+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ }
+ }, {
+ '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',
+ 'uploader': 'EGSM',
+ }
+ }, {
+ 'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://player.theplatform.com/p/2E2eJC/nbcNewsOffsite?guid=tdy_or_siri_150701',
+ 'md5': 'fb96bb3d85118930a5b055783a3bd992',
+ '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',
+ 'uploader': 'NBCU-NEWS',
+ },
+ }, {
+ # 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,
+ }]
+ _SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
+
+ @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]
+
+ @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')
+
+ def hex_to_bytes(hex):
+ return binascii.a2b_hex(hex.encode('ascii'))
+
+ relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1)
+ clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path))
+ 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)
+
+ 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:
+ token_expires = unified_timestamp(xml_text(authn_token, 'simpleTokenExpires').replace('_GMT', ''))
+ if token_expires and token_expires >= time.time():
+ authn_token = None
+ if not authn_token:
+ # TODO add support for other TV Providers
+ mso_id = 'DTV'
+ login_info = netrc.netrc().authenticators(mso_id)
+ if not login_info:
+ return None
+
+ 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', {
+ 'username': login_info[0],
+ 'password': login_info[2],
+ })
+ 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)
+
+ def _real_extract(self, url):
+ url, smuggled_data = unsmuggle_url(url, {})
+
+ mobj = re.match(self._VALID_URL, url)
+ provider_id = mobj.group('provider_id')
+ video_id = mobj.group('id')
+
+ if not provider_id:
+ provider_id = 'dJ5BDC'
+
+ path = provider_id + '/'
+ if mobj.group('media'):
+ path += mobj.group('media')
+ path += video_id
+
+ 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):
+ feed_script = self._download_webpage(
+ 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)
+ 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]))
+
+ if smuggled_data.get('force_smil_url', False):
+ smil_url = url
+ # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385)
+ elif '/guid/' in url:
+ 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)
+ 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')
+ smil_url += '?' if '?' not in smil_url else '&' + 'formats=m3u,mpeg4'
+ elif mobj.group('config'):
+ config_url = url + '&form=json'
+ 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')
+ if 'releaseUrl' in config:
+ release_url = config['releaseUrl']
+ else:
+ release_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
+ smil_url = release_url + '&formats=MPEG4&manifest=f4m'