Sirius/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/master'

Browse source
This commit is contained in:
Allan Zhou 2013-08-22 10:43:51 -07:00
commit b4e60dac23
7 changed files with 153 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
devscripts/youtube_genalgo.py
View file

@ -11,24 +11,27 @@ tests = [
# 90
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`",
"mrtyuioplkjhgfdsazxcvbne1234567890QWER[YUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={`]}|"),
# 89
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
"/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
# 88
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
"J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
# 87 - vflART1Nf 2013/07/24
# 87
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
"tyuioplkjhgfdsazxcv<nm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>"),
# 86 - vflm_D8eE 2013/07/31
"uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
# 86
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
">.1}|[{=+-_)(*&^%$#@!MNBVCXZASDFGHJK<POIUYTREW509876L432/mnbvcxzasdfghjklpoiuytre"),
# 85 - vflSAFCP9 2013/07/19
"yuioplkjhgfdsazecvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<"),
# 85
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
"ertyuiqplkjhgfdsazx$vbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#<%^&*()_-+={[};?/c"),
".>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ0q876543r1mnbvcx9asdfghjklpoiuyt2"),
# 84
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
"<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"),
# 83 - vflTWC9KW 2013/08/01
"<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ09876543q1mnbvcxzasdfghjklpoiuew2"),
# 83
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
"qwertyuioplkjhg>dsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/f"),
".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
# 82
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
"Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"),

1
youtube_dl/__init__.py
View file

@ -27,6 +27,7 @@ __authors__ = (
'Johny Mo Swag',
'Axel Noack',
'Albert Kim',
'Pierre Rudloff',
)
__license__ = 'Public Domain'

4
youtube_dl/extractor/__init__.py
View file

@ -36,6 +36,7 @@ from .ign import IGNIE, OneUPIE
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
from .jeuxvideo import JeuxVideoIE
from .jukebox import JukeboxIE
from .justintv import JustinTVIE
from .kankan import KankanIE
@ -50,6 +51,7 @@ from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .nba import NBAIE
from .ooyala import OoyalaIE
from .pbs import PBSIE
from .photobucket import PhotobucketIE
from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE
@ -58,6 +60,7 @@ from .ringtv import RingTVIE
from .roxwel import RoxwelIE
from .rtlnow import RTLnowIE
from .sina import SinaIE
from .slashdot import SlashdotIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
@ -72,6 +75,7 @@ from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
from .ustream import UstreamIE
from .unistra import UnistraIE
from .vbox7 import Vbox7IE
from .veoh import VeohIE
from .vevo import VevoIE

47
youtube_dl/extractor/jeuxvideo.py Normal file
View file

@ -0,0 +1,47 @@
# coding: utf-8
import json
import re
import xml.etree.ElementTree
from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
_TEST = {
u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
u'file': u'5182.mp4',
u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
u'info_dict': {
u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
xml_link = m_download.group(1)
id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
xml_config = self._download_webpage(xml_link, title,
'Downloading XML config')
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
info = re.search(r'<format\.json>(.*?)</format\.json>',
xml_config, re.MULTILINE|re.DOTALL).group(1)
info = json.loads(info)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file']
return {'id': id,
'title' : config.find('titre_video').text,
'ext' : 'mp4',
'url' : video_url,
'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
}

34
youtube_dl/extractor/pbs.py Normal file
View file

@ -0,0 +1,34 @@
import re
import json
from .common import InfoExtractor
class PBSIE(InfoExtractor):
_VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
_TEST = {
u'url': u'http://video.pbs.org/video/2365006249/',
u'file': u'2365006249.mp4',
u'md5': 'ce1888486f0908d555a8093cac9a7362',
u'info_dict': {
u'title': u'A More Perfect Union',
u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
u'duration': 3190,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
info_page = self._download_webpage(info_url, video_id)
info =json.loads(info_page)
return {'id': video_id,
'title': info['title'],
'url': info['alternate_encoding']['url'],
'ext': 'mp4',
'description': info['program'].get('description'),
'thumbnail': info.get('image_url'),
'duration': info.get('duration'),
}

23
youtube_dl/extractor/slashdot.py Normal file
View file

@ -0,0 +1,23 @@
import re
from .common import InfoExtractor
class SlashdotIE(InfoExtractor):
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
_TEST = {
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
u'info_dict': {
u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
return self.url_result(ooyala_url, 'Ooyala')

32
youtube_dl/extractor/unistra.py Normal file
View file

@ -0,0 +1,32 @@
import re
from .common import InfoExtractor
class UnistraIE(InfoExtractor):
_VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
_TEST = {
u'url': u'http://utv.unistra.fr/video.php?id_video=154',
u'file': u'154.mp4',
u'md5': u'736f605cfdc96724d55bb543ab3ced24',
u'info_dict': {
u'title': u'M!ss Yella',
u'description': u'md5:75e8439a3e2981cd5d4b6db232e8fdfc',
},
}
def _real_extract(self, url):
id = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, id)
file = re.search(r'file: "(.*?)",', webpage).group(1)
title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
return {'id': id,
'title': title,
'ext': 'mp4',
'url': video_url,
'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
}