This commit is contained in:
Gilles Habran 2016-04-04 08:56:16 +02:00
commit 2424572262
27 changed files with 332 additions and 80 deletions

View File

@ -95,6 +95,7 @@ from .camdemy import (
CamdemyIE,
CamdemyFolderIE
)
from .camwithher import CamWithHerIE
from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE
from .canvas import CanvasIE
@ -103,6 +104,7 @@ from .cbc import (
CBCPlayerIE,
)
from .cbs import CBSIE
from .cbsinteractive import CBSInteractiveIE
from .cbsnews import (
CBSNewsIE,
CBSNewsLiveVideoIE,
@ -128,7 +130,6 @@ from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
from .cnbc import CNBCIE
from .cnet import CNETIE
from .cnn import (
CNNIE,
CNNBlogsIE,

View File

@ -22,6 +22,9 @@ class AENetworksIE(InfoExtractor):
'ext': 'mp4',
'title': "Bet You Didn't Know: Valentine's Day",
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
@ -37,6 +40,9 @@ class AENetworksIE(InfoExtractor):
'ext': 'mp4',
'title': 'Winter Is Coming',
'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
'timestamp': 1338306241,
'upload_date': '20120529',
'uploader': 'AENE-NEW',
},
'add_ie': ['ThePlatform'],
}, {
@ -69,8 +75,9 @@ class AENetworksIE(InfoExtractor):
info = self._search_json_ld(webpage, video_id, fatal=False)
info.update({
'_type': 'url_transparent',
'url': smuggle_url(update_url_query(
video_url, query), {
'url': smuggle_url(
update_url_query(video_url, query),
{
'sig': {
'key': 'crazyjava',
'secret': 's3cr3t'},

View File

@ -328,6 +328,7 @@ class BBCCoUkIE(InfoExtractor):
'format_id': '%s_%s' % (service, format['format_id']),
'abr': abr,
'acodec': acodec,
'vcodec': 'none',
})
formats.extend(conn_formats)
return formats

View File

@ -15,6 +15,9 @@ class BravoTVIE(InfoExtractor):
'ext': 'mp4',
'title': 'Last Chance Kitchen Returns',
'description': 'S13: Last Chance Kitchen Returns for Top Chef Season 13',
'timestamp': 1448926740,
'upload_date': '20151130',
'uploader': 'NBCU-BRAV',
}
}

View File

@ -46,6 +46,9 @@ class BrightcoveLegacyIE(InfoExtractor):
'title': 'Xavier Sala i Martín: “Un banc que no presta és un banc zombi que no serveix per a res”',
'uploader': '8TV',
'description': 'md5:a950cc4285c43e44d763d036710cd9cd',
'timestamp': 1368213670,
'upload_date': '20130510',
'uploader_id': '1589608506001',
}
},
{
@ -57,6 +60,9 @@ class BrightcoveLegacyIE(InfoExtractor):
'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
'uploader': 'Oracle',
'timestamp': 1344975024,
'upload_date': '20120814',
'uploader_id': '1460825906',
},
},
{
@ -68,6 +74,9 @@ class BrightcoveLegacyIE(InfoExtractor):
'title': 'This Bracelet Acts as a Personal Thermostat',
'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
'uploader': 'Mashable',
'timestamp': 1382041798,
'upload_date': '20131017',
'uploader_id': '1130468786001',
},
},
{
@ -85,14 +94,17 @@ class BrightcoveLegacyIE(InfoExtractor):
{
# test flv videos served by akamaihd.net
# From http://www.redbull.com/en/bike/stories/1331655643987/replay-uci-dh-world-cup-2014-from-fort-william
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3ABC2996102916001&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?%40videoPlayer=ref%3Aevent-stream-356&linkBaseURL=http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fvideos%2F1331655630249%2Freplay-uci-fort-william-2014-dh&playerKey=AQ%7E%7E%2CAAAApYJ7UqE%7E%2Cxqr_zXk0I-zzNndy8NlHogrCb5QdyZRf&playerID=1398061561001#__youtubedl_smuggle=%7B%22Referer%22%3A+%22http%3A%2F%2Fwww.redbull.com%2Fen%2Fbike%2Fstories%2F1331655643987%2Freplay-uci-dh-world-cup-2014-from-fort-william%22%7D',
# The md5 checksum changes on each download
'info_dict': {
'id': '2996102916001',
'id': '3750436379001',
'ext': 'flv',
'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
'uploader': 'Red Bull TV',
'uploader': 'RBTV Old (do not use)',
'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
'timestamp': 1409122195,
'upload_date': '20140827',
'uploader_id': '710858724001',
},
},
{
@ -106,6 +118,12 @@ class BrightcoveLegacyIE(InfoExtractor):
'playlist_mincount': 7,
},
]
FLV_VCODECS = {
1: 'SORENSON',
2: 'ON2',
3: 'H264',
4: 'VP8',
}
@classmethod
def _build_brighcove_url(cls, object_str):
@ -289,12 +307,16 @@ class BrightcoveLegacyIE(InfoExtractor):
playlist_title=playlist_info['mediaCollectionDTO']['displayName'])
def _extract_video_info(self, video_info):
publisher_id = video_info.get('publisherId')
info = {
'id': compat_str(video_info['id']),
'title': video_info['displayName'].strip(),
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
'uploader': video_info.get('publisherName'),
'uploader_id': compat_str(publisher_id) if publisher_id else None,
'duration': float_or_none(video_info.get('length'), 1000),
'timestamp': int_or_none(video_info.get('creationDate'), 1000),
}
renditions = video_info.get('renditions', []) + video_info.get('IOSRenditions', [])
@ -318,19 +340,30 @@ class BrightcoveLegacyIE(InfoExtractor):
ext = 'flv'
if ext is None:
ext = determine_ext(url)
size = rend.get('size')
tbr = int_or_none(rend.get('encodingRate'), 1000),
a_format = {
'format_id': 'http%s' % ('-%s' % tbr if tbr else ''),
'url': url,
'ext': ext,
'height': rend.get('frameHeight'),
'width': rend.get('frameWidth'),
'filesize': size if size != 0 else None,
'filesize': int_or_none(rend.get('size')) or None,
'tbr': tbr,
}
if rend.get('audioOnly'):
a_format.update({
'vcodec': 'none',
})
else:
a_format.update({
'height': int_or_none(rend.get('frameHeight')),
'width': int_or_none(rend.get('frameWidth')),
'vcodec': rend.get('videoCodec'),
})
# m3u8 manifests with remote == false are media playlists
# Not calling _extract_m3u8_formats here to save network traffic
if ext == 'm3u8':
a_format.update({
'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''),
'ext': 'mp4',
'protocol': 'm3u8',
})
@ -341,6 +374,8 @@ class BrightcoveLegacyIE(InfoExtractor):
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
'vcodec': self.FLV_VCODECS.get(video_info.get('FLVFullCodec')),
'filesize': int_or_none(video_info.get('FLVFullSize')),
})
if self._downloader.params.get('include_ads', False):
@ -396,6 +431,7 @@ class BrightcoveNewIE(InfoExtractor):
'formats': 'mincount:41',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
@ -480,7 +516,7 @@ class BrightcoveNewIE(InfoExtractor):
raise ExtractorError(json_data[0]['message'], expected=True)
raise
title = json_data['name']
title = json_data['name'].strip()
formats = []
for source in json_data.get('sources', []):
@ -533,7 +569,7 @@ class BrightcoveNewIE(InfoExtractor):
f.update({
'url': src or streaming_src,
'format_id': build_format_id('http' if src else 'http-streaming'),
'preference': 2 if src else 1,
'source_preference': 0 if src else -1,
})
else:
f.update({
@ -544,20 +580,22 @@ class BrightcoveNewIE(InfoExtractor):
formats.append(f)
self._sort_formats(formats)
description = json_data.get('description')
thumbnail = json_data.get('thumbnail')
timestamp = parse_iso8601(json_data.get('published_at'))
duration = float_or_none(json_data.get('duration'), 1000)
tags = json_data.get('tags', [])
subtitles = {}
for text_track in json_data.get('text_tracks', []):
if text_track.get('src'):
subtitles.setdefault(text_track.get('srclang'), []).append({
'url': text_track['src'],
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'description': json_data.get('description'),
'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
'duration': float_or_none(json_data.get('duration'), 1000),
'timestamp': parse_iso8601(json_data.get('published_at')),
'uploader_id': account_id,
'formats': formats,
'tags': tags,
'subtitles': subtitles,
'tags': json_data.get('tags', []),
}

View File

@ -0,0 +1,87 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
unified_strdate,
)
class CamWithHerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?camwithher\.tv/view_video\.php\?.*\bviewkey=(?P<id>\w+)'
_TESTS = [{
'url': 'http://camwithher.tv/view_video.php?viewkey=6e9a24e2c0e842e1f177&page=&viewtype=&category=',
'info_dict': {
'id': '5644',
'ext': 'flv',
'title': 'Periscope Tease',
'description': 'In the clouds teasing on periscope to my favorite song',
'duration': 240,
'view_count': int,
'comment_count': int,
'uploader': 'MileenaK',
'upload_date': '20160322',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://camwithher.tv/view_video.php?viewkey=6dfd8b7c97531a459937',
'only_matching': True,
}, {
'url': 'http://camwithher.tv/view_video.php?page=&viewkey=6e9a24e2c0e842e1f177&viewtype=&category=',
'only_matching': True,
}, {
'url': 'http://camwithher.tv/view_video.php?viewkey=b6c3b5bea9515d1a1fc4&page=&viewtype=&category=mv',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
flv_id = self._html_search_regex(
r'<a[^>]+href=["\']/download/\?v=(\d+)', webpage, 'video id')
# Video URL construction algorithm is reverse-engineered from cwhplayer.swf
rtmp_url = 'rtmp://camwithher.tv/clipshare/%s' % (
('mp4:%s.mp4' % flv_id) if int(flv_id) > 2010 else flv_id)
title = self._html_search_regex(
r'<div[^>]+style="float:left"[^>]*>\s*<h2>(.+?)</h2>', webpage, 'title')
description = self._html_search_regex(
r'>Description:</span>(.+?)</div>', webpage, 'description', default=None)
runtime = self._search_regex(
r'Runtime\s*:\s*(.+?) \|', webpage, 'duration', default=None)
if runtime:
runtime = re.sub(r'[\s-]', '', runtime)
duration = parse_duration(runtime)
view_count = int_or_none(self._search_regex(
r'Views\s*:\s*(\d+)', webpage, 'view count', default=None))
comment_count = int_or_none(self._search_regex(
r'Comments\s*:\s*(\d+)', webpage, 'comment count', default=None))
uploader = self._search_regex(
r'Added by\s*:\s*<a[^>]+>([^<]+)</a>', webpage, 'uploader', default=None)
upload_date = unified_strdate(self._search_regex(
r'Added on\s*:\s*([\d-]+)', webpage, 'upload date', default=None))
return {
'id': flv_id,
'url': rtmp_url,
'ext': 'flv',
'no_resume': True,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
'uploader': uploader,
'upload_date': upload_date,
}

View File

@ -33,6 +33,9 @@ class CBSIE(CBSBaseIE):
'title': 'Connect Chat feat. Garth Brooks',
'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
'duration': 1495,
'timestamp': 1385585425,
'upload_date': '20131127',
'uploader': 'CBSI-NEW',
},
'params': {
# rtmp download

View File

@ -1,12 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from ..utils import int_or_none
class CNETIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?cnet\.com/videos/(?P<id>[^/]+)/'
class CBSInteractiveIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video/share)/(?P<id>[^/?]+)'
_TESTS = [{
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'info_dict': {
@ -17,6 +19,8 @@ class CNETIE(ThePlatformIE):
'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
'uploader': 'Sarah Mitroff',
'duration': 70,
'timestamp': 1396479627,
'upload_date': '20140402',
},
}, {
'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
@ -28,15 +32,38 @@ class CNETIE(ThePlatformIE):
'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
'uploader': 'Ashley Esqueda',
'duration': 1482,
'timestamp': 1433289889,
'upload_date': '20150603',
},
}, {
'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
'info_dict': {
'id': 'bc1af9f0-a2b5-4e54-880d-0d95525781c0',
'ext': 'mp4',
'title': 'Video: Keeping Android smartphones and tablets secure',
'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
'uploader': 'Adrian Kingsley-Hughes',
'timestamp': 1448961720,
'upload_date': '20151201',
},
'params': {
# m3u8 download
'skip_download': True,
}
}]
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true'
MPX_ACCOUNTS = {
'cnet': 2288573011,
'zdnet': 2387448114,
}
def _real_extract(self, url):
display_id = self._match_id(url)
site, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"data-cnet-video(?:-uvp)?-options='([^']+)'",
r"data-(?:cnet|zdnet)-video(?:-uvp)?-options='([^']+)'",
webpage, 'data json')
data = self._parse_json(data_json, display_id)
vdata = data.get('video') or data['videos'][0]
@ -51,16 +78,15 @@ class CNETIE(ThePlatformIE):
uploader = None
uploader_id = None
metadata = self.get_metadata('kYEXFC/%s' % list(vdata['files'].values())[0], video_id)
description = vdata.get('description') or metadata.get('description')
duration = int_or_none(vdata.get('duration')) or metadata.get('duration')
formats = []
subtitles = {}
media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId'])
formats, subtitles = [], {}
if site == 'cnet':
formats, subtitles = self._extract_theplatform_smil(
self.TP_RELEASE_URL_TEMPLATE % media_guid_path, video_id)
for (fkey, vid) in vdata['files'].items():
if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
continue
release_url = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true' % vid
release_url = self.TP_RELEASE_URL_TEMPLATE % vid
if fkey == 'hds':
release_url += '&manifest=f4m'
tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
@ -68,15 +94,15 @@ class CNETIE(ThePlatformIE):
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
return {
info = self.get_metadata('kYEXFC/%s' % media_guid_path, video_id)
info.update({
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': metadata.get('thumbnail'),
'duration': duration,
'duration': int_or_none(vdata.get('duration')),
'uploader': uploader,
'uploader_id': uploader_id,
'subtitles': subtitles,
'formats': formats,
}
})
return info

View File

@ -5,7 +5,6 @@ from .common import InfoExtractor
from .cbs import CBSBaseIE
from ..utils import (
parse_duration,
find_xpath_attr,
)

View File

@ -14,6 +14,9 @@ class CNBCIE(InfoExtractor):
'ext': 'mp4',
'title': 'Fighting zombies is big business',
'description': 'md5:0c100d8e1a7947bd2feec9a5550e519e',
'timestamp': 1459332000,
'upload_date': '20160330',
'uploader': 'NBCU-CNBC',
},
'params': {
# m3u8 download

View File

@ -1335,7 +1335,7 @@ class InfoExtractor(object):
if not src or src in urls:
continue
urls.append(src)
ext = textstream.get('ext') or determine_ext(src) or mimetype2ext(textstream.get('type'))
ext = textstream.get('ext') or mimetype2ext(textstream.get('type')) or determine_ext(src)
lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang
subtitles.setdefault(lang, []).append({
'url': src,
@ -1515,9 +1515,16 @@ class InfoExtractor(object):
representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
media_template = representation_ms_info['media_template']
media_template = media_template.replace('$RepresentationID$', representation_id)
media_template = re.sub(r'\$(Number|Bandwidth)(?:%(0\d+)d)?\$', r'%(\1)\2d', media_template)
media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
media_template = re.sub(r'\$(Number|Bandwidth)%(\d+)\$', r'%(\1)\2d', media_template)
media_template.replace('$$', '$')
representation_ms_info['segment_urls'] = [media_template % {'Number': segment_number, 'Bandwidth': representation_attrib.get('bandwidth')} for segment_number in range(representation_ms_info['start_number'], representation_ms_info['total_number'] + representation_ms_info['start_number'])]
representation_ms_info['segment_urls'] = [
media_template % {
'Number': segment_number,
'Bandwidth': representation_attrib.get('bandwidth')}
for segment_number in range(
representation_ms_info['start_number'],
representation_ms_info['total_number'] + representation_ms_info['start_number'])]
if 'segment_urls' in representation_ms_info:
f.update({
'segment_urls': representation_ms_info['segment_urls'],

View File

@ -16,6 +16,9 @@ class FOXIE(InfoExtractor):
'title': 'Official Trailer: Gotham',
'description': 'Tracing the rise of the great DC Comics Super-Villains and vigilantes, Gotham reveals an entirely new chapter that has never been told.',
'duration': 129,
'timestamp': 1400020798,
'upload_date': '20140513',
'uploader': 'NEWA-FNG-FOXCOM',
},
'add_ie': ['ThePlatform'],
}

View File

@ -152,7 +152,7 @@ class InstagramUserIE(InfoExtractor):
if not page['items']:
break
max_id = page['items'][-1]['id']
max_id = page['items'][-1]['id'].split('_')[0]
media_url = (
'http://instagram.com/%s/media?max_id=%s' % (
uploader_id, max_id))

View File

@ -28,8 +28,8 @@ class LyndaBaseIE(InfoExtractor):
return
login_form = {
'username': username.encode('utf-8'),
'password': password.encode('utf-8'),
'username': username,
'password': password,
'remember': 'false',
'stayPut': 'false'
}

View File

@ -2,39 +2,48 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import sanitized_Request
from ..utils import (
smuggle_url,
float_or_none,
parse_iso8601,
update_url_query,
)
class MovieClipsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)'
_TEST = {
'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597?autoPlay=true&playlistId=5',
'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597',
'md5': '42b5a0352d4933a7bd54f2104f481244',
'info_dict': {
'id': 'pKIGmG83AqD9',
'display_id': 'warcraft-trailer-1-561180739597',
'ext': 'mp4',
'title': 'Warcraft Trailer 1',
'description': 'Watch Trailer 1 from Warcraft (2016). Legendarys WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1446843055,
'upload_date': '20151106',
'uploader': 'Movieclips',
},
'add_ie': ['ThePlatform'],
}
def _real_extract(self, url):
display_id = self._match_id(url)
req = sanitized_Request(url)
# it doesn't work if it thinks the browser it's too old
req.add_header('User-Agent', 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20150101 Firefox/43.0 (Chrome)')
webpage = self._download_webpage(req, display_id)
theplatform_link = self._html_search_regex(r'src="(http://player.theplatform.com/p/.*?)"', webpage, 'theplatform link')
title = self._html_search_regex(r'<title[^>]*>([^>]+)-\s*\d+\s*|\s*Movieclips.com</title>', webpage, 'title')
description = self._html_search_meta('description', webpage)
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video = next(v for v in self._parse_json(self._search_regex(
r'var\s+__REACT_ENGINE__\s*=\s*({.+});',
webpage, 'react engine'), video_id)['playlist']['videos'] if v['id'] == video_id)
return {
'_type': 'url_transparent',
'url': theplatform_link,
'title': title,
'display_id': display_id,
'description': description,
'ie_key': 'ThePlatform',
'url': smuggle_url(update_url_query(
video['contentUrl'], {'mbr': 'true'}), {'force_smil_url': True}),
'title': self._og_search_title(webpage),
'description': self._html_search_meta('description', webpage),
'duration': float_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('dateCreated')),
'thumbnail': video.get('defaultImage'),
'uploader': video.get('provider'),
}

View File

@ -21,6 +21,9 @@ class NationalGeographicIE(InfoExtractor):
'ext': 'mp4',
'title': 'Mating Crabs Busted by Sharks',
'description': 'md5:16f25aeffdeba55aaa8ec37e093ad8b3',
'timestamp': 1423523799,
'upload_date': '20150209',
'uploader': 'NAGS',
},
'add_ie': ['ThePlatform'],
},
@ -32,6 +35,9 @@ class NationalGeographicIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Real Jaws',
'description': 'md5:8d3e09d9d53a85cd397b4b21b2c77be6',
'timestamp': 1433772632,
'upload_date': '20150608',
'uploader': 'NAGS',
},
'add_ie': ['ThePlatform'],
},
@ -68,6 +74,9 @@ class NationalGeographicChannelIE(InfoExtractor):
'ext': 'mp4',
'title': 'Uncovering a Universal Knowledge',
'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
'timestamp': 1458680907,
'upload_date': '20160322',
'uploader': 'NEWA-FNG-NGTV',
},
'add_ie': ['ThePlatform'],
},
@ -79,6 +88,9 @@ class NationalGeographicChannelIE(InfoExtractor):
'ext': 'mp4',
'title': 'The Stunning Red Bird of Paradise',
'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
'timestamp': 1459362152,
'upload_date': '20160330',
'uploader': 'NEWA-FNG-NGTV',
},
'add_ie': ['ThePlatform'],
},

View File

@ -27,6 +27,9 @@ class NBCIE(InfoExtractor):
'ext': 'mp4',
'title': 'Jimmy Fallon Surprises Fans at Ben & Jerry\'s',
'description': 'Jimmy gives out free scoops of his new "Tonight Dough" ice cream flavor by surprising customers at the Ben & Jerry\'s scoop shop.',
'timestamp': 1424246400,
'upload_date': '20150218',
'uploader': 'NBCU-COM',
},
'params': {
# m3u8 download
@ -50,6 +53,9 @@ class NBCIE(InfoExtractor):
'ext': 'mp4',
'title': 'Star Wars Teaser',
'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
'timestamp': 1417852800,
'upload_date': '20141206',
'uploader': 'NBCU-COM',
},
'params': {
# m3u8 download
@ -78,6 +84,7 @@ class NBCIE(InfoExtractor):
theplatform_url = 'http:' + theplatform_url
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(theplatform_url, {'source_url': url}),
'id': video_id,
}
@ -93,6 +100,9 @@ class NBCSportsVPlayerIE(InfoExtractor):
'ext': 'flv',
'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
'timestamp': 1426270238,
'upload_date': '20150313',
'uploader': 'NBCU-SPORTS',
}
}, {
'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
@ -144,6 +154,9 @@ class CSNNEIE(InfoExtractor):
'ext': 'mp4',
'title': 'SNC evening update: Wright named Red Sox\' No. 5 starter.',
'description': 'md5:1753cfee40d9352b19b4c9b3e589b9e3',
'timestamp': 1459369979,
'upload_date': '20160330',
'uploader': 'NBCU-SPORTS',
}
}
@ -331,6 +344,7 @@ class MSNBCIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1406937606,
'upload_date': '20140802',
'uploader': 'NBCU-NEWS',
'categories': ['MSNBC/Topics/Franchise/Best of last night', 'MSNBC/Topics/General/Congress'],
},
}

View File

@ -63,8 +63,11 @@ class NownessIE(NownessBaseIE):
'title': 'Candor: The Art of Gesticulation',
'description': 'Candor: The Art of Gesticulation',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
'timestamp': 1446745676,
'upload_date': '20151105',
'uploader_id': '2385340575001',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://cn.nowness.com/story/kasper-bjorke-ft-jaakko-eino-kalevi-tnr',
'md5': 'e79cf125e387216f86b2e0a5b5c63aa3',
@ -74,8 +77,11 @@ class NownessIE(NownessBaseIE):
'title': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'description': 'Kasper Bjørke ft. Jaakko Eino Kalevi: TNR',
'thumbnail': 're:^https?://.*\.jpg',
'uploader': 'Nowness',
'timestamp': 1407315371,
'upload_date': '20140806',
'uploader_id': '2385340575001',
},
'add_ie': ['BrightcoveNew'],
}, {
# vimeo
'url': 'https://www.nowness.com/series/nowness-picks/jean-luc-godard-supercut',
@ -90,6 +96,7 @@ class NownessIE(NownessBaseIE):
'uploader': 'Cinema Sem Lei',
'uploader_id': 'cinemasemlei',
},
'add_ie': ['Vimeo'],
}]
def _real_extract(self, url):

View File

@ -64,8 +64,8 @@ class PluralsightIE(PluralsightBaseIE):
login_form = self._hidden_inputs(login_page)
login_form.update({
'Username': username.encode('utf-8'),
'Password': password.encode('utf-8'),
'Username': username,
'Password': password,
})
post_url = self._search_regex(

View File

@ -24,6 +24,9 @@ class SBSIE(InfoExtractor):
'description': 'md5:f250a9856fca50d22dec0b5b8015f8a5',
'thumbnail': 're:http://.*\.jpg',
'duration': 308,
'timestamp': 1408613220,
'upload_date': '20140821',
'uploader': 'SBSC',
},
}, {
'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed',
@ -57,6 +60,7 @@ class SBSIE(InfoExtractor):
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'id': video_id,
'url': smuggle_url(theplatform_url, {'force_smil_url': True}),
'url': smuggle_url(self._proto_relative_url(theplatform_url), {'force_smil_url': True}),
}

View File

@ -12,7 +12,7 @@ from ..utils import (
class ScreencastIE(InfoExtractor):
_VALID_URL = r'https?://www\.screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
_VALID_URL = r'https?://(?:www\.)?screencast\.com/t/(?P<id>[a-zA-Z0-9]+)'
_TESTS = [{
'url': 'http://www.screencast.com/t/3ZEjQXlT',
'md5': '917df1c13798a3e96211dd1561fded83',
@ -53,8 +53,10 @@ class ScreencastIE(InfoExtractor):
'description': 'md5:7b9f393bc92af02326a5c5889639eab0',
'thumbnail': 're:^https?://.*\.(?:gif|jpg)$',
}
},
]
}, {
'url': 'http://screencast.com/t/aAB3iowa',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -94,8 +96,9 @@ class ScreencastIE(InfoExtractor):
title = self._og_search_title(webpage, default=None)
if title is None:
title = self._html_search_regex(
[r'<b>Title:</b> ([^<]*)</div>',
r'class="tabSeperator">></span><span class="tabText">(.*?)<'],
[r'<b>Title:</b> ([^<]+)</div>',
r'class="tabSeperator">></span><span class="tabText">(.+?)<',
r'<title>([^<]+)</title>'],
webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage, default=None)

View File

@ -76,6 +76,8 @@ class ThePlatformBaseIE(OnceIE):
'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'],
'duration': int_or_none(info.get('duration'), 1000),
'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
'uploader': info.get('billingCode'),
}
@ -94,6 +96,9 @@ class ThePlatformIE(ThePlatformBaseIE):
'title': 'Blackberry\'s big, bold Z30',
'description': 'The Z30 is Blackberry\'s biggest, baddest mobile messaging device yet.',
'duration': 247,
'timestamp': 1383239700,
'upload_date': '20131031',
'uploader': 'CBSI-NEW',
},
'params': {
# rtmp download
@ -107,6 +112,9 @@ class ThePlatformIE(ThePlatformBaseIE):
'ext': 'flv',
'description': 'md5:ac330c9258c04f9d7512cf26b9595409',
'title': 'Tesla Model S: A second step towards a cleaner motoring future',
'timestamp': 1426176191,
'upload_date': '20150312',
'uploader': 'CBSI-NEW',
},
'params': {
# rtmp download
@ -119,6 +127,7 @@ class ThePlatformIE(ThePlatformBaseIE):
'ext': 'mp4',
'description': 'md5:644ad9188d655b742f942bf2e06b002d',
'title': 'HIGHLIGHTS: USA bag first ever series Cup win',
'uploader': 'EGSM',
}
}, {
'url': 'http://player.theplatform.com/p/NnzsPC/widget/select/media/4Y0TlYUr_ZT7',
@ -135,6 +144,7 @@ class ThePlatformIE(ThePlatformBaseIE):
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1435752600,
'upload_date': '20150701',
'uploader': 'NBCU-NEWS',
},
}, {
# From http://www.nbc.com/the-blacklist/video/sir-crispin-crandall/2928790?onid=137781#vc137781=1

View File

@ -19,6 +19,10 @@ class TheStarIE(InfoExtractor):
'uploader_id': '794267642001',
'timestamp': 1454353482,
'upload_date': '20160201',
},
'params': {
# m3u8 download
'skip_download': True,
}
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/794267642001/default_default/index.html?videoId=%s'

View File

@ -21,6 +21,7 @@ class TV3IE(InfoExtractor):
'Failed to download MPD manifest'
],
'params': {
# m3u8 download
'skip_download': True,
},
}

View File

@ -151,8 +151,8 @@ class UdemyIE(InfoExtractor):
login_form = self._form_hidden_inputs('login-form', login_popup)
login_form.update({
'email': username.encode('utf-8'),
'password': password.encode('utf-8'),
'email': username,
'password': password,
})
request = sanitized_Request(
@ -193,12 +193,12 @@ class UdemyIE(InfoExtractor):
asset = lecture['asset']
asset_type = asset.get('assetType') or asset.get('asset_type')
asset_type = asset.get('asset_type') or asset.get('assetType')
if asset_type != 'Video':
raise ExtractorError(
'Lecture %s is not a video' % lecture_id, expected=True)
stream_url = asset.get('streamUrl') or asset.get('stream_url')
stream_url = asset.get('stream_url') or asset.get('streamUrl')
if stream_url:
youtube_url = self._search_regex(
r'(https?://www\.youtube\.com/watch\?v=.*)', stream_url, 'youtube URL', default=None)
@ -206,7 +206,7 @@ class UdemyIE(InfoExtractor):
return self.url_result(youtube_url, 'Youtube')
video_id = asset['id']
thumbnail = asset.get('thumbnailUrl') or asset.get('thumbnail_url')
thumbnail = asset.get('thumbnail_url') or asset.get('thumbnailUrl')
duration = float_or_none(asset.get('data', {}).get('duration'))
formats = []
@ -325,7 +325,7 @@ class UdemyCourseIE(UdemyIE):
'https://www.udemy.com/api-2.0/courses/%s/cached-subscriber-curriculum-items' % course_id,
course_id, 'Downloading course curriculum', query={
'fields[chapter]': 'title,object_index',
'fields[lecture]': 'title',
'fields[lecture]': 'title,asset',
'page_size': '1000',
})
@ -334,6 +334,11 @@ class UdemyCourseIE(UdemyIE):
for entry in response['results']:
clazz = entry.get('_class')
if clazz == 'lecture':
asset = entry.get('asset')
if isinstance(asset, dict):
asset_type = asset.get('asset_type') or asset.get('assetType')
if asset_type != 'Video':
continue
lecture_id = entry.get('id')
if lecture_id:
entry = {

View File

@ -270,7 +270,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
))
|(?:
youtu\.be| # just youtu.be/xxxx
vid\.plus # or vid.plus/xxxx
vid\.plus| # or vid.plus/xxxx
zwearz\.com/watch| # or zwearz.com/watch/xxxx
)/
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
@ -758,6 +759,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'url': 'http://vid.plus/FlRa-iH7PGw',
'only_matching': True,
},
{
'url': 'http://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
'only_matching': True,
},
{
# Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
# Also tests cut-off URL expansion in video description (see

View File

@ -536,7 +536,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
sub_filenames.append(old_file)
new_file = subtitles_filename(filename, lang, new_ext)
if ext == 'dfxp' or ext == 'ttml':
if ext == 'dfxp' or ext == 'ttml' or ext == 'tt':
self._downloader.report_warning(
'You have requested to convert dfxp (TTML) subtitles into another format, '
'which results in style information loss')