1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-25 21:53:45 +01:00
yt-dlp/yt_dlp/extractor/telemundo.py
king-millez 13a49340ed
[telemundo] add extractor (#327)
Closes #284
Authored by: king-millez
2021-05-22 17:17:49 +05:30

59 lines
2.5 KiB
Python

# coding=utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
try_get,
unified_timestamp,
HEADRequest,
)
class TelemundoIE(InfoExtractor):
_VALID_URL = r'https?:\/\/(?:www\.)?telemundo\.com\/.+?video\/[^\/]+(?P<id>tmvo\d{7})'
_TESTS = [{
'url': 'https://www.telemundo.com/noticias/noticias-telemundo-en-la-noche/empleo/video/esta-aplicacion-gratuita-esta-ayudando-los-latinos-encontrar-trabajo-en-estados-unidos-tmvo9829325',
'info_dict': {
'id': 'tmvo9829325',
'timestamp': 1621396800,
'title': 'Esta aplicación gratuita está ayudando a los latinos a encontrar trabajo en Estados Unidos',
'uploader': 'Telemundo',
'uploader_id': 'NBCU_Telemundo',
'ext': 'mp4',
'upload_date': '20210519',
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://www.telemundo.com/shows/al-rojo-vivo/empleo/video/personajes-de-times-square-piden-que-la-ciudad-de-nueva-york-los-deje-volver-trabajar-tmvo9816272',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
metadata = self._parse_json(
self._search_regex(r'<[^>]+id="__NEXT_DATA__"[^>]+>([^<]+)', webpage, 'JSON metadata'), video_id)
redirect_url = try_get(
metadata,
lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['videoAssets'][0]['publicUrl'])
m3u8_url = self._request_webpage(HEADRequest(
redirect_url + '?format=redirect&manifest=m3u&format=redirect&Tracking=true&Embedded=true&formats=MPEG4'),
video_id, 'Processing m3u8').geturl()
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
self._sort_formats(formats)
date = unified_timestamp(try_get(
metadata, lambda x: x['props']['initialState']['video']['associatedPlaylists'][0]['videos'][0]['datePublished'].split(' ', 1)[1]))
return {
'url': url,
'id': video_id,
'title': self._search_regex(r'<h1[^>]+>([^<]+)', webpage, 'title', fatal=False),
'formats': formats,
'timestamp': date,
'uploader': 'Telemundo',
'uploader_id': self._search_regex(r'https?:\/\/(?:[^/]+\/){3}video\/(?P<id>[^\/]+)', m3u8_url, 'Akamai account', fatal=False)
}