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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urlparse,
   8     compat_urllib_parse,
   9 )
  10 from ..utils import (
  11     xpath_with_ns,
  12 )
  13
  14
  15 class InternetVideoArchiveIE(InfoExtractor):
  16     _VALID_URL = r'https?://video\.internetvideoarchive\.net/flash/players/.*?\?.*?publishedid.*?'
  17
  18     _TEST = {
  19         'url': 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247',
  20         'info_dict': {
  21             'id': '452693',
  22             'ext': 'mp4',
  23             'title': 'SKYFALL',
  24             'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.',
  25             'duration': 152,
  26         },
  27     }
  28
  29     @staticmethod
  30     def _build_url(query):
  31         return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query
  32
  33     @staticmethod
  34     def _clean_query(query):
  35         NEEDED_ARGS = ['publishedid', 'customerid']
  36         query_dic = compat_urlparse.parse_qs(query)
  37         cleaned_dic = dict((k, v[0]) for (k, v) in query_dic.items() if k in NEEDED_ARGS)
  38         # Other player ids return m3u8 urls
  39         cleaned_dic['playerid'] = '247'
  40         cleaned_dic['videokbrate'] = '100000'
  41         return compat_urllib_parse.urlencode(cleaned_dic)
  42
  43     def _real_extract(self, url):
  44         query = compat_urlparse.urlparse(url).query
  45         query_dic = compat_urlparse.parse_qs(query)
  46         video_id = query_dic['publishedid'][0]
  47         url = self._build_url(query)
  48
  49         flashconfiguration = self._download_xml(url, video_id,
  50                                                 'Downloading flash configuration')
  51         file_url = flashconfiguration.find('file').text
  52         file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx')
  53         # Replace some of the parameters in the query to get the best quality
  54         # and http links (no m3u8 manifests)
  55         file_url = re.sub(r'(?<=\?)(.+)$',
  56                           lambda m: self._clean_query(m.group()),
  57                           file_url)
  58         info = self._download_xml(file_url, video_id,
  59                                   'Downloading video info')
  60         item = info.find('channel/item')
  61
  62         def _bp(p):
  63             return xpath_with_ns(
  64                 p,
  65                 {
  66                     'media': 'http://search.yahoo.com/mrss/',
  67                     'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats',
  68                 }
  69             )
  70         formats = []
  71         for content in item.findall(_bp('media:group/media:content')):
  72             attr = content.attrib
  73             f_url = attr['url']
  74             width = int(attr['width'])
  75             bitrate = int(attr['bitrate'])
  76             format_id = '%d-%dk' % (width, bitrate)
  77             formats.append({
  78                 'format_id': format_id,
  79                 'url': f_url,
  80                 'width': width,
  81                 'tbr': bitrate,
  82             })
  83
  84         self._sort_formats(formats)
  85
  86         return {
  87             'id': video_id,
  88             'title': item.find('title').text,
  89             'formats': formats,
  90             'thumbnail': item.find(_bp('media:thumbnail')).attrib['url'],
  91             'description': item.find('description').text,
  92             'duration': int(attr['duration']),
  93         }