youtube_dl/extractor/movieclips.py

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