X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ced7488f6d3a519b2c1b1cbd31048743fb8285bd..9113dfef91df19343cf76c6274dd0a85258c1004:/youtube_dl/extractor/pbs.py diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index b490ef7..f11d5da 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -8,7 +8,9 @@ from ..utils import ( ExtractorError, determine_ext, int_or_none, + float_or_none, js_to_json, + orderedSet, strip_jsonp, strip_or_none, unified_strdate, @@ -185,14 +187,16 @@ class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: # Direct video URL - (?:%s)/(?:viralplayer|video)/(?P[0-9]+)/? | + (?:%s)/(?:(?:vir|port)alplayer|video)/(?P[0-9]+)(?:[?/]|$) | # Article with embedded player (or direct video) - (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | + (?:www\.)?pbs\.org/(?:[^/]+/){1,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+)/ ) ''' % '|'.join(list(zip(*_STATIONS))[0]) + _GEO_COUNTRIES = ['US'] + _TESTS = [ { 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', @@ -236,7 +240,7 @@ class PBSIE(InfoExtractor): 'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full', 'description': 'md5:657897370e09e2bc6bf0f8d2cd313c6b', 'duration': 6559, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, }, { @@ -249,7 +253,7 @@ class PBSIE(InfoExtractor): 'description': 'md5:c741d14e979fc53228c575894094f157', 'title': 'NOVA - Killer Typhoon', 'duration': 3172, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'upload_date': '20140122', 'age_limit': 10, }, @@ -261,6 +265,13 @@ class PBSIE(InfoExtractor): }, 'playlist_count': 2, }, + { + 'url': 'http://www.pbs.org/wgbh/americanexperience/films/great-war/', + 'info_dict': { + 'id': 'great-war', + }, + 'playlist_count': 3, + }, { 'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/', 'info_dict': { @@ -270,7 +281,7 @@ class PBSIE(InfoExtractor): 'title': 'American Experience - Death and the Civil War, Chapter 1', 'description': 'md5:67fa89a9402e2ee7d08f53b920674c18', 'duration': 682, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -286,7 +297,7 @@ class PBSIE(InfoExtractor): 'title': 'FRONTLINE - United States of Secrets (Part One)', 'description': 'md5:55756bd5c551519cc4b7703e373e217e', 'duration': 6851, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, }, { @@ -302,7 +313,7 @@ class PBSIE(InfoExtractor): 'title': "A Chef's Life - Season 3, Ep. 5: Prickly Business", 'description': 'md5:c0ff7475a4b70261c7e58f493c2792a5', 'duration': 1480, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, }, { @@ -315,7 +326,7 @@ class PBSIE(InfoExtractor): 'title': 'FRONTLINE - The Atomic Artists', 'description': 'md5:f677e4520cfacb4a5ce1471e31b57800', 'duration': 723, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', }, 'params': { 'skip_download': True, # requires ffmpeg @@ -330,10 +341,25 @@ class PBSIE(InfoExtractor): 'ext': 'mp4', 'title': 'FRONTLINE - Netanyahu at War', 'duration': 6852, - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'formats': 'mincount:8', }, }, + { + # https://github.com/rg3/youtube-dl/issues/13801 + 'url': 'https://www.pbs.org/video/pbs-newshour-full-episode-july-31-2017-1501539057/', + 'info_dict': { + 'id': '3003333873', + 'ext': 'mp4', + 'title': 'PBS NewsHour - full episode July 31, 2017', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'duration': 3265, + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + }, { 'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true', 'only_matching': True, @@ -341,6 +367,10 @@ class PBSIE(InfoExtractor): { 'url': 'http://watch.knpb.org/video/2365616055/', 'only_matching': True, + }, + { + 'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=', + 'only_matching': True, } ] _ERRORS = { @@ -350,6 +380,15 @@ class PBSIE(InfoExtractor): 410: 'This video has expired and is no longer available for online streaming.', } + def _real_initialize(self): + cookie = (self._download_json( + 'http://localization.services.pbs.org/localize/auto/cookie/', + None, headers=self.geo_verification_headers(), fatal=False) or {}).get('cookie') + if cookie: + station = self._search_regex(r'#?s=\["([^"]+)"', cookie, 'station') + if station: + self._set_cookie('.pbs.org', 'pbsol.station', station) + def _extract_webpage(self, url): mobj = re.match(self._VALID_URL, url) @@ -370,10 +409,10 @@ class PBSIE(InfoExtractor): # tabbed frontline videos MULTI_PART_REGEXES = ( r']+class="videotab[^"]*"[^>]+vid="(\d+)"', - r']+href=["\']#video-\d+["\'][^>]+data-coveid=["\'](\d+)', + r']+href=["\']#(?:video-|part)\d+["\'][^>]+data-cove[Ii]d=["\'](\d+)', ) for p in MULTI_PART_REGEXES: - tabbed_videos = re.findall(p, webpage) + tabbed_videos = orderedSet(re.findall(p, webpage)) if tabbed_videos: return tabbed_videos, presumptive_id, upload_date, description @@ -382,6 +421,7 @@ class PBSIE(InfoExtractor): r'class="coveplayerid">([^<]+)<', # coveplayer r']+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/ r'', # jwplayer + r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',", ] media_id = self._search_regex( @@ -413,6 +453,9 @@ class PBSIE(InfoExtractor): if url: break + if not url: + url = self._og_search_url(webpage) + mobj = re.match(self._VALID_URL, url) player_id = mobj.group('player_id') @@ -453,6 +496,7 @@ class PBSIE(InfoExtractor): redirects.append(redirect) redirect_urls.add(redirect_url) + chapters = [] # Player pages may also serve different qualities for page in ('widget/partnerplayer', 'portalplayer'): player = self._download_webpage( @@ -468,6 +512,20 @@ class PBSIE(InfoExtractor): extract_redirect_urls(video_info) if not info: info = video_info + if not chapters: + for chapter_data in re.findall(r'(?s)chapters\.push\(({.*?})\)', player): + chapter = self._parse_json(chapter_data, video_id, js_to_json, fatal=False) + if not chapter: + continue + start_time = float_or_none(chapter.get('start_time'), 1000) + duration = float_or_none(chapter.get('duration'), 1000) + if start_time is None or duration is None: + continue + chapters.append({ + 'start_time': start_time, + 'end_time': start_time + duration, + 'title': chapter.get('title'), + }) formats = [] http_url = None @@ -476,14 +534,17 @@ class PBSIE(InfoExtractor): redirect_info = self._download_json( '%s?format=json' % redirect['url'], display_id, - 'Downloading %s video url info' % (redirect_id or num)) + 'Downloading %s video url info' % (redirect_id or num), + headers=self.geo_verification_headers()) if redirect_info['status'] == 'error': + message = self._ERRORS.get( + redirect_info['http_code'], redirect_info['message']) + if redirect_info['http_code'] == 403: + self.raise_geo_restricted( + msg=message, countries=self._GEO_COUNTRIES) raise ExtractorError( - '%s said: %s' % ( - self.IE_NAME, - self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])), - expected=True) + '%s said: %s' % (self.IE_NAME, message), expected=True) format_url = redirect_info.get('url') if not format_url: @@ -501,7 +562,7 @@ class PBSIE(InfoExtractor): http_url = format_url self._remove_duplicate_formats(formats) m3u8_formats = list(filter( - lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple', + lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none', formats)) if http_url: for m3u8_format in m3u8_formats: @@ -558,7 +619,7 @@ class PBSIE(InfoExtractor): # Try turning it to 'program - title' naming scheme if possible alt_title = info.get('program', {}).get('title') if alt_title: - info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-:]+', '', info['title']) + info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + r'[\s\-:]+', '', info['title']) description = info.get('description') or info.get( 'program', {}).get('description') or description @@ -574,4 +635,5 @@ class PBSIE(InfoExtractor): 'upload_date': upload_date, 'formats': formats, 'subtitles': subtitles, + 'chapters': chapters, }