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
  14     ExtractorError,
  15 )
  16
  17 class DailymotionBaseInfoExtractor(InfoExtractor):
  18     @staticmethod
  19     def _build_request(url):
  20         """Build a request with the family filter disabled"""
  21         request = compat_urllib_request.Request(url)
  22         request.add_header('Cookie', 'family_filter=off')
  23         return request
  24
  25 class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor):
  26     """Information Extractor for Dailymotion"""
  27
  28     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/(?:embed/)?video/([^/]+)'
  29     IE_NAME = u'dailymotion'
  30     _TEST = {
  31         u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
  32         u'file': u'x33vw9.mp4',
  33         u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
  34         u'info_dict': {
  35             u"uploader": u"Amphora Alex and Van .",
  36             u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
  37         }
  38     }
  39
  40     def _real_extract(self, url):
  41         # Extract id and simplified title from URL
  42         mobj = re.match(self._VALID_URL, url)
  43
  44         video_id = mobj.group(1).split('_')[0].split('?')[0]
  45
  46         video_extension = 'mp4'
  47         url = 'http://www.dailymotion.com/video/%s' % video_id
  48
  49         # Retrieve video webpage to extract further information
  50         request = self._build_request(url)
  51         webpage = self._download_webpage(request, video_id)
  52
  53         # Extract URL, uploader and title from webpage
  54         self.report_extraction(video_id)
  55
  56         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
  57                                              # Looking for official user
  58                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
  59                                             webpage, 'video uploader')
  60
  61         video_upload_date = None
  62         mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
  63         if mobj is not None:
  64             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
  65
  66         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
  67         embed_page = self._download_webpage(embed_url, video_id,
  68                                             u'Downloading embed page')
  69         info = self._search_regex(r'var info = ({.*?}),$', embed_page,
  70             'video info', flags=re.MULTILINE)
  71         info = json.loads(info)
  72         if info.get('error') is not None:
  73             msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
  74             raise ExtractorError(msg, expected=True)
  75
  76         # TODO: support choosing qualities
  77
  78         for key in ['stream_h264_hd1080_url','stream_h264_hd_url',
  79                     'stream_h264_hq_url','stream_h264_url',
  80                     'stream_h264_ld_url']:
  81             if info.get(key):#key in info and info[key]:
  82                 max_quality = key
  83                 self.to_screen(u'Using %s' % key)
  84                 break
  85         else:
  86             raise ExtractorError(u'Unable to extract video URL')
  87         video_url = info[max_quality]
  88
  89         # subtitles
  90         video_subtitles = self.extract_subtitles(video_id)
  91         if self._downloader.params.get('listsubtitles', False):
  92             self._list_available_subtitles(video_id)
  93             return
  94
  95         return [{
  96             'id':       video_id,
  97             'url':      video_url,
  98             'uploader': video_uploader,
  99             'upload_date':  video_upload_date,
 100             'title':    self._og_search_title(webpage),
 101             'ext':      video_extension,
 102             'subtitles':    video_subtitles,
 103             'thumbnail': info['thumbnail_url']
 104         }]
 105
 106     def _get_available_subtitles(self, video_id):
 107         try:
 108             sub_list = self._download_webpage(
 109                 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
 110                 video_id, note=False)
 111         except ExtractorError as err:
 112             self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
 113             return {}
 114         info = json.loads(sub_list)
 115         if (info['total'] > 0):
 116             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
 117             return sub_lang_list
 118         self._downloader.report_warning(u'video doesn\'t have subtitles')
 119         return {}
 120
 121
 122 class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
 123     IE_NAME = u'dailymotion:playlist'
 124     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>.+?)/'
 125     _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/playlist/.+?".*?>.*?</a>.*?</div>'
 126     _PAGE_TEMPLATE = 'https://www.dailymotion.com/playlist/%s/%s'
 127
 128     def _extract_entries(self, id):
 129         video_ids = []
 130         for pagenum in itertools.count(1):
 131             request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum))
 132             webpage = self._download_webpage(request,
 133                                              id, u'Downloading page %s' % pagenum)
 134
 135             playlist_el = get_element_by_attribute(u'class', u'video_list', webpage)
 136             video_ids.extend(re.findall(r'data-id="(.+?)" data-ext-id', playlist_el))
 137
 138             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 139                 break
 140         return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
 141                    for video_id in video_ids]
 142
 143     def _real_extract(self, url):
 144         mobj = re.match(self._VALID_URL, url)
 145         playlist_id = mobj.group('id')
 146         webpage = self._download_webpage(url, playlist_id)
 147
 148         return {'_type': 'playlist',
 149                 'id': playlist_id,
 150                 'title': get_element_by_id(u'playlist_name', webpage),
 151                 'entries': self._extract_entries(playlist_id),
 152                 }
 153
 154
 155 class DailymotionUserIE(DailymotionPlaylistIE):
 156     IE_NAME = u'dailymotion:user'
 157     _VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
 158     _MORE_PAGES_INDICATOR = r'<div class="next">.*?<a.*?href="/user/.+?".*?>.*?</a>.*?</div>'
 159     _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
 160
 161     def _real_extract(self, url):
 162         mobj = re.match(self._VALID_URL, url)
 163         user = mobj.group('user')
 164         webpage = self._download_webpage(url, user)
 165         full_user = self._html_search_regex(
 166             r'<a class="label" href="/%s".*?>(.*?)</' % re.escape(user),
 167             webpage, u'user', flags=re.DOTALL)
 168
 169         return {
 170             '_type': 'playlist',
 171             'id': user,
 172             'title': full_user,
 173             'entries': self._extract_entries(user),
 174         }