]>
Commit | Line | Data |
---|---|---|
46b18f23 JH |
1 | import re |
2 | ||
3 | from .common import InfoExtractor | |
46b18f23 JH |
4 | from ..utils import ( |
5 | extract_attributes, | |
6 | ) | |
7 | ||
8 | ||
9 | class BostonGlobeIE(InfoExtractor): | |
10 | _VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?' | |
11 | _TESTS = [ | |
12 | { | |
13 | 'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html', | |
14 | 'md5': '0a62181079c85c2d2b618c9a738aedaf', | |
15 | 'info_dict': { | |
16 | 'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood', | |
17 | 'id': '5320421710001', | |
18 | 'ext': 'mp4', | |
19 | 'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.', | |
20 | 'timestamp': 1486877593, | |
21 | 'upload_date': '20170212', | |
22 | 'uploader_id': '245991542', | |
23 | }, | |
24 | }, | |
25 | { | |
26 | # Embedded youtube video; we hand it off to the Generic extractor. | |
27 | 'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html', | |
28 | 'md5': '582b40327089d5c0c949b3c54b13c24b', | |
29 | 'info_dict': { | |
30 | 'title': "Who Is Matt Damon's Favorite Batman?", | |
31 | 'id': 'ZW1QCnlA6Qc', | |
32 | 'ext': 'mp4', | |
33 | 'upload_date': '20170217', | |
34 | 'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb', | |
35 | 'uploader': 'The Late Late Show with James Corden', | |
36 | 'uploader_id': 'TheLateLateShow', | |
37 | }, | |
38 | 'expected_warnings': ['404'], | |
39 | }, | |
40 | ] | |
41 | ||
42 | def _real_extract(self, url): | |
43 | page_id = self._match_id(url) | |
44 | webpage = self._download_webpage(url, page_id) | |
45 | ||
46 | page_title = self._og_search_title(webpage, default=None) | |
47 | ||
48 | # <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject"> | |
49 | entries = [] | |
50 | for video in re.findall(r'(?i)(<video[^>]+>)', webpage): | |
51 | attrs = extract_attributes(video) | |
52 | ||
53 | video_id = attrs.get('data-brightcove-video-id') | |
54 | account_id = attrs.get('data-account') | |
55 | player_id = attrs.get('data-player') | |
56 | embed = attrs.get('data-embed') | |
57 | ||
58 | if video_id and account_id and player_id and embed: | |
59 | entries.append( | |
60 | 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' | |
61 | % (account_id, player_id, embed, video_id)) | |
62 | ||
63 | if len(entries) == 0: | |
64 | return self.url_result(url, 'Generic') | |
65 | elif len(entries) == 1: | |
66 | return self.url_result(entries[0], 'BrightcoveNew') | |
67 | else: | |
68 | return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew') |