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