[cleanup] Misc (#8968)
[yt-dlp.git] / yt_dlp / extractor / mangomolo.py
blobefaf66fa200d123685e59b80f7ae1c2d07534695
1 from .common import InfoExtractor
2 from ..compat import (
3 compat_b64decode,
4 compat_urllib_parse_unquote,
6 from ..utils import classproperty, int_or_none
9 class MangomoloBaseIE(InfoExtractor):
10 _BASE_REGEX = r'(?:https?:)?//(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
11 _SLUG = None
13 @classproperty
14 def _VALID_URL(cls):
15 return f'{cls._BASE_REGEX}{cls._SLUG}'
17 @classproperty
18 def _EMBED_REGEX(cls):
19 return [rf'<iframe[^>]+src=(["\'])(?P<url>{cls._VALID_URL}.+?)\1']
21 def _extract_from_webpage(self, url, webpage):
22 for res in super()._extract_from_webpage(url, webpage):
23 yield {
24 **res,
25 '_type': 'url_transparent',
26 'id': self._search_regex(self._SLUG, res['url'], 'id', group='id'),
27 'uploader': self._search_regex(r'^(?:https?://)?([^/]*)/.*', url, 'video uploader'),
30 def _get_real_id(self, page_id):
31 return page_id
33 def _real_extract(self, url):
34 page_id = self._get_real_id(self._match_id(url))
35 webpage = self._download_webpage(
36 'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id)
37 hidden_inputs = self._hidden_inputs(webpage)
38 m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
40 format_url = self._html_search_regex(
42 r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
43 r'<a[^>]+href="(rtsp://[^"]+)"'
44 ], webpage, 'format url')
45 formats = self._extract_wowza_formats(
46 format_url, page_id, m3u8_entry_protocol, ['smil'])
48 return {
49 'id': page_id,
50 'title': page_id,
51 'uploader_id': hidden_inputs.get('userid'),
52 'duration': int_or_none(hidden_inputs.get('duration')),
53 'is_live': self._IS_LIVE,
54 'formats': formats,
58 class MangomoloVideoIE(MangomoloBaseIE):
59 _TYPE = 'video'
60 IE_NAME = 'mangomolo:' + _TYPE
61 _SLUG = r'video\?.*?\bid=(?P<id>\d+)'
63 _IS_LIVE = False
66 class MangomoloLiveIE(MangomoloBaseIE):
67 _TYPE = 'live'
68 IE_NAME = 'mangomolo:' + _TYPE
69 _SLUG = r'(?:live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
70 _IS_LIVE = True
72 def _get_real_id(self, page_id):
73 return compat_b64decode(compat_urllib_parse_unquote(page_id)).decode()