]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/ninecninemedia.py
Update changelog
[youtubedl] / 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 self._sort_formats(formats)
38
39 return {
40 'id': stack_id,
41 'formats': formats,
42 }
43
44
45 class NineCNineMediaIE(NineCNineMediaBaseIE):
46 IE_NAME = '9c9media'
47 _VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
48
49 def _real_extract(self, url):
50 destination_code, content_id = re.match(self._VALID_URL, url).groups()
51 api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
52 content = self._download_json(api_base_url, content_id, query={
53 '$include': '[Media,Season,ContentPackages]',
54 })
55 title = content['Name']
56 if len(content['ContentPackages']) > 1:
57 raise ExtractorError('multiple content packages')
58 content_package = content['ContentPackages'][0]
59 package_id = content_package['Id']
60 content_package_url = api_base_url + 'contentpackages/%s/' % package_id
61 content_package = self._download_json(content_package_url, content_id)
62
63 if content_package.get('Constraints', {}).get('Security', {}).get('Type') == 'adobe-drm':
64 raise ExtractorError('This video is DRM protected.', expected=True)
65
66 stacks = self._download_json(content_package_url + 'stacks/', package_id)['Items']
67 multistacks = len(stacks) > 1
68
69 thumbnails = []
70 for image in content.get('Images', []):
71 image_url = image.get('Url')
72 if not image_url:
73 continue
74 thumbnails.append({
75 'url': image_url,
76 'width': int_or_none(image.get('Width')),
77 'height': int_or_none(image.get('Height')),
78 })
79
80 tags, categories = [], []
81 for source_name, container in (('Tags', tags), ('Genres', categories)):
82 for e in content.get(source_name, []):
83 e_name = e.get('Name')
84 if not e_name:
85 continue
86 container.append(e_name)
87
88 description = content.get('Desc') or content.get('ShortDesc')
89 season = content.get('Season', {})
90 base_info = {
91 'description': description,
92 'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
93 'episode_number': int_or_none(content.get('Episode')),
94 'season': season.get('Name'),
95 'season_number': season.get('Number'),
96 'season_id': season.get('Id'),
97 'series': content.get('Media', {}).get('Name'),
98 'tags': tags,
99 'categories': categories,
100 }
101
102 entries = []
103 for stack in stacks:
104 stack_id = compat_str(stack['Id'])
105 entry = {
106 '_type': 'url_transparent',
107 'url': '9c9media:stack:%s:%s:%s:%s' % (destination_code, content_id, package_id, stack_id),
108 'id': stack_id,
109 'title': '%s_part%s' % (title, stack['Name']) if multistacks else title,
110 'duration': float_or_none(stack.get('Duration')),
111 'ie_key': 'NineCNineMediaStack',
112 }
113 entry.update(base_info)
114 entries.append(entry)
115
116 return {
117 '_type': 'multi_video',
118 'id': content_id,
119 'title': title,
120 'description': description,
121 'entries': entries,
122 }