Allan Zhou
11 years ago
7 changed files with 153 additions and 9 deletions
Split View
Diff Options
-
21devscripts/youtube_genalgo.py
-
1youtube_dl/__init__.py
-
4youtube_dl/extractor/__init__.py
-
47youtube_dl/extractor/jeuxvideo.py
-
34youtube_dl/extractor/pbs.py
-
23youtube_dl/extractor/slashdot.py
-
32youtube_dl/extractor/unistra.py
@ -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, |
|||
} |
|||
@ -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'), |
|||
} |
|||
@ -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') |
|||
@ -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'), |
|||
} |
|||
Write
Preview
Loading…
Cancel
Save