mirror of
https://codeberg.org/polarisfm/youtube-dl
synced 2024-10-31 14:34:32 +01:00
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import json
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urllib_parse_unquote,
|
|
compat_urlparse,
|
|
)
|
|
from ..utils import (
|
|
get_element_by_attribute,
|
|
parse_duration,
|
|
strip_jsonp,
|
|
)
|
|
|
|
|
|
class TelecincoIE(InfoExtractor):
|
|
IE_NAME = 'telecinco.es'
|
|
_VALID_URL = r'https?://www\.telecinco\.es/(?:[^/]+/)+(?P<id>.+?)\.html'
|
|
|
|
_TESTS = [{
|
|
'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html',
|
|
'info_dict': {
|
|
'id': 'MDSVID20141015_0058',
|
|
'ext': 'mp4',
|
|
'title': 'Con Martín Berasategui, hacer un bacalao al ...',
|
|
'duration': 662,
|
|
},
|
|
'params': {
|
|
# m3u8 download
|
|
'skip_download': True,
|
|
},
|
|
}, {
|
|
'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html',
|
|
'only_matching': True,
|
|
}, {
|
|
'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html',
|
|
'only_matching': True,
|
|
}]
|
|
|
|
def _real_extract(self, url):
|
|
episode = self._match_id(url)
|
|
webpage = self._download_webpage(url, episode)
|
|
embed_data_json = self._search_regex(
|
|
r'(?s)MSV\.embedData\[.*?\]\s*=\s*({.*?});', webpage, 'embed data',
|
|
).replace('\'', '"')
|
|
embed_data = json.loads(embed_data_json)
|
|
|
|
domain = embed_data['mediaUrl']
|
|
if not domain.startswith('http'):
|
|
# only happens in telecinco.es videos
|
|
domain = 'http://' + domain
|
|
info_url = compat_urlparse.urljoin(
|
|
domain,
|
|
compat_urllib_parse_unquote(embed_data['flashvars']['host'])
|
|
)
|
|
info_el = self._download_xml(info_url, episode).find('./video/info')
|
|
|
|
video_link = info_el.find('videoUrl/link').text
|
|
token_query = compat_urllib_parse.urlencode({'id': video_link})
|
|
token_info = self._download_json(
|
|
embed_data['flashvars']['ov_tk'] + '?' + token_query,
|
|
episode,
|
|
transform_source=strip_jsonp
|
|
)
|
|
formats = self._extract_m3u8_formats(
|
|
token_info['tokenizedUrl'], episode, ext='mp4')
|
|
|
|
return {
|
|
'id': embed_data['videoId'],
|
|
'display_id': episode,
|
|
'title': info_el.find('title').text,
|
|
'formats': formats,
|
|
'description': get_element_by_attribute('class', 'text', webpage),
|
|
'thumbnail': info_el.find('thumb').text,
|
|
'duration': parse_duration(info_el.find('duration').text),
|
|
}
|