mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-25 03:31:03 +00:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
69 lines
2.2 KiB
Python
69 lines
2.2 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import json
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import (
|
|
compat_urllib_parse,
|
|
compat_urlparse,
|
|
)
|
|
from ..utils import (
|
|
get_element_by_attribute,
|
|
parse_duration,
|
|
strip_jsonp,
|
|
)
|
|
|
|
|
|
class MiTeleIE(InfoExtractor):
|
|
IE_NAME = 'mitele.es'
|
|
_VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
|
|
|
|
_TEST = {
|
|
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
|
|
'md5': '6a75fe9d0d3275bead0cb683c616fddb',
|
|
'info_dict': {
|
|
'id': '0fce117d',
|
|
'ext': 'mp4',
|
|
'title': 'Programa 144 - Tor, la web invisible',
|
|
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
|
|
'display_id': 'programa-144',
|
|
'duration': 2913,
|
|
},
|
|
}
|
|
|
|
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
|
|
)
|
|
|
|
return {
|
|
'id': embed_data['videoId'],
|
|
'display_id': episode,
|
|
'title': info_el.find('title').text,
|
|
'url': token_info['tokenizedUrl'],
|
|
'description': get_element_by_attribute('class', 'text', webpage),
|
|
'thumbnail': info_el.find('thumb').text,
|
|
'duration': parse_duration(info_el.find('duration').text),
|
|
}
|