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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_str,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     clean_html,
  12 )
  13
  14
  15 class MovieClipsIE(InfoExtractor):
  16     _VALID_URL = r'https?://movieclips\.com/(?P<id>[\da-zA-Z]+)(?:-(?P<display_id>[\da-z-]+))?'
  17     _TEST = {
  18         'url': 'http://movieclips.com/Wy7ZU-my-week-with-marilyn-movie-do-you-love-me/',
  19         'info_dict': {
  20             'id': 'Wy7ZU',
  21             'display_id': 'my-week-with-marilyn-movie-do-you-love-me',
  22             'ext': 'mp4',
  23             'title': 'My Week with Marilyn - Do You Love Me?',
  24             'description': 'md5:e86795bd332fe3cff461e7c8dc542acb',
  25             'thumbnail': 're:^https?://.*\.jpg$',
  26         },
  27         'params': {
  28             # rtmp download
  29             'skip_download': True,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('id')
  36         display_id = mobj.group('display_id')
  37         show_id = display_id or video_id
  38
  39         config = self._download_xml(
  40             'http://config.movieclips.com/player/config/%s' % video_id,
  41             show_id, 'Downloading player config')
  42
  43         if config.find('./country-region').text == 'false':
  44             raise ExtractorError(
  45                 '%s said: %s' % (self.IE_NAME, config.find('./region_alert').text), expected=True)
  46
  47         properties = config.find('./video/properties')
  48         smil_file = properties.attrib['smil_file']
  49
  50         smil = self._download_xml(smil_file, show_id, 'Downloading SMIL')
  51         base_url = smil.find('./head/meta').attrib['base']
  52
  53         formats = []
  54         for video in smil.findall('./body/switch/video'):
  55             vbr = int(video.attrib['system-bitrate']) / 1000
  56             src = video.attrib['src']
  57             formats.append({
  58                 'url': base_url,
  59                 'play_path': src,
  60                 'ext': src.split(':')[0],
  61                 'vbr': vbr,
  62                 'format_id': '%dk' % vbr,
  63             })
  64
  65         self._sort_formats(formats)
  66
  67         title = '%s - %s' % (properties.attrib['clip_movie_title'], properties.attrib['clip_title'])
  68         description = clean_html(compat_str(properties.attrib['clip_description']))
  69         thumbnail = properties.attrib['image']
  70         categories = properties.attrib['clip_categories'].split(',')
  71
  72         return {
  73             'id': video_id,
  74             'display_id': display_id,
  75             'title': title,
  76             'description': description,
  77             'thumbnail': thumbnail,
  78             'categories': categories,
  79             'formats': formats,
  80         }