Compare commits

...

47 Commits

Author SHA1 Message Date
7575d52a73 release 2014.06.24 2014-06-24 08:59:40 +02:00
9a2dc4f7ac [teachertube] Fix extraction 2014-06-23 03:07:10 +07:00
c5cd249e41 [generic] Extract mtvservices embedded videos 2014-06-22 21:39:36 +02:00
8940c1c058 [mtv] Add an extractor for the mtvservices embedded player (closes #2995) 2014-06-22 21:39:27 +02:00
27ec04b232 [BR] replace test 2014-06-22 17:33:27 +02:00
d2824416aa [firstpost] Fix title extraction and add description 2014-06-22 01:20:40 +07:00
18061bbab0 [Youtube] add DASH format 272 (fixes #3128) 2014-06-21 12:03:27 +02:00
4ecbbcbcea Merge branch 'eliasp-spiegel' 2014-06-21 16:32:01 +07:00
55c97a03e1 [spiegel] Add description and modernize 2014-06-21 16:31:18 +07:00
98aeac6ea9 Use the 'base_url' for building the resulting 'url' as well. 2014-06-21 01:10:10 +02:00
8bfb6723cb Extract the base_url for the XML download from the JS snippet's 'server' variable. 2014-06-21 01:00:48 +02:00
a20575e8ae Make debug message useful and also report, which URL failed to download. 2014-06-21 00:35:12 +02:00
7724572519 [noco] Switch to HTTPS (Closes #3116) 2014-06-20 18:40:47 +07:00
d763637f6a release 2014.06.19 2014-06-19 17:13:50 +02:00
c26e9ac4b2 [youtube] Recognize signature functions that contain '$' (fixes #3104) 2014-06-19 16:42:49 +02:00
896bf55352 [LifeNews] update thumbnail in test 2014-06-19 16:34:48 +02:00
a23ba9b53c [Steam] update description in test 2014-06-19 16:32:11 +02:00
38a9339baf [prosiebensat1] Update some regexes 2014-06-19 19:51:49 +07:00
def8b4039f [bilibili] Fix extraction 2014-06-18 18:53:25 +07:00
a14e1538fe [ustream:channel] replace test for an updated channel 2014-06-17 16:03:03 +02:00
5f28a1acad [GorillaVid] improve extractor 2014-06-17 15:18:46 +02:00
25e9953c6f Merge pull request #3059 from marcwebbie/gorillavid
* marcwebbie/gorillavid:
  Changed video url to a public video
  [GorillaVid] Added GorillaVid extractor
2014-06-17 15:14:18 +02:00
f9df094ca5 Merge pull request #3089 from pulpe/ard_fix
[ARDIE] fix formats extraction (fixes #3087)
2014-06-17 14:53:51 +02:00
b60a469023 Merge pull request #3090 from Kagee/patch-1
tv.nrk.no urls mostly contain capital characters
2014-06-17 02:21:10 +07:00
7012631257 Fix test
Didn't use .lower() as planned, so update test with new ID.
2014-06-16 19:37:59 +02:00
e6c9f80c48 tv.nrk.no urls mostly contain capital characters
Updated regexp and one of the test cases to reflect this.
tv.nrksuper.no mostly uses lowercase, so that is still there.
2014-06-16 19:29:23 +02:00
895ce482b1 [ARDIE] adjustments suggested by @jaimeMF 2014-06-16 18:15:41 +02:00
e5da4021eb [ARDIE] fix formats extraction (fixes #3087) 2014-06-16 16:17:49 +02:00
2371053565 [rai] Skip test 2014-06-16 18:50:15 +07:00
33bf9033e0 release 2014.06.16 2014-06-16 10:15:24 +02:00
35eacd0dae [brightcove] Set the filesize of the formats and use _sort_formats 2014-06-15 11:37:39 +02:00
96bef88f5f [brightcove] Modernize some tests 2014-06-15 11:24:05 +02:00
5524b242a7 [brightcove] Add support for renditions with 'remote' set to True (fixes #3081)
The url needs to be modified to get the flv video.
2014-06-15 11:20:40 +02:00
a013eba65f [brightcove] Improve the 'experienceJSON' regex (#3081)
One of the strings may contain ';', we would get an invalid json string.
2014-06-15 11:08:24 +02:00
36755d40b4 Merge pull request #3078 from pulpe/youtube_fix
[Youtube] Recognize playlists with LL
2014-06-15 02:49:16 +07:00
7d568f5ab8 [Youtube] Recognize playlists with LL 2014-06-14 13:23:28 +02:00
a7207cd580 [wrzuta] Add age limit 2014-06-14 17:00:59 +07:00
e8ef659cd9 Merge pull request #3075 from pulpe/wrzuta
[WrzutaIE] Add extractor for wrzuta.pl (fixes #3072)
2014-06-14 16:51:27 +07:00
b0adbe98fb [rai] Add support for Rai websites (Closes #2930) 2014-06-13 23:44:44 +07:00
0c361c41b8 [WrzutaIE] Add extractor for wrzuta.pl (fixes #3072) 2014-06-13 08:51:35 +02:00
c5469e046a [livestream] Modernize 2014-06-12 20:42:46 +07:00
4d2f143ce5 [ted] Update test md5 2014-06-12 20:33:53 +07:00
8f93030c85 [blinkx] Modernize 2014-06-11 18:38:13 +07:00
fdb9aebead [tube8] Update test and modernize 2014-06-11 18:20:14 +07:00
3141feb73b [ndtv] Fix title extraction and modernize 2014-06-10 19:37:38 +07:00
77abae55df Changed video url to a public video 2014-06-08 03:13:45 -03:00
617c0b2239 [GorillaVid] Added GorillaVid extractor 2014-06-07 23:09:45 -03:00
26 changed files with 546 additions and 119 deletions

View File

@ -114,10 +114,10 @@ class TestPlaylists(unittest.TestCase):
def test_ustream_channel(self):
dl = FakeYDL()
ie = UstreamChannelIE(dl)
result = ie.extract('http://www.ustream.tv/channel/young-americans-for-liberty')
result = ie.extract('http://www.ustream.tv/channel/channeljapan')
self.assertIsPlaylist(result)
self.assertEqual(result['id'], '5124905')
self.assertTrue(len(result['entries']) >= 6)
self.assertEqual(result['id'], '10874166')
self.assertTrue(len(result['entries']) >= 54)
def test_soundcloud_set(self):
dl = FakeYDL()

View File

@ -109,6 +109,7 @@ from .gdcvault import GDCVaultIE
from .generic import GenericIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE
from .hark import HarkIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
@ -169,6 +170,7 @@ from .moviezine import MoviezineIE
from .movshare import MovShareIE
from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
MTVIggyIE,
)
from .musicplayon import MusicPlayOnIE
@ -216,6 +218,7 @@ from .pornotube import PornotubeIE
from .prosiebensat1 import ProSiebenSat1IE
from .pyvideo import PyvideoIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
@ -344,6 +347,7 @@ from .weibo import WeiboIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .wrzuta import WrzutaIE
from .xbef import XBefIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE

View File

@ -56,7 +56,18 @@ class ARDIE(InfoExtractor):
raise ExtractorError('This video is only available after 20:00')
formats = []
for s in streams:
if type(s['_stream']) == list:
for index, url in enumerate(s['_stream'][::-1]):
quality = s['_quality'] + index
formats.append({
'quality': quality,
'url': url,
'format_id': '%s-%s' % (determine_ext(url), quality)
})
continue
format = {
'quality': s['_quality'],
'url': s['_stream'],

View File

@ -13,7 +13,7 @@ from ..utils import (
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'http://www\.bilibili\.tv/video/av(?P<id>[0-9]+)/'
_VALID_URL = r'http://www\.bilibili\.(?:tv|com)/video/av(?P<id>[0-9]+)/'
_TEST = {
'url': 'http://www.bilibili.tv/video/av1074402/',
@ -56,7 +56,7 @@ class BiliBiliIE(InfoExtractor):
'thumbnailUrl', video_code, 'thumbnail', fatal=False)
player_params = compat_parse_qs(self._html_search_regex(
r'<iframe .*?class="player" src="https://secure.bilibili.tv/secure,([^"]+)"',
r'<iframe .*?class="player" src="https://secure\.bilibili\.(?:tv|com)/secure,([^"]+)"',
webpage, 'player params'))
if 'cid' in player_params:

View File

@ -4,9 +4,7 @@ import json
import re
from .common import InfoExtractor
from ..utils import (
remove_start,
)
from ..utils import remove_start
class BlinkxIE(InfoExtractor):
@ -15,9 +13,10 @@ class BlinkxIE(InfoExtractor):
_TEST = {
'url': 'http://www.blinkx.com/ce/8aQUy7GVFYgFzpKhT0oqsilwOGFRVXk3R1ZGWWdGenBLaFQwb3FzaWx3OGFRVXk3R1ZGWWdGenB',
'file': '8aQUy7GV.mp4',
'md5': '2e9a07364af40163a908edbf10bb2492',
'info_dict': {
'id': '8aQUy7GV',
'ext': 'mp4',
'title': 'Police Car Rolls Away',
'uploader': 'stupidvideos.com',
'upload_date': '20131215',
@ -27,6 +26,7 @@ class BlinkxIE(InfoExtractor):
'thumbnails': [{
'width': 100,
'height': 76,
'resolution': '100x76',
'url': 'http://cdn.blinkx.com/stream/b/41/StupidVideos/20131215/1873969261/1873969261_tn_0.jpg',
}],
},
@ -37,7 +37,7 @@ class BlinkxIE(InfoExtractor):
video_id = m.group('id')
display_id = video_id[:8]
api_url = (u'https://apib4.blinkx.com/api.php?action=play_video&' +
api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' +
'video=%s' % video_id)
data_json = self._download_webpage(api_url, display_id)
data = json.loads(data_json)['api']['results'][0]
@ -55,13 +55,13 @@ class BlinkxIE(InfoExtractor):
duration = m['d']
elif m['type'] == 'youtube':
yt_id = m['link']
self.to_screen(u'Youtube video detected: %s' % yt_id)
self.to_screen('Youtube video detected: %s' % yt_id)
return self.url_result(yt_id, 'Youtube', video_id=yt_id)
elif m['type'] in ('flv', 'mp4'):
vcodec = remove_start(m['vcodec'], 'ff')
acodec = remove_start(m['acodec'], 'ff')
tbr = (int(m['vbr']) + int(m['abr'])) // 1000
format_id = u'%s-%sk-%s' % (vcodec, tbr, m['w'])
format_id = '%s-%sk-%s' % (vcodec, tbr, m['w'])
formats.append({
'format_id': format_id,
'url': m['link'],

View File

@ -17,15 +17,13 @@ class BRIE(InfoExtractor):
_TESTS = [
{
'url': 'http://www.br.de/mediathek/video/anselm-gruen-114.html',
'md5': 'c4f83cf0f023ba5875aba0bf46860df2',
'url': 'http://www.br.de/mediathek/video/sendungen/heimatsound/heimatsound-festival-2014-trailer-100.html',
'md5': '93556dd2bcb2948d9259f8670c516d59',
'info_dict': {
'id': '2c8d81c5-6fb7-4a74-88d4-e768e5856532',
'id': '25e279aa-1ffd-40fd-9955-5325bd48a53a',
'ext': 'mp4',
'title': 'Feiern und Verzichten',
'description': 'Anselm Grün: Feiern und Verzichten',
'uploader': 'BR/Birgit Baier',
'upload_date': '20140301',
'title': 'Am 1. und 2. August in Oberammergau',
'description': 'md5:dfd224e5aa6819bc1fcbb7826a932021',
}
},
{

View File

@ -15,6 +15,7 @@ from ..utils import (
compat_urllib_request,
compat_parse_qs,
determine_ext,
ExtractorError,
unsmuggle_url,
unescapeHTML,
@ -29,10 +30,11 @@ class BrightcoveIE(InfoExtractor):
{
# From http://www.8tv.cat/8aldia/videos/xavier-sala-i-martin-aquesta-tarda-a-8-al-dia/
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1654948606001&flashID=myExperience&%40videoPlayer=2371591881001',
'file': '2371591881001.mp4',
'md5': '5423e113865d26e40624dce2e4b45d95',
'note': 'Test Brightcove downloads and detection in GenericIE',
'info_dict': {
'id': '2371591881001',
'ext': 'mp4',
'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',
@ -41,8 +43,9 @@ class BrightcoveIE(InfoExtractor):
{
# From http://medianetwork.oracle.com/video/player/1785452137001
'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=1217746023001&flashID=myPlayer&%40videoPlayer=1785452137001',
'file': '1785452137001.flv',
'info_dict': {
'id': '1785452137001',
'ext': 'flv',
'title': 'JVMLS 2012: Arrays 2.0 - Opportunities and Challenges',
'description': 'John Rose speaks at the JVM Language Summit, August 1, 2012.',
'uploader': 'Oracle',
@ -70,7 +73,20 @@ class BrightcoveIE(InfoExtractor):
'description': 'md5:363109c02998fee92ec02211bd8000df',
'uploader': 'National Ballet of Canada',
},
}
},
{
# 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',
# The md5 checksum changes on each download
'info_dict': {
'id': '2996102916001',
'ext': 'flv',
'title': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
'uploader': 'Red Bull TV',
'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals',
},
},
]
@classmethod
@ -187,7 +203,7 @@ class BrightcoveIE(InfoExtractor):
webpage = self._download_webpage(req, video_id)
self.report_extraction(video_id)
info = self._search_regex(r'var experienceJSON = ({.*?});', webpage, 'json')
info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
info = json.loads(info)['data']
video_info = info['programmedContent']['videoPlayer']['mediaDTO']
video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
@ -219,12 +235,26 @@ class BrightcoveIE(InfoExtractor):
renditions = video_info.get('renditions')
if renditions:
renditions = sorted(renditions, key=lambda r: r['size'])
info['formats'] = [{
'url': rend['defaultURL'],
'height': rend.get('frameHeight'),
'width': rend.get('frameWidth'),
} for rend in renditions]
formats = []
for rend in renditions:
url = rend['defaultURL']
if rend['remote']:
# This type of renditions are served through akamaihd.net,
# but they don't use f4m manifests
url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
ext = 'flv'
else:
ext = determine_ext(url)
size = rend.get('size')
formats.append({
'url': url,
'ext': ext,
'height': rend.get('frameHeight'),
'width': rend.get('frameWidth'),
'filesize': size if size != 0 else None,
})
self._sort_formats(formats)
info['formats'] = formats
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],

View File

@ -15,6 +15,7 @@ class FirstpostIE(InfoExtractor):
'id': '1025403',
'ext': 'mp4',
'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
}
}
@ -22,13 +23,16 @@ class FirstpostIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id)
title = self._html_search_meta('twitter:title', page, 'title')
description = self._html_search_meta('twitter:description', page, 'title')
data = self._download_xml(
'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
'Downloading video XML')
item = data.find('./playlist/item')
thumbnail = item.find('./image').text
title = item.find('./title').text
formats = [
{
@ -42,6 +46,7 @@ class FirstpostIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@ -278,6 +278,17 @@ class GenericIE(InfoExtractor):
'skip_download': True,
}
},
# MTVSercices embed
{
'url': 'http://www.gametrailers.com/news-post/76093/north-america-europe-is-getting-that-mario-kart-8-mercedes-dlc-too',
'md5': '35727f82f58c76d996fc188f9755b0d5',
'info_dict': {
'id': '0306a69b-8adf-4fb5-aace-75f8e8cbfca9',
'ext': 'mp4',
'title': 'Review',
'description': 'Mario\'s life in the fast lane has never looked so good.',
},
},
]
def report_download_webpage(self, video_id):
@ -676,6 +687,14 @@ class GenericIE(InfoExtractor):
url = unescapeHTML(mobj.group('url'))
return self.url_result(url, ie='Vulture')
# Look for embedded mtvservices player
mobj = re.search(
r'<iframe src="(?P<url>https?://media\.mtvnservices\.com/embed/[^"]+)"',
webpage)
if mobj is not None:
url = unescapeHTML(mobj.group('url'))
return self.url_result(url, ie='MTVServicesEmbedded')
# Start with something easy: JW Player in SWFObject
found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)
if not found:

View File

@ -0,0 +1,76 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
compat_urllib_parse,
compat_urllib_request,
)
class GorillaVidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
_TESTS = [{
'url': 'http://gorillavid.in/06y9juieqpmi',
'md5': '5ae4a3580620380619678ee4875893ba',
'info_dict': {
'id': '06y9juieqpmi',
'ext': 'flv',
'title': 'Rebecca Black My Moment Official Music Video Reaction',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
'md5': 'c9e293ca74d46cad638e199c3f3fe604',
'info_dict': {
'id': 'z08zf8le23c6',
'ext': 'mp4',
'title': 'Say something nice',
'thumbnail': 're:http://.*\.jpg',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://gorillavid.in/%s' % video_id
webpage = self._download_webpage(url, video_id)
fields = dict(re.findall(r'''(?x)<input\s+
type="hidden"\s+
name="([^"]+)"\s+
(?:id="[^"]+"\s+)?
value="([^"]*)"
''', webpage))
if fields['op'] == 'download1':
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
formats = [{
'format_id': 'sd',
'url': url,
'ext': determine_ext(url),
'quality': 1,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@ -24,7 +24,7 @@ class LifeNewsIE(InfoExtractor):
'ext': 'mp4',
'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
'thumbnail': 're:http://.*\.jpg',
'upload_date': '20140130',
}
}

View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import re
import json
@ -6,31 +8,34 @@ from ..utils import (
compat_urllib_parse_urlparse,
compat_urlparse,
xpath_with_ns,
compat_str,
)
class LivestreamIE(InfoExtractor):
IE_NAME = u'livestream'
IE_NAME = 'livestream'
_VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
_TEST = {
u'url': u'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
u'file': u'4719370.mp4',
u'md5': u'0d2186e3187d185a04b3cdd02b828836',
u'info_dict': {
u'title': u'Live from Webster Hall NYC',
u'upload_date': u'20121012',
'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
'md5': '53274c76ba7754fb0e8d072716f2292b',
'info_dict': {
'id': '4719370',
'ext': 'mp4',
'title': 'Live from Webster Hall NYC',
'upload_date': '20121012',
}
}
def _extract_video_info(self, video_data):
video_url = video_data.get('progressive_url_hd') or video_data.get('progressive_url')
return {'id': video_data['id'],
'url': video_url,
'ext': 'mp4',
'title': video_data['caption'],
'thumbnail': video_data['thumbnail_url'],
'upload_date': video_data['updated_at'].replace('-','')[:8],
}
return {
'id': compat_str(video_data['id']),
'url': video_url,
'ext': 'mp4',
'title': video_data['caption'],
'thumbnail': video_data['thumbnail_url'],
'upload_date': video_data['updated_at'].replace('-', '')[:8],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -40,36 +45,36 @@ class LivestreamIE(InfoExtractor):
if video_id is None:
# This is an event page:
config_json = self._search_regex(r'window.config = ({.*?});',
webpage, u'window config')
config_json = self._search_regex(
r'window.config = ({.*?});', webpage, 'window config')
info = json.loads(config_json)['event']
videos = [self._extract_video_info(video_data['data'])
for video_data in info['feed']['data'] if video_data['type'] == u'video']
for video_data in info['feed']['data'] if video_data['type'] == 'video']
return self.playlist_result(videos, info['id'], info['full_name'])
else:
og_video = self._og_search_video_url(webpage, name=u'player url')
og_video = self._og_search_video_url(webpage, 'player url')
query_str = compat_urllib_parse_urlparse(og_video).query
query = compat_urlparse.parse_qs(query_str)
api_url = query['play_url'][0].replace('.smil', '')
info = json.loads(self._download_webpage(api_url, video_id,
u'Downloading video info'))
info = json.loads(self._download_webpage(
api_url, video_id, 'Downloading video info'))
return self._extract_video_info(info)
# The original version of Livestream uses a different system
class LivestreamOriginalIE(InfoExtractor):
IE_NAME = u'livestream:original'
IE_NAME = 'livestream:original'
_VALID_URL = r'https?://www\.livestream\.com/(?P<user>[^/]+)/video\?.*?clipId=(?P<id>.*?)(&|$)'
_TEST = {
u'url': u'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
u'info_dict': {
u'id': u'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
u'ext': u'flv',
u'title': u'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
'info_dict': {
'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
'ext': 'flv',
'title': 'Spark 1 (BitCoin) with Cameron Winklevoss & Tyler Winklevoss of Winklevoss Capital',
},
u'params': {
'params': {
# rtmp
u'skip_download': True,
'skip_download': True,
},
}
@ -84,7 +89,7 @@ class LivestreamOriginalIE(InfoExtractor):
ns = {'media': 'http://search.yahoo.com/mrss'}
thumbnail_url = item.find(xpath_with_ns('media:thumbnail', ns)).attrib['url']
# Remove the extension and number from the path (like 1.jpg)
path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, u'path')
path = self._search_regex(r'(user-files/.+)_.*?\.jpg$', thumbnail_url, 'path')
return {
'id': video_id,

View File

@ -22,6 +22,7 @@ def _media_xml_tag(tag):
class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
@staticmethod
def _id_from_uri(uri):
return uri.split(':')[-1]
@ -35,6 +36,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/'
return base + m.group('finalid')
def _get_feed_url(self, uri):
return self._FEED_URL
def _get_thumbnail_url(self, uri, itemdoc):
search_path = '%s/%s' % (_media_xml_tag('group'), _media_xml_tag('thumbnail'))
thumb_node = itemdoc.find(search_path)
@ -136,10 +140,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
def _get_videos_info(self, uri):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
idoc = self._download_xml(
self._FEED_URL + '?' + data, video_id,
feed_url + '?' + data, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
return [self._get_video_info(item) for item in idoc.findall('.//item')]
@ -160,6 +164,37 @@ class MTVServicesInfoExtractor(InfoExtractor):
return self._get_videos_info(mgid)
class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
IE_NAME = 'mtvservices:embedded'
_VALID_URL = r'https?://media\.mtvnservices\.com/embed/(?P<mgid>.+?)(\?|/|$)'
_TEST = {
# From http://www.thewrap.com/peter-dinklage-sums-up-game-of-thrones-in-45-seconds-video/
'url': 'http://media.mtvnservices.com/embed/mgid:uma:video:mtv.com:1043906/cp~vid%3D1043906%26uri%3Dmgid%3Auma%3Avideo%3Amtv.com%3A1043906',
'md5': 'cb349b21a7897164cede95bd7bf3fbb9',
'info_dict': {
'id': '1043906',
'ext': 'mp4',
'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
},
}
def _get_feed_url(self, uri):
video_id = self._id_from_uri(uri)
site_id = uri.replace(video_id, '')
config_url = 'http://media.mtvnservices.com/pmt/e1/players/{0}/config.xml'.format(site_id)
config_doc = self._download_xml(config_url, video_id)
feed_node = config_doc.find('.//feed')
feed_url = feed_node.text.strip().split('?')[0]
return feed_url
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
mgid = mobj.group('mgid')
return self._get_videos_info(mgid)
class MTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'''(?x)^https?://
(?:(?:www\.)?mtv\.com/videos/.+?/(?P<videoid>[0-9]+)/[^/]+$|

View File

@ -1,22 +1,28 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import month_by_name
from ..utils import (
month_by_name,
int_or_none,
)
class NDTVIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?ndtv\.com/video/player/[^/]*/[^/]*/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710",
u"file": u"300710.mp4",
u"md5": u"39f992dbe5fb531c395d8bbedb1e5e88",
u"info_dict": {
u"title": u"NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
u"description": u"In an exclusive interview to NDTV, Aam Aadmi Party's Arvind Kejriwal says it makes no difference to him that Rahul Gandhi said the Congress needs to learn from his party.",
u"upload_date": u"20131208",
u"duration": 1327,
u"thumbnail": u"http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg",
'url': 'http://www.ndtv.com/video/player/news/ndtv-exclusive-don-t-need-character-certificate-from-rahul-gandhi-says-arvind-kejriwal/300710',
'md5': '39f992dbe5fb531c395d8bbedb1e5e88',
'info_dict': {
'id': '300710',
'ext': 'mp4',
'title': "NDTV exclusive: Don't need character certificate from Rahul Gandhi, says Arvind Kejriwal",
'description': 'md5:ab2d4b4a6056c5cb4caa6d729deabf02',
'upload_date': '20131208',
'duration': 1327,
'thumbnail': 'http://i.ndtvimg.com/video/images/vod/medium/2013-12/big_300710_1386518307.jpg',
},
}
@ -27,13 +33,12 @@ class NDTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
filename = self._search_regex(
r"__filename='([^']+)'", webpage, u'video filename')
video_url = (u'http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
r"__filename='([^']+)'", webpage, 'video filename')
video_url = ('http://bitcast-b.bitgravity.com/ndtvod/23372/ndtv/%s' %
filename)
duration_str = filename = self._search_regex(
r"__duration='([^']+)'", webpage, u'duration', fatal=False)
duration = None if duration_str is None else int(duration_str)
duration = int_or_none(self._search_regex(
r"__duration='([^']+)'", webpage, 'duration', fatal=False))
date_m = re.search(r'''(?x)
<p\s+class="vod_dateline">\s*
@ -41,7 +46,7 @@ class NDTVIE(InfoExtractor):
(?P<monthname>[A-Za-z]+)\s+(?P<day>[0-9]+),\s*(?P<year>[0-9]+)
''', webpage)
upload_date = None
assert date_m
if date_m is not None:
month = month_by_name(date_m.group('monthname'))
if month is not None:
@ -49,14 +54,19 @@ class NDTVIE(InfoExtractor):
date_m.group('year'), month, int(date_m.group('day')))
description = self._og_search_description(webpage)
READ_MORE = u' (Read more)'
READ_MORE = ' (Read more)'
if description.endswith(READ_MORE):
description = description[:-len(READ_MORE)]
title = self._og_search_title(webpage)
TITLE_SUFFIX = ' - NDTV'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
return {
'id': video_id,
'url': video_url,
'title': self._og_search_title(webpage),
'title': title,
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,

View File

@ -35,7 +35,7 @@ class NocoIE(InfoExtractor):
video_id = mobj.group('id')
medias = self._download_json(
'http://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON')
formats = []
@ -43,7 +43,7 @@ class NocoIE(InfoExtractor):
format_id = fmt['quality_key']
file = self._download_json(
'http://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id),
video_id, 'Downloading %s video JSON' % format_id)
file_url = file['file']
@ -71,7 +71,7 @@ class NocoIE(InfoExtractor):
self._sort_formats(formats)
show = self._download_json(
'http://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0]
upload_date = unified_strdate(show['indexed'])
uploader = show['partner_name']

View File

@ -72,14 +72,14 @@ class NRKIE(InfoExtractor):
class NRKTVIE(InfoExtractor):
_VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-z]{4}\d{8})'
_VALID_URL = r'http://tv\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})'
_TESTS = [
{
'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/muhh48000314/23-05-2014',
'url': 'http://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': '7b96112fbae1faf09a6f9ae1aff6cb84',
'info_dict': {
'id': 'muhh48000314',
'id': 'MUHH48000314',
'ext': 'flv',
'title': '20 spørsmål',
'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
@ -141,4 +141,4 @@ class NRKTVIE(InfoExtractor):
'upload_date': upload_date,
'duration': duration,
'formats': formats,
}
}

View File

@ -158,19 +158,19 @@ class ProSiebenSat1IE(InfoExtractor):
_CLIPID_REGEXES = [
r'"clip_id"\s*:\s+"(\d+)"',
r'clipid: "(\d+)"',
r'clipId=(\d+)',
r'clip[iI]d=(\d+)',
]
_TITLE_REGEXES = [
r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
r'<header class="clearfix">\s*<h3>(.+?)</h3>',
r'<!-- start video -->\s*<h1>(.+?)</h1>',
r'<div class="ep-femvideos-pi4-video-txt">\s*<h2>(.+?)</h2>',
r'<h1 class="att-name">\s*(.+?)</h1>',
]
_DESCRIPTION_REGEXES = [
r'<p itemprop="description">\s*(.+?)</p>',
r'<div class="videoDecription">\s*<p><strong>Beschreibung</strong>: (.+?)</p>',
r'<div class="g-plusone" data-size="medium"></div>\s*</div>\s*</header>\s*(.+?)\s*<footer>',
r'<p>(.+?)</p>\s*<div class="ep-femvideos-pi4-video-footer">',
r'<p class="att-description">\s*(.+?)\s*</p>',
]
_UPLOAD_DATE_REGEXES = [
r'<meta property="og:published_time" content="(.+?)">',

121
youtube_dl/extractor/rai.py Normal file
View File

@ -0,0 +1,121 @@
from __future__ import unicode_literals
import re
from .subtitles import SubtitlesInfoExtractor
from ..utils import (
parse_duration,
unified_strdate,
compat_urllib_parse,
)
class RaiIE(SubtitlesInfoExtractor):
_VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
_TESTS = [
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': 'c064c0b2d09c278fb293116ef5d0a32d',
'info_dict': {
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4',
'title': 'Report del 07/04/2014',
'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
'upload_date': '20140407',
'duration': 6160,
}
},
{
'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
'md5': '8bb9c151924ce241b74dd52ef29ceafa',
'info_dict': {
'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
'ext': 'mp4',
'title': 'TG PRIMO TEMPO',
'description': '',
'upload_date': '20140612',
'duration': 1758,
}
},
{
'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
'md5': '35cf7c229f22eeef43e48b5cf923bef0',
'info_dict': {
'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
'ext': 'mp4',
'title': 'State of the Net, Antonella La Carpia: regole virali',
'description': 'md5:b0ba04a324126903e3da7763272ae63c',
'upload_date': '20140613',
},
'skip': 'Error 404',
},
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
'md5': '35694f062977fe6619943f08ed935730',
'info_dict': {
'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
'ext': 'mp4',
'title': 'Alluvione in Sardegna e dissesto idrogeologico',
'description': 'Edizione delle ore 20:30 ',
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
title = media.get('name')
description = media.get('desc')
thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
duration = parse_duration(media.get('length'))
uploader = media.get('author')
upload_date = unified_strdate(media.get('date'))
formats = []
for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
media_url = media.get(format_id)
if not media_url:
continue
formats.append({
'url': media_url,
'format_id': format_id,
'ext': 'mp4',
})
if self._downloader.params.get('listsubtitles', False):
page = self._download_webpage(url, video_id)
self._list_available_subtitles(video_id, page)
return
subtitles = {}
if self._have_to_download_any_subtitles:
page = self._download_webpage(url, video_id)
subtitles = self.extract_subtitles(video_id, page)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}
def _get_available_subtitles(self, video_id, webpage):
subtitles = {}
m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
if m:
captions = m.group('captions')
STL_EXT = '.stl'
SRT_EXT = '.srt'
if captions.endswith(STL_EXT):
captions = captions[:-len(STL_EXT)] + SRT_EXT
subtitles['it'] = 'http://www.rai.tv%s' % compat_urllib_parse.quote(captions)
return subtitles

View File

@ -1,3 +1,4 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
@ -9,18 +10,33 @@ class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
_TESTS = [{
'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
'file': '1259285.mp4',
'md5': '2c2754212136f35fb4b19767d242f66e',
'info_dict': {
'id': '1259285',
'ext': 'mp4',
'title': 'Vulkanausbruch in Ecuador: Der "Feuerschlund" ist wieder aktiv',
'description': 'md5:8029d8310232196eb235d27575a8b9f4',
'duration': 49,
},
},
{
}, {
'url': 'http://www.spiegel.de/video/schach-wm-videoanalyse-des-fuenften-spiels-video-1309159.html',
'file': '1309159.mp4',
'md5': 'f2cdf638d7aa47654e251e1aee360af1',
'info_dict': {
'id': '1309159',
'ext': 'mp4',
'title': 'Schach-WM in der Videoanalyse: Carlsen nutzt die Fehlgriffe des Titelverteidigers',
'description': 'md5:c2322b65e58f385a820c10fa03b2d088',
'duration': 983,
},
}, {
'url': 'http://www.spiegel.de/video/johann-westhauser-videobotschaft-des-hoehlenforschers-video-1502367.html',
'md5': '54f58ba0e752e3c07bc2a26222dd0acf',
'info_dict': {
'id': '1502367',
'ext': 'mp4',
'title': 'Videobotschaft: Höhlenforscher Westhauser dankt seinen Rettern',
'description': 'md5:c6f1ec11413ebd1088b6813943e5fc91',
'duration': 42,
},
}]
@ -30,18 +46,20 @@ class SpiegelIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(
title = self._html_search_regex(
r'<div class="module-title">(.*?)</div>', webpage, 'title')
description = self._html_search_meta('description', webpage, 'description')
xml_url = 'http://video2.spiegel.de/flash/' + video_id + '.xml'
idoc = self._download_xml(
xml_url, video_id,
note='Downloading XML', errnote='Failed to download XML')
base_url = self._search_regex(
r'var\s+server\s*=\s*"([^"]+)\"', webpage, 'server URL')
xml_url = base_url + video_id + '.xml'
idoc = self._download_xml(xml_url, video_id)
formats = [
{
'format_id': n.tag.rpartition('type')[2],
'url': 'http://video2.spiegel.de/flash/' + n.find('./filename').text,
'url': base_url + n.find('./filename').text,
'width': int(n.find('./width').text),
'height': int(n.find('./height').text),
'abr': int(n.find('./audiobitrate').text),
@ -59,7 +77,8 @@ class SpiegelIE(InfoExtractor):
return {
'id': video_id,
'title': video_title,
'title': title,
'description': description,
'duration': duration,
'formats': formats,
}

View File

@ -53,7 +53,7 @@ class SteamIE(InfoExtractor):
'ext': 'mp4',
'upload_date': '20140329',
'title': 'FRONTIERS - Final Greenlight Trailer',
'description': "The final trailer for the Steam Greenlight launch. Hooray, progress! Here's the official Greenlight page: http://steamcommunity.com/sharedfiles/filedetails/?id=242472205",
'description': 'md5:6df4fe8dd494ae811869672b0767e025',
'uploader': 'AAD Productions',
'uploader_id': 'AtomicAgeDogGames',
}

View File

@ -22,8 +22,8 @@ class TeacherTubeIE(InfoExtractor):
'info_dict': {
'id': '339997',
'ext': 'mp4',
'title': 'Measures of dispersion from a frequency table_x264',
'description': 'md5:a3e9853487185e9fcd7181a07164650b',
'title': 'Measures of dispersion from a frequency table',
'description': 'Measures of dispersion from a frequency table',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@ -33,7 +33,7 @@ class TeacherTubeIE(InfoExtractor):
'id': '340064',
'ext': 'mp4',
'title': 'How to Make Paper Dolls _ Paper Art Projects',
'description': 'md5:2ca52b20cd727773d1dc418b3d6bd07b',
'description': 'Learn how to make paper dolls in this simple',
'thumbnail': 're:http://.*\.jpg',
},
}, {
@ -43,7 +43,7 @@ class TeacherTubeIE(InfoExtractor):
'id': '8805',
'ext': 'mp3',
'title': 'PER ASPERA AD ASTRA',
'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNIČKE ŠKOLE PER ASPERA AD ASTRA',
'description': 'RADIJSKA EMISIJA ZRAKOPLOVNE TEHNI?KE ?KOLE P',
},
}]
@ -53,9 +53,19 @@ class TeacherTubeIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('title', webpage, 'title')
TITLE_SUFFIX = ' - TeacherTube'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)].strip()
description = self._html_search_meta('description', webpage, 'description')
if description:
description = description.strip()
quality = qualities(['mp3', 'flv', 'mp4'])
_, media_urls = zip(*re.findall(r'([\'"])file\1\s*:\s*"([^"]+)"', webpage))
media_urls = re.findall(r'data-contenturl="([^"]+)"', webpage)
media_urls.extend(re.findall(r'var\s+filePath\s*=\s*"([^"]+)"', webpage))
formats = [
{
@ -68,10 +78,10 @@ class TeacherTubeIE(InfoExtractor):
return {
'id': video_id,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'title': title,
'thumbnail': self._html_search_regex(r'var\s+thumbUrl\s*=\s*"([^"]+)"', webpage, 'thumbnail'),
'formats': formats,
'description': self._og_search_description(webpage),
'description': description,
}
@ -85,8 +95,9 @@ class TeacherTubeClassroomIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user')
rss = self._download_xml('http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
user_id, 'Downloading classroom RSS')
rss = self._download_xml(
'http://www.teachertube.com/rssclassroom.php?mode=user&username=%s' % user_id,
user_id, 'Downloading classroom RSS')
entries = []
for url in rss.findall('.//{http://search.yahoo.com/mrss/}player'):

View File

@ -27,7 +27,7 @@ class TEDIE(SubtitlesInfoExtractor):
'''
_TESTS = [{
'url': 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
'md5': '4ea1dada91e4174b53dac2bb8ace429d',
'md5': 'fc94ac279feebbce69f21c0c6ee82810',
'info_dict': {
'id': '102',
'ext': 'mp4',

View File

@ -17,9 +17,10 @@ class Tube8IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P<id>\d+)'
_TEST = {
'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
'file': '229795.mp4',
'md5': 'e9e0b0c86734e5e3766e653509475db0',
'md5': '44bf12b98313827dd52d35b8706a4ea0',
'info_dict': {
'id': '229795',
'ext': 'mp4',
'description': 'hot teen Kasia grinding',
'uploader': 'unknown',
'title': 'Kasia music video',

View File

@ -0,0 +1,81 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
)
class WrzutaIE(InfoExtractor):
IE_NAME = 'wrzuta.pl'
_VALID_URL = r'https?://(?P<uploader>[0-9a-zA-Z]+)\.wrzuta\.pl/(?P<typ>film|audio)/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://laboratoriumdextera.wrzuta.pl/film/aq4hIZWrkBu/nike_football_the_last_game',
'md5': '9e67e05bed7c03b82488d87233a9efe7',
'info_dict': {
'id': 'aq4hIZWrkBu',
'ext': 'mp4',
'title': 'Nike Football: The Last Game',
'duration': 307,
'uploader_id': 'laboratoriumdextera',
'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd',
},
}, {
'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad',
'md5': '1e546a18e1c22ac6e9adce17b8961ff5',
'info_dict': {
'id': '9oXJqdcndqv',
'ext': 'ogg',
'title': 'David Guetta & Showtek ft. Vassy - Bad',
'duration': 270,
'uploader_id': 'w729',
'description': 'md5:4628f01c666bbaaecefa83476cfa794a',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
typ = mobj.group('typ')
uploader = mobj.group('uploader')
webpage = self._download_webpage(url, video_id)
quality = qualities(['SD', 'MQ', 'HQ', 'HD'])
audio_table = {'flv': 'mp3', 'webm': 'ogg'}
embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id)
formats = []
for media in embedpage['url']:
if typ == 'audio':
ext = audio_table[media['type'].split('@')[0]]
else:
ext = media['type'].split('@')[0]
formats.append({
'format_id': '%s_%s' % (ext, media['quality'].lower()),
'url': media['url'],
'ext': ext,
'quality': quality(media['quality']),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
'duration': int_or_none(embedpage['duration']),
'uploader_id': uploader,
'description': self._og_search_description(webpage),
'age_limit': embedpage.get('minimalAge', 0),
}

View File

@ -224,6 +224,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
'272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40},
# Dash webm audio
'171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 48, 'preference': -50},
@ -440,7 +441,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
def _parse_sig_js(self, jscode):
funcname = self._search_regex(
r'signature=([a-zA-Z]+)', jscode,
r'signature=([$a-zA-Z]+)', jscode,
u'Initial JS player signature function name')
jsi = JSInterpreter(jscode)
@ -1386,13 +1387,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
| p/
)
(
(?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
(?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}
# Top tracks, they can also include dots
|(?:MC)[\w\.]*
)
.*
|
((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
((?:PL|LL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_MORE_PAGES_INDICATOR = r'data-link-type="next"'

View File

@ -1,2 +1,2 @@
__version__ = '2014.06.09'
__version__ = '2014.06.24'