2015-08-19 13:47:55 -04:00
|
|
|
|
# -*- coding: utf-8 -*-
|
2014-05-30 15:10:48 -04:00
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2013-12-04 17:28:40 -05:00
|
|
|
|
import re
|
2015-02-14 17:56:12 -05:00
|
|
|
|
import time
|
|
|
|
|
import hmac
|
|
|
|
|
import binascii
|
|
|
|
|
import hashlib
|
2016-07-02 16:19:07 -04:00
|
|
|
|
import netrc
|
2015-02-14 17:56:12 -05:00
|
|
|
|
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
2016-03-17 11:06:25 -04:00
|
|
|
|
from .once import OnceIE
|
2015-08-19 13:38:39 -04:00
|
|
|
|
from ..compat import (
|
|
|
|
|
compat_parse_qs,
|
|
|
|
|
compat_urllib_parse_urlparse,
|
|
|
|
|
)
|
2014-12-13 06:24:42 -05:00
|
|
|
|
from ..utils import (
|
2016-06-08 08:47:39 -04:00
|
|
|
|
determine_ext,
|
2013-12-15 21:34:46 -05:00
|
|
|
|
ExtractorError,
|
2015-12-08 10:15:45 -05:00
|
|
|
|
float_or_none,
|
2015-04-08 12:29:10 -04:00
|
|
|
|
int_or_none,
|
2015-12-08 10:15:45 -05:00
|
|
|
|
sanitized_Request,
|
|
|
|
|
unsmuggle_url,
|
2016-06-08 08:47:39 -04:00
|
|
|
|
update_url_query,
|
2015-12-08 10:15:45 -05:00
|
|
|
|
xpath_with_ns,
|
2016-02-20 16:02:03 -05:00
|
|
|
|
mimetype2ext,
|
2016-03-02 15:41:29 -05:00
|
|
|
|
find_xpath_attr,
|
2016-07-02 16:19:07 -04:00
|
|
|
|
unescapeHTML,
|
|
|
|
|
urlencode_postdata,
|
|
|
|
|
unified_timestamp,
|
2013-12-04 17:28:40 -05:00
|
|
|
|
)
|
|
|
|
|
|
2015-08-19 11:11:25 -04:00
|
|
|
|
default_ns = 'http://www.w3.org/2005/SMIL21/Language'
|
|
|
|
|
_x = lambda p: xpath_with_ns(p, {'smil': default_ns})
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
|
|
|
|
|
2016-03-17 11:06:25 -04:00
|
|
|
|
class ThePlatformBaseIE(OnceIE):
|
2015-08-20 13:37:43 -04:00
|
|
|
|
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
|
2016-03-18 04:43:28 -04:00
|
|
|
|
meta = self._download_xml(smil_url, video_id, note=note, query={'format': 'SMIL'})
|
2016-03-18 11:08:25 -04:00
|
|
|
|
error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src')
|
|
|
|
|
if error_element is not None and error_element.attrib['src'].startswith(
|
|
|
|
|
'http://link.theplatform.com/s/errorFiles/Unavailable.'):
|
2016-03-02 15:41:29 -05:00
|
|
|
|
raise ExtractorError(error_element.attrib['abstract'], expected=True)
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
2016-03-17 11:06:25 -04:00
|
|
|
|
smil_formats = self._parse_smil_formats(
|
2015-08-19 13:24:32 -04:00
|
|
|
|
meta, smil_url, video_id, namespace=default_ns,
|
|
|
|
|
# the parameters are from syfy.com, other sites may use others,
|
|
|
|
|
# they also work for nbc.com
|
|
|
|
|
f4m_params={'g': 'UXWGVKRWHFSP', 'hdcore': '3.0.3'},
|
|
|
|
|
transform_rtmp_url=lambda streamer, src: (streamer, 'mp4:' + src))
|
|
|
|
|
|
2016-03-17 11:06:25 -04:00
|
|
|
|
formats = []
|
|
|
|
|
for _format in smil_formats:
|
|
|
|
|
if OnceIE.suitable(_format['url']):
|
|
|
|
|
formats.extend(self._extract_once_formats(_format['url']))
|
|
|
|
|
else:
|
2016-06-08 08:47:39 -04:00
|
|
|
|
media_url = _format['url']
|
|
|
|
|
if determine_ext(media_url) == 'm3u8':
|
|
|
|
|
hdnea2 = self._get_cookies(media_url).get('hdnea2')
|
|
|
|
|
if hdnea2:
|
|
|
|
|
_format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
|
|
|
|
|
|
2016-03-17 11:06:25 -04:00
|
|
|
|
formats.append(_format)
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
2015-08-20 13:37:43 -04:00
|
|
|
|
subtitles = self._parse_smil_subtitles(meta, default_ns)
|
|
|
|
|
|
|
|
|
|
return formats, subtitles
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
def _download_theplatform_metadata(self, path, video_id):
|
2015-08-19 13:24:32 -04:00
|
|
|
|
info_url = 'http://link.theplatform.com/s/%s?format=preview' % path
|
2016-07-02 16:19:07 -04:00
|
|
|
|
return self._download_json(info_url, video_id)
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
def _parse_theplatform_metadata(self, info):
|
2015-08-19 13:24:32 -04:00
|
|
|
|
subtitles = {}
|
|
|
|
|
captions = info.get('captions')
|
|
|
|
|
if isinstance(captions, list):
|
|
|
|
|
for caption in captions:
|
|
|
|
|
lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
|
|
|
|
|
subtitles[lang] = [{
|
2016-02-20 16:02:03 -05:00
|
|
|
|
'ext': mimetype2ext(mime),
|
2015-08-19 13:24:32 -04:00
|
|
|
|
'url': src,
|
|
|
|
|
}]
|
|
|
|
|
|
|
|
|
|
return {
|
|
|
|
|
'title': info['title'],
|
|
|
|
|
'subtitles': subtitles,
|
|
|
|
|
'description': info['description'],
|
|
|
|
|
'thumbnail': info['defaultThumbnailUrl'],
|
|
|
|
|
'duration': int_or_none(info.get('duration'), 1000),
|
2016-04-01 13:06:11 -04:00
|
|
|
|
'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
|
|
|
|
|
'uploader': info.get('billingCode'),
|
2015-08-19 13:24:32 -04:00
|
|
|
|
}
|
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
def _extract_theplatform_metadata(self, path, video_id):
|
|
|
|
|
info = self._download_theplatform_metadata(path, video_id)
|
|
|
|
|
return self._parse_theplatform_metadata(info)
|
|
|
|
|
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
|
|
|
|
class ThePlatformIE(ThePlatformBaseIE):
|
2013-12-23 10:41:35 -05:00
|
|
|
|
_VALID_URL = r'''(?x)
|
2015-02-14 17:56:12 -05:00
|
|
|
|
(?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
|
2016-03-30 18:18:31 -04:00
|
|
|
|
(?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
|
2013-12-23 10:41:35 -05:00
|
|
|
|
|theplatform:)(?P<id>[^/\?&]+)'''
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
2015-04-08 07:20:34 -04:00
|
|
|
|
_TESTS = [{
|
2013-12-04 17:28:40 -05:00
|
|
|
|
# from http://www.metacafe.com/watch/cb-e9I_cZgTgIPd/blackberrys_big_bold_z30/
|
2014-05-30 15:10:48 -04:00
|
|
|
|
'url': 'http://link.theplatform.com/s/dJ5BDC/e9I_cZgTgIPd/meta.smil?format=smil&Tracking=true&mbr=true',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'e9I_cZgTgIPd',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'title': 'Blackberry\'s big, bold Z30',
|
|
|
|
|
'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
|
|
|
|
|
'duration': 247,
|
2016-04-01 13:06:11 -04:00
|
|
|
|
'timestamp': 1383239700,
|
|
|
|
|
'upload_date': '20131031',
|
|
|
|
|
'uploader': 'CBSI-NEW',
|
2013-12-04 17:28:40 -05:00
|
|
|
|
},
|
2014-05-30 15:10:48 -04:00
|
|
|
|
'params': {
|
2013-12-04 17:28:40 -05:00
|
|
|
|
# rtmp download
|
2014-05-30 15:10:48 -04:00
|
|
|
|
'skip_download': True,
|
2013-12-04 17:28:40 -05:00
|
|
|
|
},
|
2015-04-08 07:20:34 -04:00
|
|
|
|
}, {
|
2015-04-08 12:27:25 -04:00
|
|
|
|
# from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
|
2015-04-08 07:20:34 -04:00
|
|
|
|
'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '22d_qsQ6MIRT',
|
|
|
|
|
'ext': 'flv',
|
|
|
|
|
'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
|
|
|
|
|
'title': 'Tesla Model S: A second step towards a cleaner motoring future',
|
2016-04-01 13:06:11 -04:00
|
|
|
|
'timestamp': 1426176191,
|
|
|
|
|
'upload_date': '20150312',
|
|
|
|
|
'uploader': 'CBSI-NEW',
|
2015-04-08 07:20:34 -04:00
|
|
|
|
},
|
|
|
|
|
'params': {
|
|
|
|
|
# rtmp download
|
|
|
|
|
'skip_download': True,
|
|
|
|
|
}
|
2015-06-09 13:07:22 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'https://player.theplatform.com/p/D6x-PC/pulse_preview/embed/select/media/yMBg9E8KFxZD',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'yMBg9E8KFxZD',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'description': 'md5:644ad9188d655b742f942bf2e06b002d',
|
|
|
|
|
'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
|
2016-04-01 13:06:11 -04:00
|
|
|
|
'uploader': 'EGSM',
|
2015-06-09 13:07:22 -04:00
|
|
|
|
}
|
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
|
|
|
|
|
'only_matching': True,
|
2015-08-19 13:38:39 -04:00
|
|
|
|
}, {
|
|
|
|
|
'url': 'http://player.theplatform.com/p/2E2eJC/nbcNewsOffsite?guid=tdy_or_siri_150701',
|
2016-03-17 11:06:25 -04:00
|
|
|
|
'md5': 'fb96bb3d85118930a5b055783a3bd992',
|
2015-08-19 13:38:39 -04:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'tdy_or_siri_150701',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'iPhone Siri’s sassy response to a math question has people talking',
|
|
|
|
|
'description': 'md5:a565d1deadd5086f3331d57298ec6333',
|
|
|
|
|
'duration': 83.0,
|
|
|
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
|
|
|
|
'timestamp': 1435752600,
|
|
|
|
|
'upload_date': '20150701',
|
2016-04-01 13:06:11 -04:00
|
|
|
|
'uploader': 'NBCU-NEWS',
|
2015-08-19 13:38:39 -04:00
|
|
|
|
},
|
2015-11-15 13:28:04 -05:00
|
|
|
|
}, {
|
|
|
|
|
# From http://www.nbc.com/the-blacklist/video/sir-crispin-crandall/2928790?onid=137781#vc137781=1
|
|
|
|
|
# geo-restricted (US), HLS encrypted with AES-128
|
|
|
|
|
'url': 'http://player.theplatform.com/p/NnzsPC/onsite_universal/select/media/guid/2410887629/2928790?fwsitesection=nbc_the_blacklist_video_library&autoPlay=true&carouselID=137781',
|
|
|
|
|
'only_matching': True,
|
2015-04-08 07:20:34 -04:00
|
|
|
|
}]
|
2016-07-02 16:19:07 -04:00
|
|
|
|
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
|
2014-11-23 14:41:03 -05:00
|
|
|
|
|
2016-05-21 20:47:22 -04:00
|
|
|
|
@classmethod
|
|
|
|
|
def _extract_urls(cls, webpage):
|
|
|
|
|
m = re.search(
|
|
|
|
|
r'''(?x)
|
|
|
|
|
<meta\s+
|
|
|
|
|
property=(["'])(?:og:video(?::(?:secure_)?url)?|twitter:player)\1\s+
|
|
|
|
|
content=(["'])(?P<url>https?://player\.theplatform\.com/p/.+?)\2
|
|
|
|
|
''', webpage)
|
|
|
|
|
if m:
|
|
|
|
|
return [m.group('url')]
|
|
|
|
|
|
|
|
|
|
matches = re.findall(
|
|
|
|
|
r'<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage)
|
|
|
|
|
if matches:
|
|
|
|
|
return list(zip(*matches))[1]
|
|
|
|
|
|
2015-02-14 17:56:12 -05:00
|
|
|
|
@staticmethod
|
|
|
|
|
def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False):
|
|
|
|
|
flags = '10' if include_qs else '00'
|
|
|
|
|
expiration_date = '%x' % (int(time.time()) + life)
|
|
|
|
|
|
|
|
|
|
def str_to_hex(str):
|
|
|
|
|
return binascii.b2a_hex(str.encode('ascii')).decode('ascii')
|
|
|
|
|
|
2016-04-27 06:08:23 -04:00
|
|
|
|
def hex_to_bytes(hex):
|
|
|
|
|
return binascii.a2b_hex(hex.encode('ascii'))
|
2015-02-14 17:56:12 -05:00
|
|
|
|
|
2016-04-01 04:55:46 -04:00
|
|
|
|
relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1)
|
2016-04-27 06:08:23 -04:00
|
|
|
|
clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path))
|
2015-02-14 17:56:12 -05:00
|
|
|
|
checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
|
|
|
|
|
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
|
|
|
|
|
return '%s&sig=%s' % (url, sig)
|
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
|
|
|
|
|
def xml_text(xml_str, tag):
|
|
|
|
|
return self._search_regex(
|
|
|
|
|
'<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
|
|
|
|
|
|
|
|
|
|
mvpd_headers = {
|
|
|
|
|
'ap_42': 'anonymous',
|
|
|
|
|
'ap_11': 'Linux i686',
|
|
|
|
|
'ap_z': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
|
|
|
|
|
'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
guid = xml_text(resource, 'guid')
|
|
|
|
|
requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
|
|
|
|
|
authn_token = requestor_info.get('authn_token')
|
|
|
|
|
if authn_token:
|
2016-08-14 06:52:48 -04:00
|
|
|
|
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(authn_token, 'simpleTokenExpires')))
|
|
|
|
|
if token_expires and token_expires <= int(time.time()):
|
2016-07-02 16:19:07 -04:00
|
|
|
|
authn_token = None
|
2016-08-14 06:52:48 -04:00
|
|
|
|
requestor_info = {}
|
2016-07-02 16:19:07 -04:00
|
|
|
|
if not authn_token:
|
|
|
|
|
# TODO add support for other TV Providers
|
|
|
|
|
mso_id = 'DTV'
|
2016-08-14 06:52:48 -04:00
|
|
|
|
username, password = self._get_netrc_login_info(mso_id)
|
|
|
|
|
if not username or not password:
|
|
|
|
|
return ''
|
2016-07-02 16:19:07 -04:00
|
|
|
|
|
|
|
|
|
def post_form(form_page, note, data={}):
|
|
|
|
|
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
|
|
|
|
|
return self._download_webpage(
|
|
|
|
|
post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
|
|
|
|
|
'Content-Type': 'application/x-www-form-urlencoded',
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
provider_redirect_page = self._download_webpage(
|
|
|
|
|
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
|
|
|
|
|
'Downloading Provider Redirect Page', query={
|
|
|
|
|
'noflash': 'true',
|
|
|
|
|
'mso_id': mso_id,
|
|
|
|
|
'requestor_id': requestor_id,
|
|
|
|
|
'no_iframe': 'false',
|
|
|
|
|
'domain_name': 'adobe.com',
|
|
|
|
|
'redirect_url': url,
|
|
|
|
|
})
|
|
|
|
|
provider_login_page = post_form(
|
|
|
|
|
provider_redirect_page, 'Downloading Provider Login Page')
|
|
|
|
|
mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
|
2016-08-14 06:52:48 -04:00
|
|
|
|
'username': username,
|
|
|
|
|
'password': password,
|
2016-07-02 16:19:07 -04:00
|
|
|
|
})
|
|
|
|
|
post_form(mvpd_confirm_page, 'Confirming Login')
|
|
|
|
|
|
|
|
|
|
session = self._download_webpage(
|
|
|
|
|
self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
|
|
|
|
|
'Retrieving Session', data=urlencode_postdata({
|
|
|
|
|
'_method': 'GET',
|
|
|
|
|
'requestor_id': requestor_id,
|
|
|
|
|
}), headers=mvpd_headers)
|
|
|
|
|
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
|
|
|
|
|
requestor_info['authn_token'] = authn_token
|
|
|
|
|
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
|
|
|
|
|
|
|
|
|
authz_token = requestor_info.get(guid)
|
|
|
|
|
if not authz_token:
|
|
|
|
|
authorize = self._download_webpage(
|
|
|
|
|
self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
|
|
|
|
|
'Retrieving Authorization Token', data=urlencode_postdata({
|
|
|
|
|
'resource_id': resource,
|
|
|
|
|
'requestor_id': requestor_id,
|
|
|
|
|
'authentication_token': authn_token,
|
|
|
|
|
'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
|
|
|
|
|
'userMeta': '1',
|
|
|
|
|
}), headers=mvpd_headers)
|
|
|
|
|
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
|
|
|
|
|
requestor_info[guid] = authz_token
|
|
|
|
|
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
|
|
|
|
|
|
|
|
|
|
mvpd_headers.update({
|
|
|
|
|
'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
|
|
|
|
|
'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
|
|
|
|
|
})
|
|
|
|
|
|
|
|
|
|
return self._download_webpage(
|
|
|
|
|
self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
|
|
|
|
|
video_id, 'Retrieving Media Token', data=urlencode_postdata({
|
|
|
|
|
'authz_token': authz_token,
|
|
|
|
|
'requestor_id': requestor_id,
|
|
|
|
|
'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
|
|
|
|
|
'hashed_guid': 'false',
|
|
|
|
|
}), headers=mvpd_headers)
|
|
|
|
|
|
2014-10-26 20:14:17 -04:00
|
|
|
|
def _real_extract(self, url):
|
2015-02-14 17:56:12 -05:00
|
|
|
|
url, smuggled_data = unsmuggle_url(url, {})
|
|
|
|
|
|
2014-10-26 20:14:17 -04:00
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
2015-02-14 17:56:12 -05:00
|
|
|
|
provider_id = mobj.group('provider_id')
|
2014-10-26 20:14:17 -04:00
|
|
|
|
video_id = mobj.group('id')
|
2015-02-14 17:56:12 -05:00
|
|
|
|
|
|
|
|
|
if not provider_id:
|
|
|
|
|
provider_id = 'dJ5BDC'
|
|
|
|
|
|
2016-03-30 18:18:31 -04:00
|
|
|
|
path = provider_id + '/'
|
2015-06-09 13:07:22 -04:00
|
|
|
|
if mobj.group('media'):
|
2016-03-30 18:18:31 -04:00
|
|
|
|
path += mobj.group('media')
|
|
|
|
|
path += video_id
|
2015-06-09 13:07:22 -04:00
|
|
|
|
|
2015-08-19 13:38:39 -04:00
|
|
|
|
qs_dict = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
|
|
|
|
|
if 'guid' in qs_dict:
|
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
|
scripts = re.findall(r'<script[^>]+src="([^"]+)"', webpage)
|
|
|
|
|
feed_id = None
|
|
|
|
|
# feed id usually locates in the last script.
|
|
|
|
|
# Seems there's no pattern for the interested script filename, so
|
|
|
|
|
# I try one by one
|
|
|
|
|
for script in reversed(scripts):
|
2015-11-19 11:58:29 -05:00
|
|
|
|
feed_script = self._download_webpage(
|
2015-11-19 11:58:43 -05:00
|
|
|
|
self._proto_relative_url(script, 'http:'),
|
|
|
|
|
video_id, 'Downloading feed script')
|
|
|
|
|
feed_id = self._search_regex(
|
|
|
|
|
r'defaultFeedId\s*:\s*"([^"]+)"', feed_script,
|
|
|
|
|
'default feed id', default=None)
|
2015-08-19 13:38:39 -04:00
|
|
|
|
if feed_id is not None:
|
|
|
|
|
break
|
|
|
|
|
if feed_id is None:
|
|
|
|
|
raise ExtractorError('Unable to find feed id')
|
|
|
|
|
return self.url_result('http://feed.theplatform.com/f/%s/%s?byGuid=%s' % (
|
|
|
|
|
provider_id, feed_id, qs_dict['guid'][0]))
|
|
|
|
|
|
2015-02-19 12:17:31 -05:00
|
|
|
|
if smuggled_data.get('force_smil_url', False):
|
|
|
|
|
smil_url = url
|
2015-11-15 12:43:23 -05:00
|
|
|
|
# Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385)
|
|
|
|
|
elif '/guid/' in url:
|
2015-12-08 10:15:45 -05:00
|
|
|
|
headers = {}
|
|
|
|
|
source_url = smuggled_data.get('source_url')
|
|
|
|
|
if source_url:
|
|
|
|
|
headers['Referer'] = source_url
|
|
|
|
|
request = sanitized_Request(url, headers=headers)
|
|
|
|
|
webpage = self._download_webpage(request, video_id)
|
2015-11-15 12:43:23 -05:00
|
|
|
|
smil_url = self._search_regex(
|
|
|
|
|
r'<link[^>]+href=(["\'])(?P<url>.+?)\1[^>]+type=["\']application/smil\+xml',
|
|
|
|
|
webpage, 'smil url', group='url')
|
|
|
|
|
path = self._search_regex(
|
|
|
|
|
r'link\.theplatform\.com/s/((?:[^/?#&]+/)+[^/?#&]+)', smil_url, 'path')
|
2016-03-18 04:21:21 -04:00
|
|
|
|
smil_url += '?' if '?' not in smil_url else '&' + 'formats=m3u,mpeg4'
|
2015-02-19 12:17:31 -05:00
|
|
|
|
elif mobj.group('config'):
|
2014-11-23 14:41:03 -05:00
|
|
|
|
config_url = url + '&form=json'
|
2014-10-26 20:14:17 -04:00
|
|
|
|
config_url = config_url.replace('swf/', 'config/')
|
|
|
|
|
config_url = config_url.replace('onsite/', 'onsite/config/')
|
|
|
|
|
config = self._download_json(config_url, video_id, 'Downloading config')
|
2015-08-13 00:56:12 -04:00
|
|
|
|
if 'releaseUrl' in config:
|
|
|
|
|
release_url = config['releaseUrl']
|
|
|
|
|
else:
|
|
|
|
|
release_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
|
2016-03-18 04:21:21 -04:00
|
|
|
|
smil_url = release_url + '&formats=MPEG4&manifest=f4m'
|
2014-10-26 20:14:17 -04:00
|
|
|
|
else:
|
2016-03-18 04:21:21 -04:00
|
|
|
|
smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
|
2015-02-14 17:56:12 -05:00
|
|
|
|
|
|
|
|
|
sig = smuggled_data.get('sig')
|
|
|
|
|
if sig:
|
|
|
|
|
smil_url = self._sign_url(smil_url, sig['key'], sig['secret'])
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
2015-08-20 13:37:43 -04:00
|
|
|
|
formats, subtitles = self._extract_theplatform_smil(smil_url, video_id)
|
2016-04-16 05:23:56 -04:00
|
|
|
|
self._sort_formats(formats)
|
2013-12-15 21:34:46 -05:00
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
ret = self._extract_theplatform_metadata(path, video_id)
|
2015-08-20 13:37:43 -04:00
|
|
|
|
combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles)
|
2015-08-19 13:24:32 -04:00
|
|
|
|
ret.update({
|
|
|
|
|
'id': video_id,
|
|
|
|
|
'formats': formats,
|
2015-08-20 13:37:43 -04:00
|
|
|
|
'subtitles': combined_subtitles,
|
2015-08-19 13:24:32 -04:00
|
|
|
|
})
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
2015-08-19 13:24:32 -04:00
|
|
|
|
return ret
|
2014-12-17 09:20:40 -05:00
|
|
|
|
|
2015-08-19 11:11:25 -04:00
|
|
|
|
|
2015-08-19 13:24:32 -04:00
|
|
|
|
class ThePlatformFeedIE(ThePlatformBaseIE):
|
2016-06-19 18:37:05 -04:00
|
|
|
|
_URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&%s'
|
|
|
|
|
_VALID_URL = r'https?://feed\.theplatform\.com/f/(?P<provider_id>[^/]+)/(?P<feed_id>[^?/]+)\?(?:[^&]+&)*(?P<filter>by(?:Gui|I)d=(?P<id>[\w-]+))'
|
|
|
|
|
_TESTS = [{
|
2015-08-19 13:24:32 -04:00
|
|
|
|
# From http://player.theplatform.com/p/7wvmTC/MSNBCEmbeddedOffSite?guid=n_hardball_5biden_140207
|
|
|
|
|
'url': 'http://feed.theplatform.com/f/7wvmTC/msnbc_video-p-test?form=json&pretty=true&range=-40&byGuid=n_hardball_5biden_140207',
|
2016-03-17 11:06:25 -04:00
|
|
|
|
'md5': '6e32495b5073ab414471b615c5ded394',
|
2015-08-19 13:24:32 -04:00
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': 'n_hardball_5biden_140207',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'The Biden factor: will Joe run in 2016?',
|
|
|
|
|
'description': 'Could Vice President Joe Biden be preparing a 2016 campaign? Mark Halperin and Sam Stein weigh in.',
|
|
|
|
|
'thumbnail': 're:^https?://.*\.jpg$',
|
|
|
|
|
'upload_date': '20140208',
|
|
|
|
|
'timestamp': 1391824260,
|
|
|
|
|
'duration': 467.0,
|
|
|
|
|
'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'],
|
2016-04-24 08:44:52 -04:00
|
|
|
|
'uploader': 'NBCU-NEWS',
|
2015-08-19 13:24:32 -04:00
|
|
|
|
},
|
2016-06-19 18:37:05 -04:00
|
|
|
|
}]
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
2016-06-19 18:37:05 -04:00
|
|
|
|
def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}):
|
|
|
|
|
real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query)
|
|
|
|
|
entry = self._download_json(real_url, video_id)['entries'][0]
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
|
|
|
|
formats = []
|
2015-08-20 13:37:43 -04:00
|
|
|
|
subtitles = {}
|
2015-08-19 13:24:32 -04:00
|
|
|
|
first_video_id = None
|
|
|
|
|
duration = None
|
2016-06-19 18:37:05 -04:00
|
|
|
|
asset_types = []
|
2015-08-19 13:24:32 -04:00
|
|
|
|
for item in entry['media$content']:
|
2016-06-19 18:37:05 -04:00
|
|
|
|
smil_url = item['plfile$url']
|
2016-02-11 12:12:38 -05:00
|
|
|
|
cur_video_id = ThePlatformIE._match_id(smil_url)
|
2015-08-19 13:24:32 -04:00
|
|
|
|
if first_video_id is None:
|
|
|
|
|
first_video_id = cur_video_id
|
|
|
|
|
duration = float_or_none(item.get('plfile$duration'))
|
2016-06-19 18:37:05 -04:00
|
|
|
|
for asset_type in item['plfile$assetTypes']:
|
|
|
|
|
if asset_type in asset_types:
|
|
|
|
|
continue
|
|
|
|
|
asset_types.append(asset_type)
|
|
|
|
|
query = {
|
|
|
|
|
'mbr': 'true',
|
|
|
|
|
'formats': item['plfile$format'],
|
|
|
|
|
'assetTypes': asset_type,
|
|
|
|
|
}
|
|
|
|
|
if asset_type in asset_types_query:
|
|
|
|
|
query.update(asset_types_query[asset_type])
|
|
|
|
|
cur_formats, cur_subtitles = self._extract_theplatform_smil(update_url_query(
|
|
|
|
|
smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type)
|
|
|
|
|
formats.extend(cur_formats)
|
|
|
|
|
subtitles = self._merge_subtitles(subtitles, cur_subtitles)
|
2015-08-19 11:11:25 -04:00
|
|
|
|
|
|
|
|
|
self._sort_formats(formats)
|
2013-12-04 17:28:40 -05:00
|
|
|
|
|
2015-08-19 13:24:32 -04:00
|
|
|
|
thumbnails = [{
|
|
|
|
|
'url': thumbnail['plfile$url'],
|
|
|
|
|
'width': int_or_none(thumbnail.get('plfile$width')),
|
|
|
|
|
'height': int_or_none(thumbnail.get('plfile$height')),
|
|
|
|
|
} for thumbnail in entry.get('media$thumbnails', [])]
|
|
|
|
|
|
|
|
|
|
timestamp = int_or_none(entry.get('media$availableDate'), scale=1000)
|
|
|
|
|
categories = [item['media$name'] for item in entry.get('media$categories', [])]
|
|
|
|
|
|
2016-07-02 16:19:07 -04:00
|
|
|
|
ret = self._extract_theplatform_metadata('%s/%s' % (provider_id, first_video_id), video_id)
|
2015-08-20 13:37:43 -04:00
|
|
|
|
subtitles = self._merge_subtitles(subtitles, ret['subtitles'])
|
2015-08-19 13:24:32 -04:00
|
|
|
|
ret.update({
|
2013-12-04 17:28:40 -05:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'formats': formats,
|
2015-08-20 13:37:43 -04:00
|
|
|
|
'subtitles': subtitles,
|
2015-08-19 13:24:32 -04:00
|
|
|
|
'thumbnails': thumbnails,
|
|
|
|
|
'duration': duration,
|
|
|
|
|
'timestamp': timestamp,
|
|
|
|
|
'categories': categories,
|
|
|
|
|
})
|
2016-06-19 18:37:05 -04:00
|
|
|
|
if custom_fields:
|
|
|
|
|
ret.update(custom_fields(entry))
|
2015-08-19 13:24:32 -04:00
|
|
|
|
|
|
|
|
|
return ret
|
2016-06-19 18:37:05 -04:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
|
|
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
|
provider_id = mobj.group('provider_id')
|
|
|
|
|
feed_id = mobj.group('feed_id')
|
|
|
|
|
filter_query = mobj.group('filter')
|
|
|
|
|
|
|
|
|
|
return self._extract_feed_info(provider_id, feed_id, filter_query, video_id)
|