]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/springboardplatform.py
[misc] Add `hatch`, `ruff`, `pre-commit` and improve dev docs (#7409)
[yt-dlp.git] / yt_dlp / extractor / springboardplatform.py
CommitLineData
7d540621
S
1import re
2
3from .common import InfoExtractor
4from ..utils import (
5 ExtractorError,
6 int_or_none,
7d540621
S
7 unescapeHTML,
8 unified_timestamp,
e897bd82
SS
9 xpath_attr,
10 xpath_element,
11 xpath_text,
7d540621
S
12)
13
14
15class SpringboardPlatformIE(InfoExtractor):
16 _VALID_URL = r'''(?x)
17 https?://
18 cms\.springboardplatform\.com/
19 (?:
20 (?:previews|embed_iframe)/(?P<index>\d+)/video/(?P<id>\d+)|
21 xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+)
22 )
23 '''
bfd973ec 24 _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1']
7d540621
S
25 _TESTS = [{
26 'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1',
27 'md5': '5c3cb7b5c55740d482561099e920f192',
28 'info_dict': {
29 'id': '981017',
30 'ext': 'mp4',
31 'title': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
32 'description': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
33 'thumbnail': r're:^https?://.*\.jpg$',
34 'timestamp': 1409132328,
35 'upload_date': '20140827',
36 'duration': 193,
37 },
38 }, {
39 'url': 'http://cms.springboardplatform.com/embed_iframe/159/video/981017/rab007/rapbasement.com/1/1',
40 'only_matching': True,
41 }, {
42 'url': 'http://cms.springboardplatform.com/embed_iframe/20/video/1731611/ki055/kidzworld.com/10',
43 'only_matching': True,
44 }, {
45 'url': 'http://cms.springboardplatform.com/xml_feeds_advanced/index/159/rss3/981017/0/0/1/',
46 'only_matching': True,
47 }]
48
7d540621 49 def _real_extract(self, url):
5ad28e7f 50 mobj = self._match_valid_url(url)
7d540621
S
51 video_id = mobj.group('id') or mobj.group('id_2')
52 index = mobj.group('index') or mobj.group('index_2')
53
54 video = self._download_xml(
55 'http://cms.springboardplatform.com/xml_feeds_advanced/index/%s/rss3/%s'
56 % (index, video_id), video_id)
57
58 item = xpath_element(video, './/item', 'item', fatal=True)
59
60 content = xpath_element(
61 item, './{http://search.yahoo.com/mrss/}content', 'content',
62 fatal=True)
63 title = unescapeHTML(xpath_text(item, './title', 'title', fatal=True))
64
65 video_url = content.attrib['url']
66
67 if 'error_video.mp4' in video_url:
68 raise ExtractorError(
69 'Video %s no longer exists' % video_id, expected=True)
70
71 duration = int_or_none(content.get('duration'))
72 tbr = int_or_none(content.get('bitrate'))
73 filesize = int_or_none(content.get('fileSize'))
74 width = int_or_none(content.get('width'))
75 height = int_or_none(content.get('height'))
76
77 description = unescapeHTML(xpath_text(
78 item, './description', 'description'))
79 thumbnail = xpath_attr(
80 item, './{http://search.yahoo.com/mrss/}thumbnail', 'url',
81 'thumbnail')
82
83 timestamp = unified_timestamp(xpath_text(
84 item, './{http://cms.springboardplatform.com/namespaces.html}created',
85 'timestamp'))
86
87 formats = [{
88 'url': video_url,
89 'format_id': 'http',
90 'tbr': tbr,
91 'filesize': filesize,
92 'width': width,
93 'height': height,
94 }]
95
96 m3u8_format = formats[0].copy()
97 m3u8_format.update({
98 'url': re.sub(r'(https?://)cdn\.', r'\1hls.', video_url) + '.m3u8',
99 'ext': 'mp4',
100 'format_id': 'hls',
101 'protocol': 'm3u8_native',
102 })
103 formats.append(m3u8_format)
104
7d540621
S
105 return {
106 'id': video_id,
107 'title': title,
108 'description': description,
109 'thumbnail': thumbnail,
110 'timestamp': timestamp,
111 'duration': duration,
112 'formats': formats,
113 }