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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     parse_iso8601,
  10     float_or_none,
  11     ExtractorError,
  12     int_or_none,
  13 )
  14
  15
  16 class NineCNineMediaBaseIE(InfoExtractor):
  17     _API_BASE_TEMPLATE = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/'
  18
  19
  20 class NineCNineMediaStackIE(NineCNineMediaBaseIE):
  21     IE_NAME = '9c9media:stack'
  22     _GEO_COUNTRIES = ['CA']
  23     _VALID_URL = r'9c9media:stack:(?P<destination_code>[^:]+):(?P<content_id>\d+):(?P<content_package>\d+):(?P<id>\d+)'
  24
  25     def _real_extract(self, url):
  26         destination_code, content_id, package_id, stack_id = re.match(self._VALID_URL, url).groups()
  27         stack_base_url_template = self._API_BASE_TEMPLATE + 'contentpackages/%s/stacks/%s/manifest.'
  28         stack_base_url = stack_base_url_template % (destination_code, content_id, package_id, stack_id)
  29
  30         formats = []
  31         formats.extend(self._extract_m3u8_formats(
  32             stack_base_url + 'm3u8', stack_id, 'mp4',
  33             'm3u8_native', m3u8_id='hls', fatal=False))
  34         formats.extend(self._extract_f4m_formats(
  35             stack_base_url + 'f4m', stack_id,
  36             f4m_id='hds', fatal=False))
  37         mp4_url = self._download_webpage(stack_base_url + 'pd', stack_id, fatal=False)
  38         if mp4_url:
  39             formats.append({
  40                 'url': mp4_url,
  41                 'format_id': 'mp4',
  42             })
  43         self._sort_formats(formats)
  44
  45         return {
  46             'id': stack_id,
  47             'formats': formats,
  48         }
  49
  50
  51 class NineCNineMediaIE(NineCNineMediaBaseIE):
  52     IE_NAME = '9c9media'
  53     _VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
  54
  55     def _real_extract(self, url):
  56         destination_code, content_id = re.match(self._VALID_URL, url).groups()
  57         api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
  58         content = self._download_json(api_base_url, content_id, query={
  59             '$include': '[Media,Season,ContentPackages]',
  60         })
  61         title = content['Name']
  62         if len(content['ContentPackages']) > 1:
  63             raise ExtractorError('multiple content packages')
  64         content_package = content['ContentPackages'][0]
  65         package_id = content_package['Id']
  66         content_package_url = api_base_url + 'contentpackages/%s/' % package_id
  67         content_package = self._download_json(content_package_url, content_id)
  68
  69         if content_package.get('Constraints', {}).get('Security', {}).get('Type') == 'adobe-drm':
  70             raise ExtractorError('This video is DRM protected.', expected=True)
  71
  72         stacks = self._download_json(content_package_url + 'stacks/', package_id)['Items']
  73         multistacks = len(stacks) > 1
  74
  75         thumbnails = []
  76         for image in content.get('Images', []):
  77             image_url = image.get('Url')
  78             if not image_url:
  79                 continue
  80             thumbnails.append({
  81                 'url': image_url,
  82                 'width': int_or_none(image.get('Width')),
  83                 'height': int_or_none(image.get('Height')),
  84             })
  85
  86         tags, categories = [], []
  87         for source_name, container in (('Tags', tags), ('Genres', categories)):
  88             for e in content.get(source_name, []):
  89                 e_name = e.get('Name')
  90                 if not e_name:
  91                     continue
  92                 container.append(e_name)
  93
  94         description = content.get('Desc') or content.get('ShortDesc')
  95         season = content.get('Season', {})
  96         base_info = {
  97             'description': description,
  98             'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
  99             'episode_number': int_or_none(content.get('Episode')),
 100             'season': season.get('Name'),
 101             'season_number': season.get('Number'),
 102             'season_id': season.get('Id'),
 103             'series': content.get('Media', {}).get('Name'),
 104             'tags': tags,
 105             'categories': categories,
 106         }
 107
 108         entries = []
 109         for stack in stacks:
 110             stack_id = compat_str(stack['Id'])
 111             entry = {
 112                 '_type': 'url_transparent',
 113                 'url': '9c9media:stack:%s:%s:%s:%s' % (destination_code, content_id, package_id, stack_id),
 114                 'id': stack_id,
 115                 'title': '%s_part%s' % (title, stack['Name']) if multistacks else title,
 116                 'duration': float_or_none(stack.get('Duration')),
 117                 'ie_key': 'NineCNineMediaStack',
 118             }
 119             entry.update(base_info)
 120             entries.append(entry)
 121
 122         return {
 123             '_type': 'multi_video',
 124             'id': content_id,
 125             'title': title,
 126             'description': description,
 127             'entries': entries,
 128         }