X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b8d8e13c1f9e4d3cdd7d41c5c9d711a36dd5f9c3..0b77335c30ccc5854a45cd8678a8b512c68b89d7:/youtube_dl/extractor/theplatform.py diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index 192d8fa..ffef5bf 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -32,13 +32,15 @@ _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'}, 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.'): + 'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD): raise ExtractorError(error_element.attrib['abstract'], expected=True) smil_formats = self._parse_smil_formats( @@ -66,7 +68,7 @@ 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): @@ -80,14 +82,33 @@ class ThePlatformBaseIE(OnceIE): '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): @@ -179,10 +200,12 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): 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): @@ -195,7 +218,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): 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) @@ -287,7 +310,7 @@ class ThePlatformIE(ThePlatformBaseIE, AdobePassIE): 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', @@ -304,11 +327,15 @@ class ThePlatformFeedIE(ThePlatformBaseIE): '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 None formats = [] subtitles = {} @@ -333,7 +360,7 @@ 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)