_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',
'description': 'md5:36f341ae62e251b8f5bd2b754b95a071',
'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',
'description': 'md5:4d3eaa01f94e61b3e73704735f1196d9',
'duration': 5050,
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- }
},
{
'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
'duration': 6559,
'thumbnail': 're:^https?://.*\.jpg$',
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
'upload_date': '20140122',
'age_limit': 10,
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
},
{
'url': 'http://www.pbs.org/video/2365245528/',
+ 'md5': '115223d41bd55cda8ae5cd5ed4e11497',
'info_dict': {
'id': '2365245528',
'display_id': '2365245528',
'duration': 6851,
'thumbnail': 're:^https?://.*\.jpg$',
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
# 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)
'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
+ 'md5': '84ced42850d78f1d4650297356e95e6f',
'info_dict': {
'id': '2365546844',
'display_id': 'a-chefs-life-season-3-episode-5-prickly-business',
'duration': 1480,
'thumbnail': 're:^https?://.*\.jpg$',
},
- 'params': {
- 'skip_download': True, # requires ffmpeg
- },
},
{
# Frontline video embedded via flp2012.js
'skip_download': True, # requires ffmpeg
},
},
+ {
+ # Serves hd only via wigget/partnerplayer page
+ 'url': 'http://www.pbs.org/video/2365641075/',
+ 'md5': 'acfd4c400b48149a44861cb16dd305cf',
+ 'info_dict': {
+ 'id': '2365641075',
+ 'ext': 'mp4',
+ 'title': 'FRONTLINE - Netanyahu at War',
+ 'duration': 6852,
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'formats': 'mincount:8',
+ },
+ },
{
'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
'only_matching': True,
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-\d+["\'][^>]+data-coveid=["\'](\d+)',
+ )
+ for p in MULTI_PART_REGEXES:
+ tabbed_videos = re.findall(p, webpage)
+ if tabbed_videos:
+ return tabbed_videos, presumptive_id, upload_date
MEDIA_ID_REGEXES = [
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
for vid_id in video_id]
return self.playlist_result(entries, 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)
+
try:
- info = self._download_json(
+ video_info = self._download_json(
'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
display_id, 'Downloading video info JSON')
+ extract_redirect_urls(video_info)
+ info = video_info
except ExtractorError as e:
+ # videoInfo API may not work for some videos
if not isinstance(e.cause, compat_HTTPError) or e.cause.code != 404:
raise
- # videoInfo API may not work for some videos, fallback to portalplayer API
+
+ # Player pages may also serve different qualities
+ for page in ('widget/partnerplayer', 'portalplayer'):
player = self._download_webpage(
- 'http://player.pbs.org/portalplayer/%s' % video_id, display_id)
- info = self._parse_json(
- self._search_regex(
- r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
- player, 'video data', default='{}'),
- display_id, transform_source=js_to_json, fatal=False)
+ 'http://player.pbs.org/%s/%s' % (page, video_id),
+ display_id, 'Downloading %s page' % page, fatal=False)
+ if player:
+ video_info = self._parse_json(
+ self._search_regex(
+ r'(?s)PBS\.videoData\s*=\s*({.+?});\n',
+ player, '%s video data' % page, default='{}'),
+ display_id, transform_source=js_to_json, fatal=False)
+ if video_info:
+ extract_redirect_urls(video_info)
+ if not info:
+ info = video_info
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))
if redirect_info['status'] == 'error':
raise ExtractorError(
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' and f.get('resolution') != 'multiple',
+ formats))
+ if http_url:
+ for m3u8_format in m3u8_formats:
+ bitrate = self._search_regex(r'(\d+k)', m3u8_format['url'], 'bitrate', default=None)
+ if not bitrate:
+ continue
+ if bitrate == '192k':
+ bitrate = 'baseline'
+ f = m3u8_format.copy()
+ f.update({
+ 'url': re.sub(r'\d+k|baseline', bitrate, http_url),
+ 'format_id': m3u8_format['format_id'].replace('hls', 'http'),
+ 'protocol': 'http',
})
+ formats.append(f)
self._sort_formats(formats)
rating_str = info.get('rating')
projects / youtube-dl / blobdiff