X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Ftheplatform.py;h=07055513a1c7f91df0af1c12c1df5bfeaaeb115f;hb=HEAD;hp=9ca765a5ffaa9d4fdf1d57fabd4a527d5a772962;hpb=9771b1f901b19ad5ba6632a37fc6348e8e6e98dd;p=youtube-dl diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 9ca765a5f..07055513a 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# coding: utf-8 from __future__ import unicode_literals import re @@ -6,10 +6,10 @@ import time import hmac import binascii import hashlib -import netrc from .once import OnceIE +from .adobepass import AdobePassIE from ..compat import ( compat_parse_qs, compat_urllib_parse_urlparse, @@ -25,9 +25,6 @@ from ..utils import ( xpath_with_ns, mimetype2ext, find_xpath_attr, - unescapeHTML, - urlencode_postdata, - unified_timestamp, ) default_ns = 'http://www.w3.org/2005/SMIL21/Language' @@ -35,12 +32,24 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(OnceIE): + _TP_TLD = 'com' + def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): - meta = self._download_xml(smil_url, video_id, note=note, query={'format': 'SMIL'}) + meta = self._download_xml( + smil_url, video_id, note=note, query={'format': 'SMIL'}, + headers=self.geo_verification_headers()) 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.'): - raise ExtractorError(error_element.attrib['abstract'], expected=True) + if error_element is not None: + exception = find_xpath_attr( + error_element, _x('.//smil:param'), 'name', 'exception') + if exception is not None: + if exception.get('value') == 'GeoLocationBlocked': + self.raise_geo_restricted(error_element.attrib['abstract']) + elif error_element.attrib['src'].startswith( + 'http://link.theplatform.%s/s/errorFiles/Unavailable.' + % self._TP_TLD): + raise ExtractorError( + error_element.attrib['abstract'], expected=True) smil_formats = self._parse_smil_formats( meta, smil_url, video_id, namespace=default_ns, @@ -67,7 +76,7 @@ class ThePlatformBaseIE(OnceIE): return formats, subtitles def _download_theplatform_metadata(self, path, video_id): - info_url = 'http://link.theplatform.com/s/%s?format=preview' % path + info_url = 'http://link.theplatform.%s/s/%s?format=preview' % (self._TP_TLD, path) return self._download_json(info_url, video_id) def _parse_theplatform_metadata(self, info): @@ -76,19 +85,38 @@ class ThePlatformBaseIE(OnceIE): if isinstance(captions, list): for caption in captions: lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type') - subtitles[lang] = [{ + subtitles.setdefault(lang, []).append({ 'ext': mimetype2ext(mime), 'url': src, - }] + }) + + duration = info.get('duration') + tp_chapters = info.get('chapters', []) + chapters = [] + if tp_chapters: + def _add_chapter(start_time, end_time): + start_time = float_or_none(start_time, 1000) + end_time = float_or_none(end_time, 1000) + if start_time is None or end_time is None: + return + chapters.append({ + 'start_time': start_time, + 'end_time': end_time, + }) + + for chapter in tp_chapters[:-1]: + _add_chapter(chapter.get('startTime'), chapter.get('endTime')) + _add_chapter(tp_chapters[-1].get('startTime'), tp_chapters[-1].get('endTime') or duration) return { 'title': info['title'], 'subtitles': subtitles, 'description': info['description'], 'thumbnail': info['defaultThumbnailUrl'], - 'duration': int_or_none(info.get('duration'), 1000), + 'duration': float_or_none(duration, 1000), 'timestamp': int_or_none(info.get('pubDate'), 1000) or None, 'uploader': info.get('billingCode'), + 'chapters': chapters, } def _extract_theplatform_metadata(self, path, video_id): @@ -96,10 +124,10 @@ class ThePlatformBaseIE(OnceIE): return self._parse_theplatform_metadata(info) -class ThePlatformIE(ThePlatformBaseIE): +class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): _VALID_URL = r'''(?x) (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P[^/]+)/ - (?:(?:(?:[^/]+/)+select/)?(?Pmedia/(?:guid/\d+/)?)|(?P(?:[^/\?]+/(?:swf|config)|onsite)/select/))? + (?:(?:(?:[^/]+/)+select/)?(?Pmedia/(?:guid/\d+/)?)?|(?P(?:[^/\?]+/(?:swf|config)|onsite)/select/))? |theplatform:)(?P[^/\?&]+)''' _TESTS = [{ @@ -119,6 +147,7 @@ class ThePlatformIE(ThePlatformBaseIE): # rtmp download 'skip_download': True, }, + 'skip': '404 Not Found', }, { # from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/ 'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT', @@ -156,7 +185,7 @@ class ThePlatformIE(ThePlatformBaseIE): 'title': 'iPhone Siri’s sassy response to a math question has people talking', 'description': 'md5:a565d1deadd5086f3331d57298ec6333', 'duration': 83.0, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1435752600, 'upload_date': '20150701', 'uploader': 'NBCU-NEWS', @@ -167,7 +196,6 @@ 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): @@ -180,10 +208,12 @@ class ThePlatformIE(ThePlatformBaseIE): if m: return [m.group('url')] + # Are whitesapces ignored in URLs? + # https://github.com/ytdl-org/youtube-dl/issues/12044 matches = re.findall( - r'<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage) + r'(?s)<(?:iframe|script)[^>]+src=(["\'])((?:https?:)?//player\.theplatform\.com/p/.+?)\1', webpage) if matches: - return list(zip(*matches))[1] + return [re.sub(r'\s', '', list(zip(*matches))[1][0])] @staticmethod def _sign_url(url, sig_key, sig_secret, life=600, include_qs=False): @@ -196,103 +226,12 @@ class ThePlatformIE(ThePlatformBaseIE): 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) + 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>(.+?)' % (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(re.sub(r'[_ ]GMT', '', xml_text(authn_token, 'simpleTokenExpires'))) - if token_expires and token_expires <= int(time.time()): - authn_token = None - requestor_info = {} - if not authn_token: - # TODO add support for other TV Providers - mso_id = 'DTV' - username, password = self._get_netrc_login_info(mso_id) - if not username or not password: - return '' - - def post_form(form_page, note, data={}): - post_url = self._html_search_regex(r']+action=(["\'])(?P.+?)\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': username, - 'password': password, - }) - 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, {}) @@ -332,7 +271,7 @@ class ThePlatformIE(ThePlatformBaseIE): if smuggled_data.get('force_smil_url', False): smil_url = url - # Explicitly specified SMIL (see https://github.com/rg3/youtube-dl/issues/7385) + # Explicitly specified SMIL (see https://github.com/ytdl-org/youtube-dl/issues/7385) elif '/guid/' in url: headers = {} source_url = smuggled_data.get('source_url') @@ -379,7 +318,7 @@ class ThePlatformIE(ThePlatformBaseIE): class ThePlatformFeedIE(ThePlatformBaseIE): _URL_TEMPLATE = '%s//feed.theplatform.com/f/%s/%s?form=json&%s' - _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P[^/]+)/(?P[^?/]+)\?(?:[^&]+&)*(?Pby(?:Gui|I)d=(?P[\w-]+))' + _VALID_URL = r'https?://feed\.theplatform\.com/f/(?P[^/]+)/(?P[^?/]+)\?(?:[^&]+&)*(?Pby(?:Gui|I)d=(?P[^&]+))' _TESTS = [{ # 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', @@ -389,18 +328,22 @@ class ThePlatformFeedIE(ThePlatformBaseIE): '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$', + 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140208', 'timestamp': 1391824260, 'duration': 467.0, 'categories': ['MSNBC/Issues/Democrats', 'MSNBC/Issues/Elections/Election 2016'], 'uploader': 'NBCU-NEWS', }, + }, { + 'url': 'http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews?byGuid=nn_netcast_180306.Copy.01', + 'only_matching': True, }] - def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}): + def _extract_feed_info(self, provider_id, feed_id, filter_query, video_id, custom_fields=None, asset_types_query={}, account_id=None): real_url = self._URL_TEMPLATE % (self.http_scheme(), provider_id, feed_id, filter_query) entry = self._download_json(real_url, video_id)['entries'][0] + main_smil_url = 'http://link.theplatform.com/s/%s/media/guid/%d/%s' % (provider_id, account_id, entry['guid']) if account_id else entry.get('plmedia$publicUrl') formats = [] subtitles = {} @@ -413,7 +356,8 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) - for asset_type in item['plfile$assetTypes']: + file_asset_types = item.get('plfile$assetTypes') or compat_parse_qs(compat_urllib_parse_urlparse(smil_url).query)['assetTypes'] + for asset_type in file_asset_types: if asset_type in asset_types: continue asset_types.append(asset_type) @@ -425,7 +369,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): 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) + main_smil_url or smil_url, query), video_id, 'Downloading SMIL data for %s' % asset_type) formats.extend(cur_formats) subtitles = self._merge_subtitles(subtitles, cur_subtitles)