]> git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/stitcher.py
[brightcove:new] extract subtitles and strip video title
[youtube-dl] / youtube_dl / extractor / stitcher.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7     determine_ext,
8     int_or_none,
9     js_to_json,
10     unescapeHTML,
11 )
12
13
14 class StitcherIE(InfoExtractor):
15     _VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
16     _TESTS = [{
17         'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
18         'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
19         'info_dict': {
20             'id': '40789481',
21             'ext': 'mp3',
22             'title': 'Machine Learning Mastery and Cancer Clusters',
23             'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3',
24             'duration': 1604,
25             'thumbnail': 're:^https?://.*\.jpg',
26         },
27     }, {
28         'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
29         'info_dict': {
30             'id': '40846275',
31             'display_id': 'the-rare-hourlong-comedy-plus',
32             'ext': 'mp3',
33             'title': "The CW's 'Crazy Ex-Girlfriend'",
34             'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17',
35             'duration': 2235,
36             'thumbnail': 're:^https?://.*\.jpg',
37         },
38         'params': {
39             'skip_download': True,
40         },
41     }, {
42         # escaped title
43         'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
44         'only_matching': True,
45     }, {
46         'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
47         'only_matching': True,
48     }]
49
50     def _real_extract(self, url):
51         mobj = re.match(self._VALID_URL, url)
52         audio_id = mobj.group('id')
53         display_id = mobj.group('display_id') or audio_id
54
55         webpage = self._download_webpage(url, display_id)
56
57         episode = self._parse_json(
58             js_to_json(self._search_regex(
59                 r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')),
60             display_id)['config']['episode']
61
62         title = unescapeHTML(episode['title'])
63         formats = [{
64             'url': episode[episode_key],
65             'ext': determine_ext(episode[episode_key]) or 'mp3',
66             'vcodec': 'none',
67         } for episode_key in ('episodeURL',) if episode.get(episode_key)]
68         description = self._search_regex(
69             r'Episode Info:\s*</span>([^<]+)<', webpage, 'description', fatal=False)
70         duration = int_or_none(episode.get('duration'))
71         thumbnail = episode.get('episodeImage')
72
73         return {
74             'id': audio_id,
75             'display_id': display_id,
76             'title': title,
77             'description': description,
78             'duration': duration,
79             'thumbnail': thumbnail,
80             'formats': formats,
81         }