aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/ustream.py
blob: d1d2af19b8870353e66cbf227727e54e5bafb0e7 (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
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import (
    compat_urlparse,
    get_meta_content,
)


class UstreamIE(InfoExtractor):
    _VALID_URL = r'https?://www\.ustream\.tv/(?P<type>recorded|embed)/(?P<videoID>\d+)'
    IE_NAME = 'ustream'
    _TESTS = [{
        'url': 'http://www.ustream.tv/recorded/20274954',
        'file': '20274954.flv',
        'md5': '088f151799e8f572f84eb62f17d73e5c',
        'info_dict': {
            "uploader": "Young Americans for Liberty",
            "title": "Young Americans for Liberty February 7, 2012 2:28 AM",
        },
    },
    {
        'url': 'http://www.ustream.tv/embed/17357891',
        'file': 'NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman-45734260.flv',
        'md5': '27b99cdb639c9b12a79bca876a073417',
        'info_dict': {
            "uploader": "AU SPA: The NSA and Privacy",
            "title": "NSA and Privacy Forum Debate featuring General Hayden and Barton Gellman"
    },
    }
    ]

    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url)
        if m.group('type') == 'embed':
            video_id = m.group('videoID')
            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')

        video_id = m.group('videoID')

        video_url = 'http://tcdn.ustream.tv/video/%s' % video_id
        webpage = self._download_webpage(url, video_id)

        self.report_extraction(video_id)

        video_title = self._html_search_regex(r'data-title="(?P<title>.+)"',
            webpage, 'title')

        uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P<uploader>.*?)</a>',
            webpage, 'uploader', fatal=False, flags=re.DOTALL)

        thumbnail = self._html_search_regex(r'<link rel="image_src" href="(?P<thumb>.*?)"',
            webpage, 'thumbnail', fatal=False)

        return {
            'id': video_id,
            'url': video_url,
            'ext': 'flv',
            'title': video_title,
            'uploader': uploader,
            'thumbnail': thumbnail,
        }


class UstreamChannelIE(InfoExtractor):
    _VALID_URL = r'https?://www\.ustream\.tv/channel/(?P<slug>.+)'
    IE_NAME = 'ustream:channel'

    def _real_extract(self, url):
        m = re.match(self._VALID_URL, url)
        slug = m.group('slug')
        webpage = self._download_webpage(url, slug)
        channel_id = get_meta_content('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 = json.loads(self._download_webpage(compat_urlparse.urljoin(BASE, next_url), channel_id))
            video_ids.extend(re.findall(r'data-content-id="(\d.*)"', reply['data']))
            next_url = reply['nextUrl']

        urls = ['http://www.ustream.tv/recorded/' + vid for vid in video_ids]
        url_entries = [self.url_result(eurl, 'Ustream') for eurl in urls]
        return self.playlist_result(url_entries, channel_id)