]>
Commit | Line | Data |
---|---|---|
1 | from __future__ import unicode_literals | |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..compat import ( | |
7 | compat_urlparse, | |
8 | ) | |
9 | from ..utils import ( | |
10 | ExtractorError, | |
11 | int_or_none, | |
12 | float_or_none, | |
13 | ) | |
14 | ||
15 | ||
16 | class UstreamIE(InfoExtractor): | |
17 | _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)' | |
18 | IE_NAME = 'ustream' | |
19 | _TESTS = [{ | |
20 | 'url': 'http://www.ustream.tv/recorded/20274954', | |
21 | 'md5': '088f151799e8f572f84eb62f17d73e5c', | |
22 | 'info_dict': { | |
23 | 'id': '20274954', | |
24 | 'ext': 'flv', | |
25 | 'uploader': 'Young Americans for Liberty', | |
26 | 'title': 'Young Americans for Liberty February 7, 2012 2:28 AM', | |
27 | }, | |
28 | }, { | |
29 | # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444 | |
30 | # Title and uploader available only from params JSON | |
31 | 'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct', | |
32 | 'md5': '5a2abf40babeac9812ed20ae12d34e10', | |
33 | 'info_dict': { | |
34 | 'id': '59307601', | |
35 | 'ext': 'flv', | |
36 | 'title': '-CG11- Canada Games Figure Skating', | |
37 | 'uploader': 'sportscanadatv', | |
38 | } | |
39 | }] | |
40 | ||
41 | def _real_extract(self, url): | |
42 | m = re.match(self._VALID_URL, url) | |
43 | video_id = m.group('id') | |
44 | ||
45 | # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990) | |
46 | if m.group('type') == 'embed/recorded': | |
47 | video_id = m.group('id') | |
48 | desktop_url = 'http://www.ustream.tv/recorded/' + video_id | |
49 | return self.url_result(desktop_url, 'Ustream') | |
50 | if m.group('type') == 'embed': | |
51 | video_id = m.group('id') | |
52 | webpage = self._download_webpage(url, video_id) | |
53 | desktop_video_id = self._html_search_regex( | |
54 | r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id') | |
55 | desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id | |
56 | return self.url_result(desktop_url, 'Ustream') | |
57 | ||
58 | params = self._download_json( | |
59 | 'https://api.ustream.tv/videos/%s.json' % video_id, video_id) | |
60 | ||
61 | error = params.get('error') | |
62 | if error: | |
63 | raise ExtractorError( | |
64 | '%s returned error: %s' % (self.IE_NAME, error), expected=True) | |
65 | ||
66 | video = params['video'] | |
67 | ||
68 | title = video['title'] | |
69 | filesize = float_or_none(video.get('file_size')) | |
70 | ||
71 | formats = [{ | |
72 | 'id': format_id, | |
73 | 'url': video_url, | |
74 | 'ext': format_id, | |
75 | 'filesize': filesize, | |
76 | } for format_id, video_url in video['media_urls'].items()] | |
77 | self._sort_formats(formats) | |
78 | ||
79 | description = video.get('description') | |
80 | timestamp = int_or_none(video.get('created_at')) | |
81 | duration = float_or_none(video.get('length')) | |
82 | view_count = int_or_none(video.get('views')) | |
83 | ||
84 | uploader = video.get('owner', {}).get('username') | |
85 | uploader_id = video.get('owner', {}).get('id') | |
86 | ||
87 | thumbnails = [{ | |
88 | 'id': thumbnail_id, | |
89 | 'url': thumbnail_url, | |
90 | } for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()] | |
91 | ||
92 | return { | |
93 | 'id': video_id, | |
94 | 'title': title, | |
95 | 'description': description, | |
96 | 'thumbnails': thumbnails, | |
97 | 'timestamp': timestamp, | |
98 | 'duration': duration, | |
99 | 'view_count': view_count, | |
100 | 'uploader': uploader, | |
101 | 'uploader_id': uploader_id, | |
102 | 'formats': formats, | |
103 | } | |
104 | ||
105 | ||
106 | class UstreamChannelIE(InfoExtractor): | |
107 | _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' | |
108 | IE_NAME = 'ustream:channel' | |
109 | _TEST = { | |
110 | 'url': 'http://www.ustream.tv/channel/channeljapan', | |
111 | 'info_dict': { | |
112 | 'id': '10874166', | |
113 | }, | |
114 | 'playlist_mincount': 17, | |
115 | } | |
116 | ||
117 | def _real_extract(self, url): | |
118 | m = re.match(self._VALID_URL, url) | |
119 | display_id = m.group('slug') | |
120 | webpage = self._download_webpage(url, display_id) | |
121 | channel_id = self._html_search_meta('ustream:channel_id', webpage) | |
122 | ||
123 | BASE = 'http://www.ustream.tv' | |
124 | next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id | |
125 | video_ids = [] | |
126 | while next_url: | |
127 | reply = self._download_json( | |
128 | compat_urlparse.urljoin(BASE, next_url), display_id, | |
129 | note='Downloading video information (next: %d)' % (len(video_ids) + 1)) | |
130 | video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) | |
131 | next_url = reply['nextUrl'] | |
132 | ||
133 | entries = [ | |
134 | self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream') | |
135 | for vid in video_ids] | |
136 | return { | |
137 | '_type': 'playlist', | |
138 | 'id': channel_id, | |
139 | 'display_id': display_id, | |
140 | 'entries': entries, | |
141 | } |