aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/techtalks.py
blob: 16e945d8e624adc51e6a68eab786bdece0a29960 (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
from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import (
    get_element_by_attribute,
    clean_html,
)


class TechTalksIE(InfoExtractor):
    _VALID_URL = r'https?://techtalks\.tv/talks/[^/]*/(?P<id>\d+)/'

    _TEST = {
        'url': 'http://techtalks.tv/talks/learning-topic-models-going-beyond-svd/57758/',
        'info_dict': {
            'id': '57758',
            'title': 'Learning Topic Models --- Going beyond SVD',
        },
        'playlist': [
            {
                'info_dict': {
                    'id': '57758',
                    'ext': 'flv',
                    'title': 'Learning Topic Models --- Going beyond SVD',
                },
            },
            {
                'info_dict': {
                    'id': '57758-slides',
                    'ext': 'flv',
                    'title': 'Learning Topic Models --- Going beyond SVD',
                },
            },
        ],
        'params': {
            # rtmp download
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        talk_id = mobj.group('id')
        webpage = self._download_webpage(url, talk_id)
        rtmp_url = self._search_regex(
            r'netConnectionUrl: \'(.*?)\'', webpage, 'rtmp url')
        play_path = self._search_regex(
            r'href=\'(.*?)\' [^>]*id="flowplayer_presenter"',
            webpage, 'presenter play path')
        title = clean_html(get_element_by_attribute('class', 'title', webpage))
        video_info = {
            'id': talk_id,
            'title': title,
            'url': rtmp_url,
            'play_path': play_path,
            'ext': 'flv',
        }
        m_slides = re.search(r'<a class="slides" href=\'(.*?)\'', webpage)
        if m_slides is None:
            return video_info
        else:
            return {
                '_type': 'playlist',
                'id': talk_id,
                'title': title,
                'entries': [
                    video_info,
                    # The slides video
                    {
                        'id': talk_id + '-slides',
                        'title': title,
                        'url': rtmp_url,
                        'play_path': m_slides.group(1),
                        'ext': 'flv',
                    },
                ],
            }