[telegram] Add extractor (#2922)

Closes #2910

Authored by: hatienl0i261299
This commit is contained in:
Ha Tien Loi 2022-03-04 18:18:46 +07:00 committed by GitHub
parent ded9f32667
commit 5bcccbfec3
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 38 additions and 0 deletions

View File

@ -1593,6 +1593,7 @@
from .telebruxelles import TeleBruxellesIE
from .telecinco import TelecincoIE
from .telegraaf import TelegraafIE
from .telegram import TelegramEmbedIE
from .telemb import TeleMBIE
from .telemundo import TelemundoIE
from .telequebec import (

View File

@ -0,0 +1,37 @@
from .common import InfoExtractor
class TelegramEmbedIE(InfoExtractor):
IE_NAME = 'telegram:embed'
_VALID_URL = r'https?://t\.me/(?P<channel_name>[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://t.me/europa_press/613',
'info_dict': {
'id': '613',
'ext': 'mp4',
'title': 'Europa Press',
'description': '6ce2d7e8d56eda16d80607b23db7b252',
'thumbnail': r're:^https?:\/\/cdn.*?telesco\.pe\/file\/\w+',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage_embed = self._download_webpage(f'{url}?embed=1', video_id)
formats = [{
'url': self._proto_relative_url(self._search_regex(
'<video[^>]+src="([^"]+)"', webpage_embed, 'source')),
'ext': 'mp4',
}]
self._sort_formats(formats)
return {
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, fatal=True),
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage, fatal=True),
'thumbnail': self._search_regex(r'tgme_widget_message_video_thumb"[^>]+background-image:url\(\'([^\']+)\'\)',
webpage_embed, 'thumbnail'),
'formats': formats,
}