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

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_urllib_request,
   9 )
  10 from ..utils import (
  11     int_or_none,
  12     ExtractorError,
  13 )
  14
  15
  16 class VeohIE(InfoExtractor):
  17     _VALID_URL = r'http://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|yapi-)[\da-zA-Z]+)'
  18
  19     _TESTS = [
  20         {
  21             'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
  22             'md5': '620e68e6a3cff80086df3348426c9ca3',
  23             'info_dict': {
  24                 'id': '56314296',
  25                 'ext': 'mp4',
  26                 'title': 'Straight Backs Are Stronger',
  27                 'uploader': 'LUMOback',
  28                 'description': 'At LUMOback, we believe straight backs are stronger.  The LUMOback Posture & Movement Sensor:  It gently vibrates when you slouch, inspiring improved posture and mobility.  Use the app to track your data and improve your posture over time. ',
  29             },
  30         },
  31         {
  32             'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
  33             'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
  34             'info_dict': {
  35                 'id': '27701988',
  36                 'ext': 'mp4',
  37                 'title': 'Chile workers cover up to avoid skin damage',
  38                 'description': 'md5:2bd151625a60a32822873efc246ba20d',
  39                 'uploader': 'afp-news',
  40                 'duration': 123,
  41             },
  42         },
  43         {
  44             'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
  45             'md5': '4fde7b9e33577bab2f2f8f260e30e979',
  46             'note': 'Embedded ooyala video',
  47             'info_dict': {
  48                 'id': '69525809',
  49                 'ext': 'mp4',
  50                 'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
  51                 'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
  52                 'uploader': 'newsy-videos',
  53             },
  54             'skip': 'This video has been deleted.',
  55         },
  56     ]
  57
  58     def _extract_formats(self, source):
  59         formats = []
  60         link = source.get('aowPermalink')
  61         if link:
  62             formats.append({
  63                 'url': link,
  64                 'ext': 'mp4',
  65                 'format_id': 'aow',
  66             })
  67         link = source.get('fullPreviewHashLowPath')
  68         if link:
  69             formats.append({
  70                 'url': link,
  71                 'format_id': 'low',
  72             })
  73         link = source.get('fullPreviewHashHighPath')
  74         if link:
  75             formats.append({
  76                 'url': link,
  77                 'format_id': 'high',
  78             })
  79         return formats
  80
  81     def _extract_video(self, source):
  82         return {
  83             'id': source.get('videoId'),
  84             'title': source.get('title'),
  85             'description': source.get('description'),
  86             'thumbnail': source.get('highResImage') or source.get('medResImage'),
  87             'uploader': source.get('username'),
  88             'duration': int_or_none(source.get('length')),
  89             'view_count': int_or_none(source.get('views')),
  90             'age_limit': 18 if source.get('isMature') == 'true' or source.get('isSexy') == 'true' else 0,
  91             'formats': self._extract_formats(source),
  92         }
  93
  94     def _real_extract(self, url):
  95         mobj = re.match(self._VALID_URL, url)
  96         video_id = mobj.group('id')
  97
  98         if video_id.startswith('v'):
  99             rsp = self._download_xml(
 100                 r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML')
 101             stat = rsp.get('stat')
 102             if stat == 'ok':
 103                 return self._extract_video(rsp.find('./videoList/video'))
 104             elif stat == 'fail':
 105                 raise ExtractorError(
 106                     '%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True)
 107
 108         webpage = self._download_webpage(url, video_id)
 109         age_limit = 0
 110         if 'class="adultwarning-container"' in webpage:
 111             self.report_age_confirmation()
 112             age_limit = 18
 113             request = compat_urllib_request.Request(url)
 114             request.add_header('Cookie', 'confirmedAdult=true')
 115             webpage = self._download_webpage(request, video_id)
 116
 117         m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|"|\?)', webpage)
 118         if m_youtube is not None:
 119             youtube_id = m_youtube.group(1)
 120             self.to_screen('%s: detected Youtube video.' % video_id)
 121             return self.url_result(youtube_id, 'Youtube')
 122
 123         info = json.loads(
 124             self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info').replace('\\\'', '\''))
 125
 126         video = self._extract_video(info)
 127         video['age_limit'] = age_limit
 128
 129         return video