]> asedeno.scripts.mit.edu Git - youtube-dl.git/blob - youtube_dl/extractor/appleconnect.py
[appleconnect] Fix extraction (#29208)
[youtube-dl.git] / youtube_dl / extractor / appleconnect.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import (
6     str_to_int,
7     ExtractorError
8 )
9
10
11 class AppleConnectIE(InfoExtractor):
12     _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
13     _TESTS = [{
14         'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
15         'md5': 'c1d41f72c8bcaf222e089434619316e4',
16         'info_dict': {
17             'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
18             'ext': 'm4v',
19             'title': 'Energy',
20             'uploader': 'Drake',
21             'thumbnail': r're:^https?://.*\.jpg$',
22             'upload_date': '20150710',
23             'timestamp': 1436545535,
24         },
25     }, {
26         'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
27         'only_matching': True,
28     }]
29
30     def _real_extract(self, url):
31         video_id = self._match_id(url)
32         webpage = self._download_webpage(url, video_id)
33
34         try:
35             video_json = self._html_search_regex(
36                 r'class="auc-video-data">(\{.*?\})', webpage, 'json')
37         except ExtractorError:
38             raise ExtractorError('This post doesn\'t contain a video', expected=True)
39
40         video_data = self._parse_json(video_json, video_id)
41         timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
42         like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
43
44         return {
45             'id': video_id,
46             'url': video_data['sslSrc'],
47             'title': video_data['title'],
48             'description': video_data['description'],
49             'uploader': video_data['artistName'],
50             'thumbnail': video_data['artworkUrl'],
51             'timestamp': timestamp,
52             'like_count': like_count,
53         }