aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/thisoldhouse.py
blob: 197258df141b4b6864afa0e4c1df7d0db431f64e (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
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor


class ThisOldHouseIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)'
    _TESTS = [{
        'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
        'md5': '946f05bbaa12a33f9ae35580d2dfcfe3',
        'info_dict': {
            'id': '2REGtUDQ',
            'ext': 'mp4',
            'title': 'How to Build a Storage Bench',
            'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',
            'timestamp': 1442548800,
            'upload_date': '20150918',
        }
    }, {
        'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
        'only_matching': True,
    }, {
        'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)
        drupal_settings = self._parse_json(self._search_regex(
            r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
            webpage, 'drupal settings'), display_id)
        video_id = drupal_settings['jwplatform']['video_id']
        return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id)