aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/byutv.py
blob: 3aec601f8e7179570088e1ea5ad1f7b6d30f219d (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
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import ExtractorError


class BYUtvIE(InfoExtractor):
    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
    _TEST = {
        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
        'md5': '05850eb8c749e2ee05ad5a1c34668493',
        'info_dict': {
            'id': 'studio-c-season-5-episode-5',
            'ext': 'mp4',
            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
            'title': 'Season 5 Episode 5',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 1486.486,
        },
        'params': {
            'skip_download': True,
        },
        'add_ie': ['Ooyala'],
    }

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

        webpage = self._download_webpage(url, video_id)
        episode_code = self._search_regex(
            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
        episode_json = re.sub(
            r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
        ep = json.loads(episode_json)

        if ep['providerType'] == 'Ooyala':
            return {
                '_type': 'url_transparent',
                'ie_key': 'Ooyala',
                'url': 'ooyala:%s' % ep['providerId'],
                'id': video_id,
                'title': ep['title'],
                'description': ep.get('description'),
                'thumbnail': ep.get('imageThumbnail'),
            }
        else:
            raise ExtractorError('Unsupported provider %s' % ep['provider'])