youtube_dl/extractor/dailymotion.py

   1 import re
   2 import json
   3 import itertools
   4 import socket
   5
   6 from .common import InfoExtractor
   7 from .subtitles import SubtitlesIE
   8
   9 from ..utils import (
  10     compat_http_client,
  11     compat_urllib_error,
  12     compat_urllib_request,
  13     compat_str,
  14     get_element_by_attribute,
  15     get_element_by_id,
  16
  17     ExtractorError,
  18 )
  19
  20
  21 class DailyMotionSubtitlesIE(SubtitlesIE):
  22
  23     def _get_available_subtitles(self, video_id):
  24         request = compat_urllib_request.Request('https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id)
  25         try:
  26             sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
  27         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
  28             self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
  29             return {}
  30         info = json.loads(sub_list)
  31         if (info['total'] > 0):
  32             sub_lang_list = dict((l['language'], l['url']) for l in info['list'])
  33             return sub_lang_list
  34         self._downloader.report_warning(u'video doesn\'t have subtitles')
  35         return {}
  36
  37     def _get_subtitle_url(self, sub_lang, sub_name, video_id, format):
  38         sub_lang_list = self._get_available_subtitles(video_id)
  39         return sub_lang_list[sub_lang]
  40
  41     def _request_automatic_caption(self, video_id, webpage):
  42         self._downloader.report_warning(u'Automatic Captions not supported by dailymotion')
  43         return {}
  44
  45
  46 class DailymotionIE(DailyMotionSubtitlesIE): #,InfoExtractor):
  47     """Information Extractor for Dailymotion"""
  48
  49     _VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
  50     IE_NAME = u'dailymotion'
  51     _TEST = {
  52         u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
  53         u'file': u'x33vw9.mp4',
  54         u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
  55         u'info_dict': {
  56             u"uploader": u"Alex and Van .",
  57             u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
  58         }
  59     }
  60
  61     def _real_extract(self, url):
  62         # Extract id and simplified title from URL
  63         mobj = re.match(self._VALID_URL, url)
  64
  65         video_id = mobj.group(1).split('_')[0].split('?')[0]
  66
  67         video_extension = 'mp4'
  68
  69         # Retrieve video webpage to extract further information
  70         request = compat_urllib_request.Request(url)
  71         request.add_header('Cookie', 'family_filter=off')
  72         webpage = self._download_webpage(request, video_id)
  73
  74         # Extract URL, uploader and title from webpage
  75         self.report_extraction(video_id)
  76
  77         video_uploader = self._search_regex([r'(?im)<span class="owner[^\"]+?">[^<]+?<a [^>]+?>([^<]+?)</a>',
  78                                              # Looking for official user
  79                                              r'<(?:span|a) .*?rel="author".*?>([^<]+?)</'],
  80                                             webpage, 'video uploader')
  81
  82         video_upload_date = None
  83         mobj = re.search(r'<div class="[^"]*uploaded_cont[^"]*" title="[^"]*">([0-9]{2})-([0-9]{2})-([0-9]{4})</div>', webpage)
  84         if mobj is not None:
  85             video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
  86
  87         embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
  88         embed_page = self._download_webpage(embed_url, video_id,
  89                                             u'Downloading embed page')
  90         info = self._search_regex(r'var info = ({.*?}),', embed_page, 'video info')
  91         info = json.loads(info)
  92
  93         # TODO: support choosing qualities
  94
  95         for key in ['stream_h264_hd1080_url', 'stream_h264_hd_url',
  96                     'stream_h264_hq_url', 'stream_h264_url',
  97                     'stream_h264_ld_url']:
  98             if info.get(key):  # key in info and info[key]:
  99                 max_quality = key
 100                 self.to_screen(u'%s: Using %s' % (video_id, key))
 101                 break
 102         else:
 103             raise ExtractorError(u'Unable to extract video URL')
 104         video_url = info[max_quality]
 105
 106         # subtitles
 107         video_subtitles = None
 108         video_webpage = None
 109
 110         if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
 111             video_subtitles = self._extract_subtitles(video_id)
 112         elif self._downloader.params.get('writeautomaticsub', False):
 113             video_subtitles = self._request_automatic_caption(video_id, video_webpage)
 114
 115         if self._downloader.params.get('listsubtitles', False):
 116             self._list_available_subtitles(video_id)
 117             return
 118
 119         if 'length_seconds' not in info:
 120             self._downloader.report_warning(u'unable to extract video duration')
 121             video_duration = ''
 122         else:
 123             video_duration = compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])
 124
 125         return [{
 126             'id':       video_id,
 127             'url':      video_url,
 128             'uploader': video_uploader,
 129             'upload_date':  video_upload_date,
 130             'title':    self._og_search_title(webpage),
 131             'ext':      video_extension,
 132             'subtitles':    video_subtitles,
 133             'thumbnail': info['thumbnail_url']
 134         }]