0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-16 01:25:06 +00:00
yt-dlp/yt_dlp/extractor/mangomolo.py
pukkandan bfd973ece3 [extractors] Use new framework for existing embeds (#4307)
`Brightcove` is difficult to migrate because it's subclasses may depend
on the signature of the current functions. So it is left as-is for now

Note: Tests have not been migrated
2022-08-02 01:08:16 +05:30

74 lines
2.4 KiB
Python

from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
from ..utils import classproperty, int_or_none
class MangomoloBaseIE(InfoExtractor):
_BASE_REGEX = r'(?:https?:)?//(?:admin\.mangomolo\.com/analytics/index\.php/customers/embed/|player\.mangomolo\.com/v1/)'
_SLUG = None
@classproperty
def _VALID_URL(cls):
return f'{cls._BASE_REGEX}{cls._SLUG}'
@classproperty
def _EMBED_REGEX(cls):
return [rf'<iframe[^>]+src=(["\'])(?P<url>{cls._VALID_URL}.+?)\1']
def _extract_from_webpage(self, url, webpage):
for res in super()._extract_from_webpage(url, webpage):
yield {
**res,
'_type': 'url_transparent',
'id': self._search_regex(self._SLUG, res['url'], 'id', group='id'),
'uploader': self._search_regex(r'^(?:https?://)?([^/]*)/.*', url, 'video uploader'),
}
def _get_real_id(self, page_id):
return page_id
def _real_extract(self, url):
page_id = self._get_real_id(self._match_id(url))
webpage = self._download_webpage(
'https://player.mangomolo.com/v1/%s?%s' % (self._TYPE, url.split('?')[1]), page_id)
hidden_inputs = self._hidden_inputs(webpage)
m3u8_entry_protocol = 'm3u8' if self._IS_LIVE else 'm3u8_native'
format_url = self._html_search_regex(
[
r'(?:file|src)\s*:\s*"(https?://[^"]+?/playlist\.m3u8)',
r'<a[^>]+href="(rtsp://[^"]+)"'
], webpage, 'format url')
formats = self._extract_wowza_formats(
format_url, page_id, m3u8_entry_protocol, ['smil'])
self._sort_formats(formats)
return {
'id': page_id,
'title': page_id,
'uploader_id': hidden_inputs.get('userid'),
'duration': int_or_none(hidden_inputs.get('duration')),
'is_live': self._IS_LIVE,
'formats': formats,
}
class MangomoloVideoIE(MangomoloBaseIE):
_TYPE = 'video'
IE_NAME = 'mangomolo:' + _TYPE
_SLUG = r'video\?.*?\bid=(?P<id>\d+)'
_IS_LIVE = False
class MangomoloLiveIE(MangomoloBaseIE):
_TYPE = 'live'
IE_NAME = 'mangomolo:' + _TYPE
_SLUG = r'(?:live|index)\?.*?\bchannelid=(?P<id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)'
_IS_LIVE = True
def _get_real_id(self, page_id):
return compat_b64decode(compat_urllib_parse_unquote(page_id)).decode()