]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/carambatv.py
[extractor/youtube] Fix live chat for videos with content warning
[yt-dlp.git] / yt_dlp / extractor / carambatv.py
CommitLineData
eb451890
S
1from .common import InfoExtractor
2from ..compat import compat_str
3from ..utils import (
e0ddbd02 4 format_field,
eb451890
S
5 float_or_none,
6 int_or_none,
7 try_get,
8)
9
62a0b86e
YCH
10from .videomore import VideomoreIE
11
eb451890
S
12
13class CarambaTVIE(InfoExtractor):
14 _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
15 _TESTS = [{
16 'url': 'http://video1.carambatv.ru/v/191910501',
17 'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
18 'info_dict': {
19 'id': '191910501',
20 'ext': 'mp4',
21 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
ec85ded8 22 'thumbnail': r're:^https?://.*\.jpg',
eb451890
S
23 'duration': 2678.31,
24 },
25 }, {
26 'url': 'carambatv:191910501',
27 'only_matching': True,
28 }]
29
30 def _real_extract(self, url):
31 video_id = self._match_id(url)
32
33 video = self._download_json(
34 'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
35 video_id)
36
37 title = video['title']
38
39 base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
40
41 formats = [{
42 'url': base_url + f['fn'],
43 'height': int_or_none(f.get('height')),
e0ddbd02 44 'format_id': format_field(f, 'height', '%sp'),
eb451890
S
45 } for f in video['qualities'] if f.get('fn')]
46 self._sort_formats(formats)
47
48 thumbnail = video.get('splash')
49 duration = float_or_none(try_get(
50 video, lambda x: x['annotations'][0]['end_time'], compat_str))
51
52 return {
53 'id': video_id,
54 'title': title,
55 'thumbnail': thumbnail,
56 'duration': duration,
57 'formats': formats,
58 }
59
60
61class CarambaTVPageIE(InfoExtractor):
62 _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
63 _TEST = {
64 'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
62a0b86e 65 'md5': 'a49fb0ec2ad66503eeb46aac237d3c86',
eb451890 66 'info_dict': {
62a0b86e
YCH
67 'id': '475222',
68 'ext': 'flv',
eb451890 69 'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
ec85ded8 70 'thumbnail': r're:^https?://.*\.jpg',
62a0b86e
YCH
71 # duration reported by videomore is incorrect
72 'duration': int,
eb451890 73 },
62a0b86e 74 'add_ie': [VideomoreIE.ie_key()],
eb451890
S
75 }
76
77 def _real_extract(self, url):
78 video_id = self._match_id(url)
79
80 webpage = self._download_webpage(url, video_id)
81
62a0b86e 82 videomore_url = VideomoreIE._extract_url(webpage)
c87f65e4
S
83 if not videomore_url:
84 videomore_id = self._search_regex(
85 r'getVMCode\s*\(\s*["\']?(\d+)', webpage, 'videomore id',
86 default=None)
87 if videomore_id:
88 videomore_url = 'videomore:%s' % videomore_id
62a0b86e
YCH
89 if videomore_url:
90 title = self._og_search_title(webpage)
91 return {
92 '_type': 'url_transparent',
93 'url': videomore_url,
94 'ie_key': VideomoreIE.ie_key(),
95 'title': title,
96 }
97
eb451890
S
98 video_url = self._og_search_property('video:iframe', webpage, default=None)
99
100 if not video_url:
101 video_id = self._search_regex(
102 r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
103 webpage, 'video id')
104 video_url = 'carambatv:%s' % video_id
105
106 return self.url_result(video_url, CarambaTVIE.ie_key())