X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fabc.py;h=6637f4f3537591b46870cb7ec3f35d1167cb3cb7;hb=HEAD;hp=9610d0cb72f50ca001abab3ad8f61368a9aabf42;hpb=2e65e7db9e39f22a8d20ea950906ee39fbf2618c;p=youtube-dl diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 9610d0cb7..6637f4f35 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -13,6 +13,8 @@ from ..utils import ( int_or_none, parse_iso8601, try_get, + unescapeHTML, + update_url_query, ) @@ -103,61 +105,59 @@ class ABCIE(InfoExtractor): class ABCIViewIE(InfoExtractor): IE_NAME = 'abc.net.au:iview' - _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P[^/?#]+)' + _VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P[^/?#]+)' + _GEO_COUNTRIES = ['AU'] # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00', - 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', + 'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', 'info_dict': { - 'id': 'ZX9735A001S00', + 'id': 'LE1927H001S00', 'ext': 'mp4', - 'title': 'Diaries Of A Broken Mind', - 'description': 'md5:7de3903874b7a1be279fe6b68718fc9e', - 'upload_date': '20161010', - 'uploader_id': 'abc2', - 'timestamp': 1476064920, + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, + }, + 'params': { + 'skip_download': True, }, - 'skip': 'Video gone', }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_params = self._parse_json(self._search_regex( - r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id) - title = video_params.get('title') or video_params['seriesTitle'] - stream = next(s for s in video_params['playlist'] if s.get('type') == 'program') - - key = 'android.content.res.Resources'.encode('utf-8') - time_str = str(int(time.time())) - house_number = video_params.get('episodeHouseNumber') - path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format( - time_str, house_number) - sig = hmac.new(key, path.encode('utf-8'), hashlib.sha256).hexdigest() - auth_url = 'http://iview.abc.net.au{0}&sig={1}'.format(path, sig) - token = self._download_webpage(auth_url, video_id) - - format_urls = [] + video_params = self._download_json( + 'https://iview.abc.net.au/api/programs/' + video_id, video_id) + title = unescapeHTML(video_params.get('title') or video_params['seriesTitle']) + stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream')) + + house_number = video_params.get('episodeHouseNumber') or video_id + path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format( + int(time.time()), house_number) + sig = hmac.new( + b'android.content.res.Resources', + path.encode('utf-8'), hashlib.sha256).hexdigest() + token = self._download_webpage( + 'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id) def tokenize_url(url, token): - return ''.join([url, '?hdnea=', token]) - - # May have higher quality video - sd_url = try_get( - stream, lambda x: x['streams']['hls']['sd'], compat_str) - if sd_url: - format_urls.append(tokenize_url(sd_url, token)) - else: - sd_low_url = try_get( - stream, lambda x: x['streams']['hls']['sd-low'], compat_str) - format_urls.append(tokenize_url(sd_low_url, token)) - - formats = [] - for format_url in format_urls: - if format_url: - formats.extend( - self._extract_m3u8_formats(format_url, video_id, 'mp4')) + return update_url_query(url, { + 'hdnea': token, + }) + + for sd in ('720', 'sd', 'sd-low'): + sd_url = try_get( + stream, lambda x: x['streams']['hls'][sd], compat_str) + if not sd_url: + continue + formats = self._extract_m3u8_formats( + tokenize_url(sd_url, token), video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) + if formats: + break self._sort_formats(formats) subtitles = {} @@ -168,18 +168,26 @@ class ABCIViewIE(InfoExtractor): 'ext': 'vtt', }] + is_live = video_params.get('livestream') == '1' + if is_live: + title = self._live_title(title) + return { 'id': video_id, 'title': title, - 'description': self._html_search_meta(['og:description', 'twitter:description'], webpage), - 'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage), + 'description': video_params.get('description'), + 'thumbnail': video_params.get('thumbnail'), 'duration': int_or_none(video_params.get('eventDuration')), 'timestamp': parse_iso8601(video_params.get('pubDate'), ' '), - 'series': video_params.get('seriesTitle'), + 'series': unescapeHTML(video_params.get('seriesTitle')), 'series_id': video_params.get('seriesHouseNumber') or video_id[:7], - 'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)), - 'episode': self._html_search_meta('episode_title', webpage, default=None), + 'season_number': int_or_none(self._search_regex( + r'\bSeries\s+(\d+)\b', title, 'season number', default=None)), + 'episode_number': int_or_none(self._search_regex( + r'\bEp\s+(\d+)\b', title, 'episode number', default=None)), + 'episode_id': house_number, 'uploader_id': video_params.get('channel'), 'formats': formats, 'subtitles': subtitles, + 'is_live': is_live, }