youtube-dl/youtube_dl/extractor/mitele.py

90 lines
2.9 KiB
Python
Raw Normal View History

2014-08-18 20:43:35 +00:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
2015-09-16 16:27:03 +00:00
encode_dict,
2014-08-18 20:43:35 +00:00
get_element_by_attribute,
2015-09-16 16:27:03 +00:00
int_or_none,
2014-08-18 20:43:35 +00:00
)
class MiTeleIE(InfoExtractor):
2015-09-16 16:39:48 +00:00
IE_DESC = 'mitele.es'
_VALID_URL = r'http://www\.mitele\.es/[^/]+/[^/]+/[^/]+/(?P<id>[^/]+)/'
2014-08-18 20:43:35 +00:00
_TESTS = [{
2014-08-18 20:43:35 +00:00
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': '0ff1a13aebb35d9bc14081ff633dd324',
2014-08-18 20:43:35 +00:00
'info_dict': {
2015-09-16 16:27:03 +00:00
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
2014-08-18 20:43:35 +00:00
'display_id': 'programa-144',
2015-09-16 16:27:03 +00:00
'ext': 'flv',
'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
'thumbnail': 're:(?i)^https?://.*\.jpg$',
2014-08-18 20:43:35 +00:00
'duration': 2913,
},
}]
2014-08-18 20:43:35 +00:00
def _real_extract(self, url):
2015-09-16 16:27:03 +00:00
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
2014-08-18 20:43:35 +00:00
2015-09-16 16:27:03 +00:00
config_url = self._search_regex(
r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
config_url = compat_urlparse.urljoin(url, config_url)
2014-08-18 20:43:35 +00:00
2015-09-16 16:27:03 +00:00
config = self._download_json(
config_url, display_id, 'Downloading config JSON')
mmc = self._download_json(
config['services']['mmc'], display_id, 'Downloading mmc JSON')
formats = []
for location in mmc['locations']:
gat = self._proto_relative_url(location.get('gat'), 'http:')
bas = location.get('bas')
loc = location.get('loc')
ogn = location.get('ogn')
if None in (gat, bas, loc, ogn):
continue
token_data = {
'bas': bas,
'icd': loc,
'ogn': ogn,
'sta': '0',
}
media = self._download_json(
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))),
2015-09-16 16:27:03 +00:00
display_id, 'Downloading %s JSON' % location['loc'])
file_ = media.get('file')
if not file_:
continue
formats.extend(self._extract_f4m_formats(
file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
display_id, f4m_id=loc))
title = self._search_regex(
r'class="Destacado-text"[^>]*>\s*<strong>([^<]+)</strong>', webpage, 'title')
video_id = self._search_regex(
r'data-media-id\s*=\s*"([^"]+)"', webpage,
'data media id', default=None) or display_id
thumbnail = config.get('poster', {}).get('imageUrl')
duration = int_or_none(mmc.get('duration'))
2014-08-18 20:43:35 +00:00
return {
2015-09-16 16:27:03 +00:00
'id': video_id,
'display_id': display_id,
'title': title,
2014-08-18 20:43:35 +00:00
'description': get_element_by_attribute('class', 'text', webpage),
2015-09-16 16:27:03 +00:00
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
2014-08-18 20:43:35 +00:00
}