aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ustream.py
blob: 9fdeb064d20cd1f4a64cd0891f04d8481f943066 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..compat import (
    compat_urlparse,
)
from ..utils import (
    ExtractorError,
    int_or_none,
    float_or_none,
)


class UstreamIE(InfoExtractor):
    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed|embed/recorded)/(?P<id>\d+)'
    IE_NAME = 'ustream'
    _TESTS = [{
        'url': 'http://www.ustream.tv/recorded/20274954',
        'md5': '088f151799e8f572f84eb62f17d73e5c',
        'info_dict': {
            'id': '20274954',
            'ext': 'flv',
            'uploader': 'Young Americans for Liberty',
            'title': 'Young Americans for Liberty February 7, 2012 2:28 AM',
        },
    }, {
        # From http://sportscanada.tv/canadagames/index.php/week2/figure-skating/444
        # Title and uploader available only from params JSON
        'url': 'http://www.ustream.tv/embed/recorded/59307601?ub=ff0000&lc=ff0000&oc=ffffff&uc=ffffff&v=3&wmode=direct',
        'md5': '5a2abf40babeac9812ed20ae12d34e10',
        'info_dict': {
            'id': '59307601',
            'ext': 'flv',
            'title': '-CG11- Canada Games Figure Skating',
            'uploader': 'sportscanadatv',
        }
    }]

    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url)
        video_id = m.group('id')

        # some sites use this embed format (see: http://github.com/rg3/youtube-dl/issues/2990)
        if m.group('type') == 'embed/recorded':
            video_id = m.group('id')
            desktop_url = 'http://www.ustream.tv/recorded/' + video_id
            return self.url_result(desktop_url, 'Ustream')
        if m.group('type') == 'embed':
            video_id = m.group('id')
            webpage = self._download_webpage(url, video_id)
            desktop_video_id = self._html_search_regex(
                r'ContentVideoIds=\["([^"]*?)"\]', webpage, 'desktop_video_id')
            desktop_url = 'http://www.ustream.tv/recorded/' + desktop_video_id
            return self.url_result(desktop_url, 'Ustream')

        params = self._download_json(
            'https://api.ustream.tv/videos/%s.json' % video_id, video_id)

        error = params.get('error')
        if error:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, error), expected=True)

        video = params['video']

        formats = [{
            'id': format_id,
            'url': video_url,
            'ext': format_id,
        } for format_id, video_url in video['media_urls'].items()]
        self._sort_formats(formats)

        title = video['title']
        description = video.get('description')
        timestamp = int_or_none(video.get('created_at'))
        duration = float_or_none(video.get('length'))
        filesize = float_or_none(video.get('file_size'))
        view_count = int_or_none(video.get('views'))

        uploader = video.get('owner', {}).get('username')
        uploader_id = video.get('owner', {}).get('id')

        thumbnails = [{
            'id': thumbnail_id,
            'url': thumbnail_url,
        } for thumbnail_id, thumbnail_url in video.get('thumbnail', {}).items()]

        return {
            'id': video_id,
            'title': title,
            'description': description,
            'thumbnails': thumbnails,
            'timestamp': timestamp,
            'duration': duration,
            'filesize': filesize,
            'view_count': view_count,
            'uploader': uploader,
            'uploader_id': uploader_id,
            'formats': formats,
        }


class UstreamChannelIE(InfoExtractor):
    _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
    IE_NAME = 'ustream:channel'
    _TEST = {
        'url': 'http://www.ustream.tv/channel/channeljapan',
        'info_dict': {
            'id': '10874166',
        },
        'playlist_mincount': 17,
    }

    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url)
        display_id = m.group('slug')
        webpage = self._download_webpage(url, display_id)
        channel_id = self._html_search_meta('ustream:channel_id', webpage)

        BASE = 'http://www.ustream.tv'
        next_url = '/ajax/socialstream/videos/%s/1.json' % channel_id
        video_ids = []
        while next_url:
            reply = self._download_json(
                compat_urlparse.urljoin(BASE, next_url), display_id,
                note='Downloading video information (next: %d)' % (len(video_ids) + 1))
            video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
            next_url = reply['nextUrl']

        entries = [
            self.url_result('http://www.ustream.tv/recorded/' + vid, 'Ustream')
            for vid in video_ids]
        return {
            '_type': 'playlist',
            'id': channel_id,
            'display_id': display_id,
            'entries': entries,
        }