Pierre Rudloff
11 years ago
9 changed files with 159 additions and 8 deletions
Split View
Diff Options
-
7youtube_dl/extractor/__init__.py
-
4youtube_dl/extractor/c56.py
-
35youtube_dl/extractor/canalc2.py
-
2youtube_dl/extractor/canalplus.py
-
2youtube_dl/extractor/dailymotion.py
-
2youtube_dl/extractor/generic.py
-
37youtube_dl/extractor/hark.py
-
76youtube_dl/extractor/trilulilu.py
-
2youtube_dl/version.py
@ -0,0 +1,35 @@ |
|||
# coding: utf-8 |
|||
import re |
|||
|
|||
from .common import InfoExtractor |
|||
|
|||
|
|||
class Canalc2IE(InfoExtractor): |
|||
_IE_NAME = 'canalc2.tv' |
|||
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui' |
|||
|
|||
_TEST = { |
|||
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui', |
|||
u'file': u'12163.mp4', |
|||
u'md5': u'060158428b650f896c542dfbb3d6487f', |
|||
u'info_dict': { |
|||
u'title': u'Terrasses du Numérique' |
|||
} |
|||
} |
|||
|
|||
def _real_extract(self, url): |
|||
video_id = re.match(self._VALID_URL, url).group(1) |
|||
webpage = self._download_webpage(url, video_id) |
|||
file_name = self._search_regex( |
|||
r"so\.addVariable\('file','(.*?)'\);", |
|||
webpage, 'file name') |
|||
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name |
|||
|
|||
title = self._html_search_regex( |
|||
r'class="evenement8">(.*?)</a>', webpage, u'title') |
|||
|
|||
return {'id': video_id, |
|||
'ext': 'mp4', |
|||
'url': video_url, |
|||
'title': title, |
|||
} |
|||
@ -0,0 +1,37 @@ |
|||
# -*- coding: utf-8 -*- |
|||
|
|||
import re |
|||
import json |
|||
|
|||
from .common import InfoExtractor |
|||
from ..utils import determine_ext |
|||
|
|||
class HarkIE(InfoExtractor): |
|||
_VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' |
|||
_TEST = { |
|||
u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', |
|||
u'file': u'mmbzyhkgny.mp3', |
|||
u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', |
|||
u'info_dict': { |
|||
u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", |
|||
u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', |
|||
u'duration': 11, |
|||
} |
|||
} |
|||
|
|||
def _real_extract(self, url): |
|||
mobj = re.match(self._VALID_URL, url) |
|||
video_id = mobj.group(1) |
|||
json_url = "http://www.hark.com/clips/%s.json" %(video_id) |
|||
info_json = self._download_webpage(json_url, video_id) |
|||
info = json.loads(info_json) |
|||
final_url = info['url'] |
|||
|
|||
return {'id': video_id, |
|||
'url' : final_url, |
|||
'title': info['name'], |
|||
'ext': determine_ext(final_url), |
|||
'description': info['description'], |
|||
'thumbnail': info['image_original'], |
|||
'duration': info['duration'], |
|||
} |
|||
@ -0,0 +1,76 @@ |
|||
import json |
|||
import re |
|||
import xml.etree.ElementTree |
|||
|
|||
from .common import InfoExtractor |
|||
from ..utils import ( |
|||
ExtractorError, |
|||
) |
|||
|
|||
|
|||
class TriluliluIE(InfoExtractor): |
|||
_VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)' |
|||
_TEST = { |
|||
u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", |
|||
u'file': u"big-buck-bunny-1.mp4", |
|||
u'info_dict': { |
|||
u"title": u"Big Buck Bunny", |
|||
u"description": u":) pentru copilul din noi", |
|||
}, |
|||
# Server ignores Range headers (--test) |
|||
u"params": { |
|||
u"skip_download": True |
|||
} |
|||
} |
|||
|
|||
def _real_extract(self, url): |
|||
mobj = re.match(self._VALID_URL, url) |
|||
video_id = mobj.group('video_id') |
|||
|
|||
webpage = self._download_webpage(url, video_id) |
|||
|
|||
title = self._og_search_title(webpage) |
|||
thumbnail = self._og_search_thumbnail(webpage) |
|||
description = self._og_search_description(webpage) |
|||
|
|||
log_str = self._search_regex( |
|||
r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') |
|||
log = json.loads(log_str) |
|||
|
|||
format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' |
|||
u'video-formats2' % log) |
|||
format_str = self._download_webpage( |
|||
format_url, video_id, |
|||
note=u'Downloading formats', |
|||
errnote=u'Error while downloading formats') |
|||
|
|||
format_doc = xml.etree.ElementTree.fromstring(format_str) |
|||
|
|||
video_url_template = ( |
|||
u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' |
|||
u'&source=site&hash=%(hash)s&username=%(userid)s&' |
|||
u'key=ministhebest&format=%%s&sig=&exp=' % |
|||
log) |
|||
formats = [ |
|||
{ |
|||
'format': fnode.text, |
|||
'url': video_url_template % fnode.text, |
|||
} |
|||
|
|||
for fnode in format_doc.findall('./formats/format') |
|||
] |
|||
|
|||
info = { |
|||
'_type': 'video', |
|||
'id': video_id, |
|||
'formats': formats, |
|||
'title': title, |
|||
'description': description, |
|||
'thumbnail': thumbnail, |
|||
} |
|||
|
|||
# TODO: Remove when #980 has been merged |
|||
info['url'] = formats[-1]['url'] |
|||
info['ext'] = formats[-1]['format'].partition('-')[0] |
|||
|
|||
return info |
|||
@ -1,2 +1,2 @@ |
|||
|
|||
__version__ = '2013.08.23' |
|||
__version__ = '2013.08.27' |
|||
Write
Preview
Loading…
Cancel
Save