X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9dc487f48b50767cf540fa36c3de2c386fd74c04..8da41cd9dd1fb23ad985894740ac01fa99733936:/youtube_dl/extractor/theplatform.py diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 07d222a..90b351c 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 @@ -9,6 +9,7 @@ import hashlib from .once import OnceIE +from .adobepass import AdobePassIE from ..compat import ( compat_parse_qs, compat_urllib_parse_urlparse, @@ -31,12 +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, @@ -62,35 +75,59 @@ class ThePlatformBaseIE(OnceIE): return formats, subtitles - def get_metadata(self, path, video_id): - info_url = 'http://link.theplatform.com/s/%s?format=preview' % path - info = self._download_json(info_url, video_id) + def _download_theplatform_metadata(self, path, video_id): + 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): 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] = [{ + 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): + info = self._download_theplatform_metadata(path, video_id) + 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 = [{ @@ -110,6 +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', @@ -147,7 +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', @@ -170,10 +208,12 @@ class ThePlatformIE(ThePlatformBaseIE): if m: return [m.group('url')] + # Are whitesapces ignored in URLs? + # https://github.com/rg3/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): @@ -186,7 +226,7 @@ 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) @@ -265,7 +305,7 @@ class ThePlatformIE(ThePlatformBaseIE): formats, subtitles = self._extract_theplatform_smil(smil_url, video_id) self._sort_formats(formats) - ret = self.get_metadata(path, video_id) + ret = self._extract_theplatform_metadata(path, video_id) combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles) ret.update({ 'id': video_id, @@ -278,7 +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', @@ -288,18 +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$publicUrl') formats = [] subtitles = {} @@ -312,7 +356,8 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$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) @@ -324,7 +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) @@ -339,7 +384,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): timestamp = int_or_none(entry.get('media$availableDate'), scale=1000) categories = [item['media$name'] for item in entry.get('media$categories', [])] - ret = self.get_metadata('%s/%s' % (provider_id, first_video_id), video_id) + ret = self._extract_theplatform_metadata('%s/%s' % (provider_id, first_video_id), video_id) subtitles = self._merge_subtitles(subtitles, ret['subtitles']) ret.update({ 'id': video_id,