downloader.report_warning(u'video doesn\'t have subtitles')
 173         return {}
 174
 175
 176 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 177     IE_NAME = u'dailymotion:playlist'
 178     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
 179     _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
 180     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
 181
 182     def _extract_entries(self, id):
 183         video_ids = []
 184         for pagenum in itertools.count(1):
 185             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
 186             webpage = self._download_webpage(request,
 187                                              id, u'Downloading page %s' % pagenum)
 188
 189             playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
 190             video_ids.extend(re.findall(r'data-id="(.+?)"', playlist_el))
 191
 192             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 193                 break
 194         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
 195                    for video_id in orderedSet(video_ids)]
 196
 197     def _real_extract(self, url):
 198         mobj = re.match(self._VALID_URL, url)
 199         playlist_id = mobj.group('id')
 200         webpage = self._download_webpage(url, playlist_id)
 201
 202         return {'_type': 'playlist',
 203                 'id': playlist_id,
 204                 'title': get_element_by_id(u'playlist_name', webpage),
 205                 'entries': self._extract_entries(playlist_id),
 206                 }
 207
 208
 209 class DailymotionUserIE(DailymotionPlaylistIE):
 210     IE_NAME = u'dailymotion:user'
 211     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
 212     _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
 213     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
 214
 215     def _real_extract(self, url):
 216         mobj = re.match(self._VALID_URL, url)
 217         user = mobj.group('user')
 218         webpage = self._download_webpage(url, user)
 219         full_user = self._html_search_regex(
 220             r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
 221             webpage, u'user', flags=re.DOTALL)
 222
 223         return {
 224             '_type': 'playlist',
 225             'id': user,
 226             'title': full_user,
 227             'entries': self._extract_entries(user),
 228         }