X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/3477c644417600d9ec8f8d2a44f82da0a4b15eb5..bb0545d1ede66375ab242a96da748913992bbf0d:/youtube_dl/extractor/abc.py diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index c0e5d1a..6637f4f 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -1,18 +1,26 @@ from __future__ import unicode_literals +import hashlib +import hmac import re +import time from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, js_to_json, int_or_none, + parse_iso8601, + try_get, + unescapeHTML, + update_url_query, ) class ABCIE(InfoExtractor): IE_NAME = 'abc.net.au' - _VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P\d+)' + _VALID_URL = r'https?://(?:www\.)?abc\.net\.au/news/(?:[^/]+/){1,2}(?P\d+)' _TESTS = [{ 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', @@ -23,6 +31,7 @@ class ABCIE(InfoExtractor): 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, + 'skip': 'this video has expired', }, { 'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326', 'md5': 'db2a5369238b51f9811ad815b69dc086', @@ -36,6 +45,7 @@ class ABCIE(InfoExtractor): 'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill', }, 'add_ie': ['Youtube'], + 'skip': 'Not accessible from Travis CI server', }, { 'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080', 'md5': 'b96eee7c9edf4fc5a358a0252881cc1f', @@ -58,6 +68,9 @@ class ABCIE(InfoExtractor): r'inline(?PVideo|Audio|YouTube)Data\.push\((?P[^)]+)\);', webpage) if mobj is None: + expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?(.+?)', webpage, 'expired', None) + if expired: + raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True) raise ExtractorError('Unable to extract video urls') urls_info = self._parse_json( @@ -88,3 +101,93 @@ class ABCIE(InfoExtractor): 'description': self._og_search_description(webpage), 'thumbnail': self._og_search_thumbnail(webpage), } + + +class ABCIViewIE(InfoExtractor): + IE_NAME = 'abc.net.au:iview' + _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': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00', + 'md5': '67715ce3c78426b11ba167d875ac6abf', + 'info_dict': { + 'id': 'LE1927H001S00', + 'ext': 'mp4', + 'title': "Series 11 Ep 1", + 'series': "Gruen", + 'description': 'md5:52cc744ad35045baf6aded2ce7287f67', + 'upload_date': '20190925', + 'uploader_id': 'abc1', + 'timestamp': 1569445289, + }, + 'params': { + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + 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 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 = {} + src_vtt = stream.get('captions', {}).get('src-vtt') + if src_vtt: + subtitles['en'] = [{ + 'url': src_vtt, + 'ext': 'vtt', + }] + + is_live = video_params.get('livestream') == '1' + if is_live: + title = self._live_title(title) + + return { + 'id': video_id, + 'title': title, + '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': unescapeHTML(video_params.get('seriesTitle')), + 'series_id': video_params.get('seriesHouseNumber') or video_id[:7], + '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, + }