]>
Commit | Line | Data |
---|---|---|
0eb799ba JMF |
1 | from __future__ import unicode_literals |
2 | ||
78af8eb1 PH |
3 | import re |
4 | ||
5 | from .common import InfoExtractor | |
1cc79574 | 6 | from ..compat import ( |
74ac9bdd | 7 | compat_urlparse, |
74ac9bdd | 8 | ) |
5820c4a2 S |
9 | from ..utils import ( |
10 | ExtractorError, | |
11 | int_or_none, | |
12 | float_or_none, | |
13 | ) | |
78af8eb1 PH |
14 | |
15 | ||
16 | class UstreamIE(InfoExtractor): | |
4853eb63 | 17 | _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)' |
0eb799ba | 18 | IE_NAME = 'ustream' |
cd9fdccd | 19 | _TESTS = [{ |
0eb799ba | 20 | 'url': 'http://www.ustream.tv/recorded/20274954', |
0eb799ba JMF |
21 | 'md5': '088f151799e8f572f84eb62f17d73e5c', |
22 | 'info_dict': { | |
9e875391 S |
23 | 'id': '20274954', |
24 | 'ext': 'flv', | |
9e875391 | 25 | 'title': 'Young Americans for Liberty February 7, 2012 2:28 AM', |
40fbb05e S |
26 | 'description': 'Young Americans for Liberty February 7, 2012 2:28 AM', |
27 | 'timestamp': 1328577035, | |
28 | 'upload_date': '20120207', | |
29 | 'uploader': 'yaliberty', | |
30 | 'uploader_id': '6780869', | |
0eb799ba | 31 | }, |
cd9fdccd YCH |
32 | }, { |
33 | # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444 | |
34 | # Title and uploader available only from params JSON | |
35 | 'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct', | |
36 | 'md5': '5a2abf40babeac9812ed20ae12d34e10', | |
37 | 'info_dict': { | |
38 | 'id': '59307601', | |
39 | 'ext': 'flv', | |
40 | 'title': '-CG11- Canada Games Figure Skating', | |
41 | 'uploader': 'sportscanadatv', | |
40fbb05e S |
42 | }, |
43 | 'skip': 'This Pro Broadcaster has chosen to remove this video from the ustream.tv site.', | |
67d46a3f YCH |
44 | }, { |
45 | 'url': 'http://www.ustream.tv/embed/10299409', | |
46 | 'info_dict': { | |
47 | 'id': '10299409', | |
48 | }, | |
49 | 'playlist_count': 3, | |
cd9fdccd | 50 | }] |
78af8eb1 PH |
51 | |
52 | def _real_extract(self, url): | |
53 | m = re.match(self._VALID_URL, url) | |
4853eb63 | 54 | video_id = m.group('id') |
b702eceb | 55 | |
e5a66240 | 56 | # some sites use this embed format (see: https://github.com/rg3/youtube-dl/issues/2990) |
9e875391 | 57 | if m.group('type') == 'embed/recorded': |
4853eb63 | 58 | video_id = m.group('id') |
b702eceb | 59 | desktop_url = 'http://www.ustream.tv/recorded/' + video_id |
60 | return self.url_result(desktop_url, 'Ustream') | |
5c386252 | 61 | if m.group('type') == 'embed': |
4853eb63 | 62 | video_id = m.group('id') |
5c386252 | 63 | webpage = self._download_webpage(url, video_id) |
67d46a3f YCH |
64 | content_video_ids = self._parse_json(self._search_regex( |
65 | r'ustream\.vars\.offAirContentVideoIds=([^;]+);', webpage, | |
66 | 'content video IDs'), video_id) | |
67 | return self.playlist_result( | |
68 | map(lambda u: self.url_result('http://www.ustream.tv/recorded/' + u, 'Ustream'), content_video_ids), | |
69 | video_id) | |
5c386252 | 70 | |
4853eb63 S |
71 | params = self._download_json( |
72 | 'https://api.ustream.tv/videos/%s.json' % video_id, video_id) | |
f8610ba1 | 73 | |
5820c4a2 S |
74 | error = params.get('error') |
75 | if error: | |
76 | raise ExtractorError( | |
77 | '%s returned error: %s' % (self.IE_NAME, error), expected=True) | |
78af8eb1 | 78 | |
5820c4a2 | 79 | video = params['video'] |
2a813727 | 80 | |
41db7333 S |
81 | title = video['title'] |
82 | filesize = float_or_none(video.get('file_size')) | |
83 | ||
5820c4a2 | 84 | formats = [{ |
dc5756fd | 85 | 'id': video_id, |
5820c4a2 S |
86 | 'url': video_url, |
87 | 'ext': format_id, | |
41db7333 | 88 | 'filesize': filesize, |
5820c4a2 S |
89 | } for format_id, video_url in video['media_urls'].items()] |
90 | self._sort_formats(formats) | |
78af8eb1 | 91 | |
5820c4a2 S |
92 | description = video.get('description') |
93 | timestamp = int_or_none(video.get('created_at')) | |
94 | duration = float_or_none(video.get('length')) | |
5820c4a2 | 95 | view_count = int_or_none(video.get('views')) |
cd9fdccd | 96 | |
5820c4a2 S |
97 | uploader = video.get('owner', {}).get('username') |
98 | uploader_id = video.get('owner', {}).get('id') | |
78af8eb1 | 99 | |
5820c4a2 S |
100 | thumbnails = [{ |
101 | 'id': thumbnail_id, | |
102 | 'url': thumbnail_url, | |
103 | } for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()] | |
0eb799ba JMF |
104 | |
105 | return { | |
106 | 'id': video_id, | |
5820c4a2 S |
107 | 'title': title, |
108 | 'description': description, | |
109 | 'thumbnails': thumbnails, | |
110 | 'timestamp': timestamp, | |
111 | 'duration': duration, | |
5820c4a2 | 112 | 'view_count': view_count, |
0eb799ba | 113 | 'uploader': uploader, |
5820c4a2 S |
114 | 'uploader_id': uploader_id, |
115 | 'formats': formats, | |
0eb799ba JMF |
116 | } |
117 | ||
bfd5c93a | 118 | |
bfd5c93a | 119 | class UstreamChannelIE(InfoExtractor): |
120 | _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)' | |
0eb799ba | 121 | IE_NAME = 'ustream:channel' |
22a6f150 PH |
122 | _TEST = { |
123 | 'url': 'http://www.ustream.tv/channel/channeljapan', | |
124 | 'info_dict': { | |
125 | 'id': '10874166', | |
126 | }, | |
446a03bd | 127 | 'playlist_mincount': 17, |
22a6f150 | 128 | } |
bfd5c93a | 129 | |
130 | def _real_extract(self, url): | |
131 | m = re.match(self._VALID_URL, url) | |
22a6f150 PH |
132 | display_id = m.group('slug') |
133 | webpage = self._download_webpage(url, display_id) | |
44789f24 | 134 | channel_id = self._html_search_meta('ustream:channel_id', webpage) |
bfd5c93a | 135 | |
bfd5c93a | 136 | BASE = 'http://www.ustream.tv' |
137 | next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id | |
a921f407 | 138 | video_ids = [] |
bfd5c93a | 139 | while next_url: |
22a6f150 PH |
140 | reply = self._download_json( |
141 | compat_urlparse.urljoin(BASE, next_url), display_id, | |
142 | note='Downloading video information (next: %d)' % (len(video_ids) + 1)) | |
a921f407 | 143 | video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data'])) |
bfd5c93a | 144 | next_url = reply['nextUrl'] |
bfd5c93a | 145 | |
22a6f150 PH |
146 | entries = [ |
147 | self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream') | |
148 | for vid in video_ids] | |
149 | return { | |
150 | '_type': 'playlist', | |
151 | 'id': channel_id, | |
152 | 'display_id': display_id, | |
153 | 'entries': entries, | |
154 | } |