diff --git a/youtube_dl/extractor/cbsinteractive.py b/youtube_dl/extractor/cbsinteractive.py index 0011c30296..821db20b23 100644 --- a/youtube_dl/extractor/cbsinteractive.py +++ b/youtube_dl/extractor/cbsinteractive.py @@ -80,9 +80,6 @@ def _real_extract(self, url): media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId']) formats, subtitles = [], {} - if site == 'cnet': - formats, subtitles = self._extract_theplatform_smil( - self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id) for (fkey, vid) in vdata['files'].items(): if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']: continue @@ -94,7 +91,7 @@ def _real_extract(self, url): subtitles = self._merge_subtitles(subtitles, tp_subtitles) self._sort_formats(formats) - info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id) + info = self._extract_theplatform_metadata('kYEXFC/%s' % media_guid_path, video_id) info.update({ 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 07d222ae3c..bb3efc4ea1 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -6,6 +6,7 @@ import hmac import binascii import hashlib +import netrc from .once import OnceIE @@ -24,6 +25,9 @@ xpath_with_ns, mimetype2ext, find_xpath_attr, + unescapeHTML, + urlencode_postdata, + unified_timestamp, ) default_ns = 'http://www.w3.org/2005/SMIL21/Language' @@ -62,10 +66,11 @@ def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL d return formats, subtitles - def get_metadata(self, path, video_id): + def _download_theplatform_metadata(self, path, video_id): info_url = 'http://link.theplatform.com/s/%s?format=preview' % path - info = self._download_json(info_url, video_id) + return self._download_json(info_url, video_id) + def _parse_theplatform_metadata(self, info): subtitles = {} captions = info.get('captions') if isinstance(captions, list): @@ -86,6 +91,10 @@ def get_metadata(self, path, video_id): 'uploader': info.get('billingCode'), } + def _extract_theplatform_metadata(self, path, video_id): + info = self._download_theplatform_metadata(path, video_id) + return self._parse_theplatform_metadata(info) + class ThePlatformIE(ThePlatformBaseIE): _VALID_URL = r'''(?x) @@ -158,6 +167,7 @@ class ThePlatformIE(ThePlatformBaseIE): '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): @@ -192,6 +202,96 @@ def hex_to_bytes(hex): 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'