import re
from .common import InfoExtractor
+from ..compat import compat_str
from ..utils import (
ExtractorError,
determine_ext,
int_or_none,
+ float_or_none,
+ js_to_json,
+ orderedSet,
strip_jsonp,
+ strip_or_none,
unified_strdate,
+ url_or_none,
US_RATINGS,
)
_VALID_URL = r'''(?x)https?://
(?:
# Direct video URL
- (?:%s)/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+ (?:%s)/(?:(?:vir|port)alplayer|video)/(?P<id>[0-9]+)(?:[?/]|$) |
# Article with embedded player (or direct video)
- (?:www\.)?pbs\.org/(?:[^/]+/){
2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
+ (?:www\.)?pbs\.org/(?:[^/]+/){
1,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player
(?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
)
''' % '|'.join(list(zip(*_STATIONS))[0])
+ _GEO_COUNTRIES = ['US']
+
_TESTS = [
{
'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
- 'md5': 'ce1888486f0908d555a8093cac9a7362',
+ 'md5': '173dc391afd361fa72eab5d3d918968d',
'info_dict': {
'id': '2365006249',
'ext': 'mp4',
'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
- 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
+ 'description': 'md5:31b664af3c65fd07fa460d306b837d00',
'duration': 3190,
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
- 'md5': '143c98aa54a346738a3d78f54c925321',
+ 'md5': '6f722cb3c3982186d34b0f13374499c7',
'info_dict': {
'id': '2365297690',
'ext': 'mp4',
'title': 'FRONTLINE - Losing Iraq',
- 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+ 'description': 'md5:5979a4d069b157f622d02bff62fbe654',
'duration': 5050,
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- }
},
{
'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
'id': '2201174722',
'ext': 'mp4',
'title': 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist',
- 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
+ 'description': 'md5:86ab9a3d04458b876147b355788b8781',
'duration': 801,
},
},
'info_dict': {
'id': '2365297708',
'ext': 'mp4',
- 'description': 'md5:68d87ef760660eb564455eb30ca464fe',
'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
+ 'description': 'md5:657897370e09e2bc6bf0f8d2cd313c6b',
'duration': 6559,
- 'thumbnail': 're:^https?://.*\.jpg$',
- },
- 'params': {
- 'skip_download': True, # requires ffmpeg
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
'description': 'md5:c741d14e979fc53228c575894094f157',
'title': 'NOVA - Killer Typhoon',
'duration': 3172,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140122',
'age_limit': 10,
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
},
'playlist_count': 2,
},
+ {
+ 'url': 'http://www.pbs.org/wgbh/americanexperience/films/great-war/',
+ 'info_dict': {
+ 'id': 'great-war',
+ },
+ 'playlist_count': 3,
+ },
{
'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
'info_dict': {
'display_id': 'player',
'ext': 'mp4',
'title': 'American Experience - Death and the Civil War, Chapter 1',
- 'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+ 'description': 'md5:67fa89a9402e2ee7d08f53b920674c18',
'duration': 682,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True, # requires ffmpeg
},
},
{
- 'url': 'http://video.pbs.org/video/2365367186/',
+ 'url': 'http://www.pbs.org/video/2365245528/',
+ 'md5': '115223d41bd55cda8ae5cd5ed4e11497',
'info_dict': {
- 'id': '2365367186',
- 'display_id': '2365367186',
+ 'id': '2365245528',
+ 'display_id': '2365245528',
'ext': 'mp4',
- 'title': 'To Catch A Comet - Full Episode',
- 'description': 'On November 12, 2014, billions of kilometers from Earth, spacecraft orbiter Rosetta and lander Philae did what no other had dared to attempt \u2014 land on the volatile surface of a comet as it zooms around the sun at 67,000 km/hr. The European Space Agency hopes this mission can help peer into our past and unlock secrets of our origins.',
- 'duration': 3342,
- 'thumbnail': 're:^https?://.*\.jpg$',
- },
- 'params': {
- 'skip_download': True, # requires ffmpeg
+ 'title': 'FRONTLINE - United States of Secrets (Part One)',
+ 'description': 'md5:55756bd5c551519cc4b7703e373e217e',
+ 'duration': 6851,
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
- 'skip': 'Expired',
},
{
# Video embedded in iframe containing angle brackets as attribute's value (e.g.
# "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
- # https://github.com/rg3/youtube-dl/issues/7059)
+ # https://github.com/ytdl-org/youtube-dl/issues/7059)
'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
+ 'md5': '59b0ef5009f9ac8a319cc5efebcd865e',
'info_dict': {
'id': '2365546844',
'display_id': 'a-chefs-life-season-3-episode-5-prickly-business',
'ext': 'mp4',
'title': "A Chef's Life - Season 3, Ep. 5: Prickly Business",
- 'description': 'md5:61db2ddf27c9912f09c241014b118ed1',
+ 'description': 'md5:c0ff7475a4b70261c7e58f493c2792a5',
'duration': 1480,
- 'thumbnail': 're:^https?://.*\.jpg$',
- },
- 'params': {
- 'skip_download': True, # requires ffmpeg
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
'display_id': 'the-atomic-artists',
'ext': 'mp4',
'title': 'FRONTLINE - The Atomic Artists',
- 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+ 'description': 'md5:f677e4520cfacb4a5ce1471e31b57800',
'duration': 723,
- 'thumbnail': 're:^https?://.*\.jpg$',
+ 'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True, # requires ffmpeg
},
},
+ {
+ # Serves hd only via wigget/partnerplayer page
+ 'url': 'http://www.pbs.org/video/2365641075/',
+ 'md5': 'fdf907851eab57211dd589cf12006666',
+ 'info_dict': {
+ 'id': '2365641075',
+ 'ext': 'mp4',
+ 'title': 'FRONTLINE - Netanyahu at War',
+ 'duration': 6852,
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ 'formats': 'mincount:8',
+ },
+ },
+ {
+ # https://github.com/ytdl-org/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$',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ },
+ {
+ 'url': 'http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/',
+ 'info_dict': {
+ 'id': '2365936247',
+ 'ext': 'mp4',
+ 'title': 'Antiques Roadshow - Indianapolis, Hour 2',
+ 'description': 'md5:524b32249db55663e7231b6b8d1671a2',
+ 'duration': 3180,
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['HTTP Error 403: Forbidden'],
+ },
+ {
+ 'url': 'https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/',
+ 'info_dict': {
+ 'id': '3007193718',
+ 'ext': 'mp4',
+ 'title': "Victoria - A Soldier's Daughter / The Green-Eyed Monster",
+ 'description': 'md5:37efbac85e0c09b009586523ec143652',
+ 'duration': 6292,
+ 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['HTTP Error 403: Forbidden'],
+ },
+ {
+ 'url': 'https://player.pbs.org/partnerplayer/tOz9tM5ljOXQqIIWke53UA==/',
+ 'info_dict': {
+ 'id': '3011407934',
+ 'ext': 'mp4',
+ 'title': 'Stories from the Stage - Road Trip',
+ 'duration': 1619,
+ 'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'expected_warnings': ['HTTP Error 403: Forbidden'],
+ },
{
'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
'only_matching': True,
{
'url': 'http://watch.knpb.org/video/2365616055/',
'only_matching': True,
+ },
+ {
+ 'url': 'https://player.pbs.org/portalplayer/3004638221/?uid=',
+ 'only_matching': True,
}
]
_ERRORS = {
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)
+ description = None
+
presumptive_id = mobj.group('presumptive_id')
display_id = presumptive_id
if presumptive_id:
webpage = self._download_webpage(url, display_id)
+ description = strip_or_none(self._og_search_description(
+ webpage, default=None) or self._html_search_meta(
+ 'description', webpage, default=None))
upload_date = unified_strdate(self._search_regex(
r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
webpage, 'upload date', default=None))
# tabbed frontline videos
- tabbed_videos = re.findall(
- r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
- if tabbed_videos:
- return tabbed_videos, presumptive_id, upload_date
+ MULTI_PART_REGEXES = (
+ r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"',
+ r'<a[^>]+href=["\']#(?:video-|part)\d+["\'][^>]+data-cove[Ii]d=["\'](\d+)',
+ )
+ for p in MULTI_PART_REGEXES:
+ tabbed_videos = orderedSet(re.findall(p, webpage))
+ if tabbed_videos:
+ return tabbed_videos, presumptive_id, upload_date, description
MEDIA_ID_REGEXES = [
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer
r'<section[^>]+data-coveid="(\d+)"', # coveplayer from http://www.pbs.org/wgbh/frontline/film/real-csi/
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
+ r"(?s)window\.PBS\.playerConfig\s*=\s*{.*?id\s*:\s*'([0-9]+)',",
+ r'<div[^>]+\bdata-cove-id=["\'](\d+)"', # http://www.pbs.org/wgbh/roadshow/watch/episode/2105-indianapolis-hour-2/
+ r'<iframe[^>]+\bsrc=["\'](?:https?:)?//video\.pbs\.org/widget/partnerplayer/(\d+)', # https://www.pbs.org/wgbh/masterpiece/episodes/victoria-s2-e1/
]
media_id = self._search_regex(
MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
if media_id:
- return media_id, presumptive_id, upload_date
+ return media_id, presumptive_id, upload_date, description
# Fronline video embedded via flp
video_id = self._search_regex(
'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
presumptive_id, 'Downloading getdir JSON',
transform_source=strip_jsonp)
- return getdir['mid'], presumptive_id, upload_date
+ return getdir['mid'], presumptive_id, upload_date, description
for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
url = self._search_regex(
if url:
break
- mobj = re.match(self._VALID_URL, url)
+ if not url:
+ url = self._og_search_url(webpage)
+
+ mobj = re.match(
+ self._VALID_URL, self._proto_relative_url(url.strip()))
player_id = mobj.group('player_id')
if not display_id:
url, display_id, note='Downloading player page',
errnote='Could not download player page')
video_id = self._search_regex(
- r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
+ r'<div\s+id=["\']video_(\d+)', player_page, 'video ID',
+ default=None)
+ if not video_id:
+ video_info = self._extract_video_data(
+ player_page, 'video data', display_id)
+ video_id = compat_str(
+ video_info.get('id') or video_info['contentID'])
else:
video_id = mobj.group('id')
display_id = video_id
- return video_id, display_id, None
+ return video_id, display_id, None, description
+
+ def _extract_video_data(self, string, name, video_id, fatal=True):
+ return self._parse_json(
+ self._search_regex(
+ [r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+ r'window\.videoBridge\s*=\s*({.+?});'],
+ string, name, default='{}'),
+ video_id, transform_source=js_to_json, fatal=fatal)
def _real_extract(self, url):
- video_id, display_id, upload_date = self._extract_webpage(url)
+ video_id, display_id, upload_date, description = self._extract_webpage(url)
if isinstance(video_id, list):
entries = [self.url_result(
for vid_id in video_id]
return self.playlist_result(entries, display_id)
- info = self._download_json(
- 'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
- display_id)
+ info = None
+ redirects = []
+ redirect_urls = set()
+
+ def extract_redirect_urls(info):
+ for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+ redirect = info.get(encoding_name)
+ if not redirect:
+ continue
+ redirect_url = redirect.get('url')
+ if redirect_url and redirect_url not in redirect_urls:
+ redirects.append(redirect)
+ redirect_urls.add(redirect_url)
+ encodings = info.get('encodings')
+ if isinstance(encodings, list):
+ for encoding in encodings:
+ encoding_url = url_or_none(encoding)
+ if encoding_url and encoding_url not in redirect_urls:
+ redirects.append({'url': encoding_url})
+ redirect_urls.add(encoding_url)
+
+ chapters = []
+ # Player pages may also serve different qualities
+ for page in ('widget/partnerplayer', 'portalplayer'):
+ player = self._download_webpage(
+ 'http://player.pbs.org/%s/%s' % (page, video_id),
+ display_id, 'Downloading %s page' % page, fatal=False)
+ if player:
+ video_info = self._extract_video_data(
+ player, '%s video data' % page, display_id, fatal=False)
+ if video_info:
+ extract_redirect_urls(video_info)
+ if not info:
+ info = video_info
+ if not chapters:
+ raw_chapters = video_info.get('chapters') or []
+ if not raw_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
+ raw_chapters.append(chapter)
+ for chapter in raw_chapters:
+ 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 = []
- for encoding_name in ('recommended_encoding', 'alternate_encoding'):
- redirect = info.get(encoding_name)
- if not redirect:
- continue
- redirect_url = redirect.get('url')
- if not redirect_url:
- continue
+ http_url = None
+ for num, redirect in enumerate(redirects):
+ redirect_id = redirect.get('eeid')
redirect_info = self._download_json(
- redirect_url + '?format=json', display_id,
- 'Downloading %s video url info' % encoding_name)
+ '%s?format=json' % redirect['url'], display_id,
+ '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:
if determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
- format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
+ format_url, display_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.append({
'url': format_url,
- 'format_id': redirect.get('eeid'),
+ 'format_id': redirect_id,
})
+ if re.search(r'^https?://.*(?:\d+k|baseline)', format_url):
+ http_url = format_url
+ self._remove_duplicate_formats(formats)
+ m3u8_formats = list(filter(
+ lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
+ formats))
+ if http_url:
+ for m3u8_format in m3u8_formats:
+ bitrate = self._search_regex(r'(\d+)k', m3u8_format['url'], 'bitrate', default=None)
+ # Lower qualities (150k and 192k) are not available as HTTP formats (see [1]),
+ # we won't try extracting them.
+ # Since summer 2016 higher quality formats (4500k and 6500k) are also available
+ # albeit they are not documented in [2].
+ # 1. https://github.com/ytdl-org/youtube-dl/commit/cbc032c8b70a038a69259378c92b4ba97b42d491#commitcomment-17313656
+ # 2. https://projects.pbs.org/confluence/display/coveapi/COVE+Video+Specifications
+ if not bitrate or int(bitrate) < 400:
+ continue
+ f_url = re.sub(r'\d+k|baseline', bitrate + 'k', http_url)
+ # This may produce invalid links sometimes (e.g.
+ # http://www.pbs.org/wgbh/frontline/film/suicide-plan)
+ if not self._is_valid_url(f_url, display_id, 'http-%sk video' % bitrate):
+ continue
+ f = m3u8_format.copy()
+ f.update({
+ 'url': f_url,
+ 'format_id': m3u8_format['format_id'].replace('hls', 'http'),
+ 'protocol': 'http',
+ })
+ formats.append(f)
self._sort_formats(formats)
rating_str = info.get('rating')
'ext': 'ttml',
'url': closed_captions_url,
}]
+ mobj = re.search(r'/(\d+)_Encoded\.dfxp', closed_captions_url)
+ if mobj:
+ ttml_caption_suffix, ttml_caption_id = mobj.group(0, 1)
+ ttml_caption_id = int(ttml_caption_id)
+ subtitles['en'].extend([{
+ 'url': closed_captions_url.replace(
+ ttml_caption_suffix, '/%d_Encoded.srt' % (ttml_caption_id + 1)),
+ 'ext': 'srt',
+ }, {
+ 'url': closed_captions_url.replace(
+ ttml_caption_suffix, '/%d_Encoded.vtt' % (ttml_caption_id + 2)),
+ 'ext': 'vtt',
+ }])
# info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
# 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
return {
'id': video_id,
'display_id': display_id,
'title': info['title'],
- 'description': info['program'].get('description'),
+ 'description': description,
'thumbnail': info.get('image_url'),
'duration': int_or_none(info.get('duration')),
'age_limit': age_limit,
'upload_date': upload_date,
'formats': formats,
'subtitles': subtitles,
+ 'chapters': chapters,
}
projects / youtube-dl / blobdiff