]>
Commit | Line | Data |
---|---|---|
758a0592 | 1 | # coding: utf-8 |
2 | from __future__ import unicode_literals | |
3 | ||
71a1db89 S |
4 | import re |
5 | ||
758a0592 | 6 | from .common import InfoExtractor |
1c45b7a8 | 7 | from ..compat import compat_str |
758a0592 | 8 | from ..utils import ( |
9 | int_or_none, | |
10 | determine_protocol, | |
1c45b7a8 | 11 | try_get, |
111de002 | 12 | unescapeHTML, |
758a0592 | 13 | ) |
14 | ||
15 | ||
16 | class DailyMailIE(InfoExtractor): | |
71a1db89 S |
17 | _VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/(?:video/[^/]+/video-|embed/video/)(?P<id>[0-9]+)' |
18 | _TESTS = [{ | |
111de002 DR |
19 | 'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html', |
20 | 'md5': 'f6129624562251f628296c3a9ffde124', | |
758a0592 | 21 | 'info_dict': { |
111de002 | 22 | 'id': '1295863', |
758a0592 | 23 | 'ext': 'mp4', |
111de002 DR |
24 | 'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'', |
25 | 'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84', | |
758a0592 | 26 | } |
71a1db89 S |
27 | }, { |
28 | 'url': 'http://www.dailymail.co.uk/embed/video/1295863.html', | |
29 | 'only_matching': True, | |
30 | }] | |
31 | ||
32 | @staticmethod | |
33 | def _extract_urls(webpage): | |
34 | return re.findall( | |
35 | r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?dailymail\.co\.uk/embed/video/\d+\.html)', | |
36 | webpage) | |
758a0592 | 37 | |
38 | def _real_extract(self, url): | |
39 | video_id = self._match_id(url) | |
40 | webpage = self._download_webpage(url, video_id) | |
41 | video_data = self._parse_json(self._search_regex( | |
42 | r"data-opts='({.+?})'", webpage, 'video data'), video_id) | |
111de002 | 43 | title = unescapeHTML(video_data['title']) |
1c45b7a8 S |
44 | |
45 | sources_url = (try_get( | |
46 | video_data, | |
47 | (lambda x: x['plugins']['sources']['url'], | |
48 | lambda x: x['sources']['url']), compat_str) or | |
49 | 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id) | |
50 | ||
51 | video_sources = self._download_json(sources_url, video_id) | |
758a0592 | 52 | |
53 | formats = [] | |
54 | for rendition in video_sources['renditions']: | |
55 | rendition_url = rendition.get('url') | |
56 | if not rendition_url: | |
57 | continue | |
58 | tbr = int_or_none(rendition.get('encodingRate'), 1000) | |
59 | container = rendition.get('videoContainer') | |
60 | is_hls = container == 'M2TS' | |
61 | protocol = 'm3u8_native' if is_hls else determine_protocol({'url': rendition_url}) | |
62 | formats.append({ | |
63 | 'format_id': ('hls' if is_hls else protocol) + ('-%d' % tbr if tbr else ''), | |
64 | 'url': rendition_url, | |
65 | 'width': int_or_none(rendition.get('frameWidth')), | |
66 | 'height': int_or_none(rendition.get('frameHeight')), | |
67 | 'tbr': tbr, | |
68 | 'vcodec': rendition.get('videoCodec'), | |
69 | 'container': container, | |
70 | 'protocol': protocol, | |
71 | 'ext': 'mp4' if is_hls else None, | |
72 | }) | |
73 | self._sort_formats(formats) | |
74 | ||
75 | return { | |
76 | 'id': video_id, | |
77 | 'title': title, | |
111de002 | 78 | 'description': unescapeHTML(video_data.get('descr')), |
758a0592 | 79 | 'thumbnail': video_data.get('poster') or video_data.get('thumbnail'), |
80 | 'formats': formats, | |
81 | } |