Compare commits

...

33 Commits

Author SHA1 Message Date
Philipp Hagemeister
473219a778 release 2014.09.12 2014-09-12 07:56:05 +02:00
Philipp Hagemeister
aa37e3d486 [utils] Default SSL to TLS. (Fixes #3727)
On 2.x, we now try TLS first, and fall back to the compat 23 (basically anything) afterwards.
On 3.4+, we now use the proper function so that we get all the latest security configurations.
We allow SSLv3 though for the time being, since a lot of older pages use that.
On 3.3, we default to SSLv23 (basically "anything, including TLS") because that has the widest compatibility.
2014-09-12 07:50:31 +02:00
Jaime Marquínez Ferrándiz
edb53e2dc3 [youtube] Don't make the url protocol optional
The generic extractor will add it.
2014-09-11 21:47:25 +02:00
Jaime Marquínez Ferrándiz
f401a4173b [youjizz] Don't make the url protocol optional (fixes #3722)
It would fail to download the webpag if it's missing.
And the generic extractor will add it.
2014-09-11 21:44:02 +02:00
Sergey M.
de00ff6494 Merge pull request #3716 from naglis/nosvideo
[nosvideo] Check for deleted video
2014-09-11 19:20:13 +07:00
Sergey M.
3616997929 Merge pull request #3718 from naglis/tv3play
[tvplay] Support similar services in different countries
2014-09-11 19:09:38 +07:00
Naglis Jonaitis
eef93b0912 [tvplay] Support similar services in different countries 2014-09-11 00:10:18 +03:00
Naglis Jonaitis
08d037309e [nosvideo] Update test 2014-09-10 18:19:59 +03:00
Naglis Jonaitis
6024b0f25e [nosvideo] Check for deleted videos 2014-09-10 18:10:21 +03:00
Philipp Hagemeister
561266641f release 2014.09.10.1 2014-09-10 16:39:23 +02:00
Sergey M․
6899f2fe9e [hostingbulk] Simplify 2014-09-10 19:13:22 +07:00
Sergey M.
136c8bd275 Merge pull request #3709 from naglis/hostingbulk
[hostingbulk] Add new extractor
2014-09-10 19:04:14 +07:00
Sergey M․
1bf5423e82 [generic/youtube] Recognize youtube nocookie embeds (Closes #3713) 2014-09-10 18:29:20 +07:00
Sergey M․
2c5c1f48e9 [izlesene] Simplify 2014-09-10 18:24:57 +07:00
Sergey M.
d8e487fbd9 Merge pull request #3710 from naglis/izlesene_fix
Izlesene fix
2014-09-10 18:20:57 +07:00
Philipp Hagemeister
bc7ff0a8dd release 2014.09.10 2014-09-10 12:26:39 +02:00
Naglis Jonaitis
8e9da53140 [izlesene] Remove API URL 2014-09-10 00:24:48 +03:00
Naglis Jonaitis
f1d15e6dbc [izlesene] Adapt to website changes and improve 2014-09-10 00:22:48 +03:00
Naglis Jonaitis
91ebb17ede [hostingbulk] Add new extractor 2014-09-09 22:17:33 +03:00
Sergey M․
c63b30901b [noco] Add authenticate support (Closes #3706) 2014-09-10 01:24:05 +07:00
Sergey M․
f009f19ece [rutv] Fix rutv player regex 2014-09-10 01:09:04 +07:00
Sergey M․
68477e8839 [khanacademy] Improve _VALID_URL (Closes #3695) 2014-09-09 22:09:32 +07:00
Sergey M․
0dc5365564 [moevideo] Make filesize exact 2014-09-09 21:48:10 +07:00
Sergey M.
9face18d08 Merge pull request #3690 from naglis/sharesix
[sharesix] Add new extractor
2014-09-09 21:14:59 +07:00
Sergey M․
ff0ba8ce0f [moevideo] Add videochart.net to _VALID_URL 2014-09-09 21:04:57 +07:00
Sergey M.
759c6293bd Merge pull request #3691 from naglis/moevideo
[moevideo] Add new extractor
2014-09-09 20:56:35 +07:00
Sergey M․
3fbeb95e14 [vgtv] Add view count to test cases 2014-09-08 21:33:03 +07:00
Sergey M․
6e25f51cdf Merge branch 'mrkolby-vgtv' 2014-09-08 21:26:59 +07:00
Sergey M․
321c1e44f9 [vgtv] Extract all formats, add support for wasLive and live streamTypes 2014-09-08 21:26:42 +07:00
Sergey M․
cc7fec5818 Merge branch 'vgtv' of https://github.com/mrkolby/youtube-dl into mrkolby-vgtv 2014-09-08 19:49:23 +07:00
Naglis Jonaitis
5fb9077e8c [moevideo] Add new extractor 2014-09-07 01:21:58 +03:00
Naglis Jonaitis
8e20f81c5b [sharesix] Add new extractor 2014-09-06 18:59:15 +03:00
Magnus Kolstad
78149a962b [vgtv] Add new extractor
Because of the #! in the URL structure for VGTV we need to add ' before and after given URL. Or else it will cry:

-bash: !/video/100495/lars-og-lars-sesong-6-episode-6-lakselus: event not found
2014-09-04 21:02:47 +02:00
16 changed files with 671 additions and 52 deletions

View File

@@ -140,6 +140,7 @@ from .hark import HarkIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .hornbunny import HornBunnyIE
from .hostingbulk import HostingBulkIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE
@@ -200,6 +201,7 @@ from .mitele import MiTeleIE
from .mixcloud import MixcloudIE
from .mlb import MLBIE
from .mpora import MporaIE
from .moevideo import MoeVideoIE
from .mofosex import MofosexIE
from .mojvideo import MojvideoIE
from .mooshare import MooshareIE
@@ -296,6 +298,7 @@ from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .servingsys import ServingSysIE
from .shared import SharedIE
from .sharesix import ShareSixIE
from .sina import SinaIE
from .slideshare import SlideshareIE
from .slutload import SlutloadIE
@@ -375,6 +378,7 @@ from .veehd import VeeHDIE
from .veoh import VeohIE
from .vesti import VestiIE
from .vevo import VevoIE
from .vgtv import VGTVIE
from .vh1 import VH1IE
from .viddler import ViddlerIE
from .videobam import VideoBamIE

View File

@@ -628,7 +628,7 @@ class GenericIE(InfoExtractor):
embedSWF\(?:\s*
)
(["\'])
(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/
(?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
(?:embed|v)/.+?)
\1''', webpage)
if matches:

View File

@@ -0,0 +1,84 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
compat_urllib_request,
int_or_none,
urlencode_postdata,
)
class HostingBulkIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?hostingbulk\.com/
(?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = {
'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
'info_dict': {
'id': 'n0ulw1hv20fm',
'ext': 'mp4',
'title': 'md5:5afeba33f48ec87219c269e054afd622',
'filesize': 6816081,
'thumbnail': 're:^http://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
# Custom request with cookie to set language to English, so our file
# deleted regex would work.
request = compat_urllib_request.Request(
url, headers={'Cookie': 'lang=english'})
webpage = self._download_webpage(request, video_id)
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
filesize = int_or_none(
self._search_regex(
r'<small>\((\d+)\sbytes?\)</small>',
webpage,
'filesize',
fatal=False
)
)
thumbnail = self._search_regex(
r'<img src="([^"]+)".+?class="pic"',
webpage, 'thumbnail', fatal=False)
fields = dict(re.findall(r'''(?x)<input\s+
type="hidden"\s+
name="([^"]+)"\s+
value="([^"]*)"
''', webpage))
request = compat_urllib_request.Request(url, urlencode_postdata(fields))
request.add_header('Content-type', 'application/x-www-form-urlencoded')
response = self._request_webpage(request, video_id,
'Submiting download request')
video_url = response.geturl()
formats = [{
'format_id': 'sd',
'filesize': filesize,
'url': video_url,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@@ -9,29 +9,50 @@ from ..utils import (
parse_iso8601,
determine_ext,
int_or_none,
float_or_none,
str_to_int,
)
class IzleseneIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|m)\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)'
_STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}'
_TEST = {
'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
'md5': '4384f9f0ea65086734b881085ee05ac2',
'info_dict': {
'id': '7599694',
'ext': 'mp4',
'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
'description': 'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor',
'thumbnail': 're:^http://.*\.jpg',
'uploader_id': 'pelikzzle',
'timestamp': 1404298698,
'upload_date': '20140702',
'duration': 95.395,
'age_limit': 0,
}
}
_VALID_URL = r'''(?x)
https?://(?:(?:www|m)\.)?izlesene\.com/
(?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
'''
_TESTS = [
{
'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
'md5': '4384f9f0ea65086734b881085ee05ac2',
'info_dict': {
'id': '7599694',
'ext': 'mp4',
'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
'description': 'md5:253753e2655dde93f59f74b572454f6d',
'thumbnail': 're:^http://.*\.jpg',
'uploader_id': 'pelikzzle',
'timestamp': 1404298698,
'upload_date': '20140702',
'duration': 95.395,
'age_limit': 0,
}
},
{
'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
'md5': '97f09b6872bffa284cb7fa4f6910cb72',
'info_dict': {
'id': '17997',
'ext': 'mp4',
'title': 'Tarkan Dortmund 2006 Konseri',
'description': 'Tarkan Dortmund 2006 Konseri',
'thumbnail': 're:^http://.*\.jpg',
'uploader_id': 'parlayankiz',
'timestamp': 1163318593,
'upload_date': '20061112',
'duration': 253.666,
'age_limit': 0,
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -45,18 +66,19 @@ class IzleseneIE(InfoExtractor):
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex(
r"adduserUsername\s*=\s*'([^']+)';", webpage, 'uploader', fatal=False, default='')
r"adduserUsername\s*=\s*'([^']+)';",
webpage, 'uploader', fatal=False, default='')
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date', fatal=False))
duration = int_or_none(self._html_search_regex(
r'"videoduration"\s*:\s*"([^"]+)"', webpage, 'duration', fatal=False))
if duration:
duration /= 1000.0
duration = float_or_none(self._html_search_regex(
r'"videoduration"\s*:\s*"([^"]+)"',
webpage, 'duration', fatal=False), scale=1000)
view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
comment_count = self._html_search_regex(
r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'uploader', fatal=False)
r'comment_count\s*=\s*\'([^\']+)\';',
webpage, 'comment_count', fatal=False)
family_friendly = self._html_search_meta(
'isFamilyFriendly', webpage, 'age limit', fatal=False)
@@ -66,20 +88,26 @@ class IzleseneIE(InfoExtractor):
ext = determine_ext(content_url, 'mp4')
# Might be empty for some videos.
qualities = self._html_search_regex(
r'"quality"\s*:\s*"([^"]+)"', webpage, 'qualities', fatal=False, default='')
streams = self._html_search_regex(
r'"qualitylevel"\s*:\s*"([^"]+)"',
webpage, 'streams', fatal=False, default='')
formats = []
for quality in qualities.split('|'):
json = self._download_json(
self._STREAM_URL.format(id=video_id, format=quality), video_id,
note='Getting video URL for "%s" quality' % quality,
errnote='Failed to get video URL for "%s" quality' % quality
)
if streams:
for stream in streams.split('|'):
quality, url = re.search(r'\[(\w+)\](.+)', stream).groups()
formats.append({
'format_id': '%sp' % quality if quality else 'sd',
'url': url,
'ext': ext,
})
else:
stream_url = self._search_regex(
r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL')
formats.append({
'url': json.get('streamurl'),
'format_id': 'sd',
'url': stream_url,
'ext': ext,
'format_id': '%sp' % quality if quality else 'sd',
})
return {

View File

@@ -9,7 +9,7 @@ from ..utils import (
class KhanAcademyIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
_VALID_URL = r'^https?://(?:(?:www|api)\.)?khanacademy\.org/(?P<key>[^/]+)/(?:[^/]+/){,2}(?P<id>[^?#/]+)(?:$|[?#])'
IE_NAME = 'KhanAcademy'
_TESTS = [{

View File

@@ -0,0 +1,112 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
compat_urllib_parse,
compat_urllib_request,
int_or_none,
)
class MoeVideoIE(InfoExtractor):
IE_DESC = 'LetitBit video services: moevideo.net, playreplay.net and videochart.net'
_VALID_URL = r'''(?x)
https?://(?P<host>(?:www\.)?
(?:(?:moevideo|playreplay|videochart)\.net))/
(?:video|framevideo)/(?P<id>[0-9]+\.[0-9A-Za-z]+)'''
_API_URL = 'http://api.letitbit.net/'
_API_KEY = 'tVL0gjqo5'
_TESTS = [
{
'url': 'http://moevideo.net/video/00297.0036103fe3d513ef27915216fd29',
'md5': '129f5ae1f6585d0e9bb4f38e774ffb3a',
'info_dict': {
'id': '00297.0036103fe3d513ef27915216fd29',
'ext': 'flv',
'title': 'Sink cut out machine',
'description': 'md5:f29ff97b663aefa760bf7ca63c8ca8a8',
'thumbnail': 're:^https?://.*\.jpg$',
'width': 540,
'height': 360,
'duration': 179,
'filesize': 17822500,
}
},
{
'url': 'http://playreplay.net/video/77107.7f325710a627383d40540d8e991a',
'md5': '74f0a014d5b661f0f0e2361300d1620e',
'info_dict': {
'id': '77107.7f325710a627383d40540d8e991a',
'ext': 'flv',
'title': 'Operacion Condor.',
'description': 'md5:7e68cb2fcda66833d5081c542491a9a3',
'thumbnail': 're:^https?://.*\.jpg$',
'width': 480,
'height': 296,
'duration': 6027,
'filesize': 588257923,
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(
'http://%s/video/%s' % (mobj.group('host'), video_id),
video_id, 'Downloading webpage')
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
r = [
self._API_KEY,
[
'preview/flv_link',
{
'uid': video_id,
},
],
]
r_json = json.dumps(r)
post = compat_urllib_parse.urlencode({'r': r_json})
req = compat_urllib_request.Request(self._API_URL, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
response = self._download_json(req, video_id)
if response['status'] != 'OK':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, response['data']),
expected=True
)
item = response['data'][0]
video_url = item['link']
duration = int_or_none(item['length'])
width = int_or_none(item['width'])
height = int_or_none(item['height'])
filesize = int_or_none(item['convert_size'])
formats = [{
'format_id': 'sd',
'http_headers': {'Range': 'bytes=0-'}, # Required to download
'url': video_url,
'width': width,
'height': height,
'filesize': filesize,
}]
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'description': description,
'duration': duration,
'formats': formats,
}

View File

@@ -5,7 +5,10 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
compat_urllib_parse,
ExtractorError,
clean_html,
unified_strdate,
compat_str,
)
@@ -13,6 +16,8 @@ from ..utils import (
class NocoIE(InfoExtractor):
_VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
_LOGIN_URL = 'http://noco.tv/do.php'
_NETRC_MACHINE = 'noco'
_TEST = {
'url': 'http://noco.tv/emission/11538/nolife/ami-ami-idol-hello-france/',
@@ -30,6 +35,28 @@ class NocoIE(InfoExtractor):
'skip': 'Requires noco account',
}
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'a': 'login',
'cookie': '1',
'username': username,
'password': password,
}
request = compat_urllib_request.Request(self._LOGIN_URL, compat_urllib_parse.urlencode(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
login = self._download_json(request, None, 'Logging in as %s' % username)
if 'erreur' in login:
raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')

View File

@@ -5,8 +5,9 @@ import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
compat_urllib_request,
urlencode_postdata,
xpath_with_ns,
)
@@ -18,11 +19,12 @@ class NosVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
'(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
_PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = {
'url': 'http://nosvideo.com/?v=drlp6s40kg54',
'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
'md5': '6124ed47130d8be3eacae635b071e6b6',
'info_dict': {
'id': 'drlp6s40kg54',
'id': 'mu8fle7g7rpq',
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
@@ -38,11 +40,14 @@ class NosVideoIE(InfoExtractor):
'op': 'download1',
'method_free': 'Continue to Video',
}
post = compat_urllib_parse.urlencode(fields)
req = compat_urllib_request.Request(url, post)
req = compat_urllib_request.Request(url, urlencode_postdata(fields))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id,
'Downloading download page')
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
playlist = self._download_xml(playlist_url, video_id)

View File

@@ -100,7 +100,7 @@ class RUTVIE(InfoExtractor):
return mobj.group('url')
mobj = re.search(
r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>http://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
r'<meta[^>]+?property=(["\'])og:video\1[^>]+?content=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/flash2v/container\.swf\?id=.+?\2)',
webpage)
if mobj:
return mobj.group('url')

View File

@@ -0,0 +1,91 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_request,
parse_duration,
)
class ShareSixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?sharesix\.com/(?:f/)?(?P<id>[0-9a-zA-Z]+)'
_TESTS = [
{
'url': 'http://sharesix.com/f/OXjQ7Y6',
'md5': '9e8e95d8823942815a7d7c773110cc93',
'info_dict': {
'id': 'OXjQ7Y6',
'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi',
'duration': 596,
'width': 854,
'height': 480,
},
},
{
'url': 'http://sharesix.com/lfrwoxp35zdd',
'md5': 'dd19f1435b7cec2d7912c64beeee8185',
'info_dict': {
'id': 'lfrwoxp35zdd',
'ext': 'flv',
'title': 'WhiteBoard___a_Mac_vs_PC_Parody_Cartoon.mp4.flv',
'duration': 65,
'width': 1280,
'height': 720,
},
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
fields = {
'method_free': 'Free'
}
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')
video_url = self._search_regex(
r"var\slnk1\s=\s'([^']+)'", webpage, 'video URL')
title = self._html_search_regex(
r'(?s)<dt>Filename:</dt>.+?<dd>(.+?)</dd>', webpage, 'title')
duration = parse_duration(
self._search_regex(
r'(?s)<dt>Length:</dt>.+?<dd>(.+?)</dd>',
webpage,
'duration',
fatal=False
)
)
m = re.search(
r'''(?xs)<dt>Width\sx\sHeight</dt>.+?
<dd>(?P<width>\d+)\sx\s(?P<height>\d+)</dd>''',
webpage
)
width = height = None
if m:
width, height = int(m.group('width')), int(m.group('height'))
formats = [{
'format_id': 'sd',
'url': video_url,
'width': width,
'height': height,
}]
return {
'id': video_id,
'title': title,
'duration': duration,
'formats': formats,
}

View File

@@ -6,13 +6,28 @@ import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
compat_str,
parse_iso8601,
qualities,
)
class TVPlayIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?tvplay\.lv/parraides/[^/]+/(?P<id>\d+)'
IE_DESC = 'TV3Play and related services'
_VALID_URL = r'''(?x)http://(?:www\.)?
(?:tvplay\.lv/parraides|
tv3play\.lt/programos|
tv3play\.ee/sisu|
tv3play\.se/program|
tv6play\.se/program|
tv8play\.se/program|
tv10play\.se/program|
tv3play\.no/programmer|
viasat4play\.no/programmer|
tv6play\.no/programmer|
tv3play\.dk/programmer|
)/[^/]+/(?P<id>\d+)
'''
_TESTS = [
{
'url': 'http://www.tvplay.lv/parraides/vinas-melo-labak/418113?autostart=true',
@@ -30,6 +45,134 @@ class TVPlayIE(InfoExtractor):
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.lt/programos/moterys-meluoja-geriau/409229?autostart=true',
'info_dict': {
'id': '409229',
'ext': 'flv',
'title': 'Moterys meluoja geriau',
'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
'duration': 1330,
'timestamp': 1403769181,
'upload_date': '20140626',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.ee/sisu/kodu-keset-linna/238551?autostart=true',
'info_dict': {
'id': '238551',
'ext': 'flv',
'title': 'Kodu keset linna 398537',
'description': 'md5:7df175e3c94db9e47c0d81ffa5d68701',
'duration': 1257,
'timestamp': 1292449761,
'upload_date': '20101215',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.se/program/husraddarna/395385?autostart=true',
'info_dict': {
'id': '395385',
'ext': 'flv',
'title': 'Husräddarna S02E07',
'description': 'md5:f210c6c89f42d4fc39faa551be813777',
'duration': 2574,
'timestamp': 1400596321,
'upload_date': '20140520',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv6play.se/program/den-sista-dokusapan/266636?autostart=true',
'info_dict': {
'id': '266636',
'ext': 'flv',
'title': 'Den sista dokusåpan S01E08',
'description': 'md5:295be39c872520221b933830f660b110',
'duration': 1492,
'timestamp': 1330522854,
'upload_date': '20120229',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv8play.se/program/antikjakten/282756?autostart=true',
'info_dict': {
'id': '282756',
'ext': 'flv',
'title': 'Antikjakten S01E10',
'description': 'md5:1b201169beabd97e20c5ad0ad67b13b8',
'duration': 2646,
'timestamp': 1348575868,
'upload_date': '20120925',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv3play.no/programmer/anna-anka-soker-assistent/230898?autostart=true',
'info_dict': {
'id': '230898',
'ext': 'flv',
'title': 'Anna Anka søker assistent - Ep. 8',
'description': 'md5:f80916bf5bbe1c5f760d127f8dd71474',
'duration': 2656,
'timestamp': 1277720005,
'upload_date': '20100628',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.viasat4play.no/programmer/budbringerne/21873?autostart=true',
'info_dict': {
'id': '21873',
'ext': 'flv',
'title': 'Budbringerne program 10',
'description': 'md5:4db78dc4ec8a85bb04fd322a3ee5092d',
'duration': 1297,
'timestamp': 1254205102,
'upload_date': '20090929',
},
'params': {
# rtmp download
'skip_download': True,
},
},
{
'url': 'http://www.tv6play.no/programmer/hotelinspektor-alex-polizzi/361883?autostart=true',
'info_dict': {
'id': '361883',
'ext': 'flv',
'title': 'Hotelinspektør Alex Polizzi - Ep. 10',
'description': 'md5:3ecf808db9ec96c862c8ecb3a7fdaf81',
'duration': 2594,
'timestamp': 1393236292,
'upload_date': '20140224',
},
'params': {
# rtmp download
'skip_download': True,
},
},
]
def _real_extract(self, url):
@@ -49,7 +192,7 @@ class TVPlayIE(InfoExtractor):
quality = qualities(['hls', 'medium', 'high'])
formats = []
for format_id, video_url in streams['streams'].items():
if not video_url:
if not video_url or not isinstance(video_url, compat_str):
continue
fmt = {
'format_id': format_id,

View File

@@ -0,0 +1,119 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import float_or_none
class VGTVIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?vgtv\.no/#!/(?:.*)/(?P<id>[0-9]+)'
_TESTS = [
{
# streamType: vod
'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
'md5': 'b8be7a234cebb840c0d512c78013e02f',
'info_dict': {
'id': '84196',
'ext': 'mp4',
'title': 'Hevnen er søt episode 10: Abu',
'description': 'md5:e25e4badb5f544b04341e14abdc72234',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 648.000,
'timestamp': 1404626400,
'upload_date': '20140706',
'view_count': int,
},
},
{
# streamType: wasLive
'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
'info_dict': {
'id': '100764',
'ext': 'mp4',
'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 9056.000,
'timestamp': 1410113864,
'upload_date': '20140907',
'view_count': int,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
# streamType: live
'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen',
'info_dict': {
'id': '100015',
'ext': 'mp4',
'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!',
'description': 'md5:9a60cc23fa349f761628924e56eeec2d',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 0,
'timestamp': 1407423348,
'upload_date': '20140807',
'view_count': int,
},
'params': {
# m3u8 download
'skip_download': True,
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
data = self._download_json(
'http://svp.vg.no/svp/api/v1/vgtv/assets/%s?appName=vgtv-website' % video_id,
video_id, 'Downloading media JSON')
streams = data['streamUrls']
formats = []
hls_url = streams.get('hls')
if hls_url:
formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4'))
hds_url = streams.get('hds')
if hds_url:
formats.extend(self._extract_f4m_formats(hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id))
mp4_url = streams.get('mp4')
if mp4_url:
_url = hls_url or hds_url
MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
for mp4_format in _url.split(','):
m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
if not m:
continue
width = int(m.group('width'))
height = int(m.group('height'))
vbr = int(m.group('vbr'))
formats.append({
'url': MP4_URL_TEMPLATE % mp4_format,
'format_id': 'mp4-%s' % vbr,
'width': width,
'height': height,
'vbr': vbr,
'preference': 1,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': data['title'],
'description': data['description'],
'thumbnail': data['images']['main'] + '?t[]=900x506q80',
'timestamp': data['published'],
'duration': float_or_none(data['duration'], 1000),
'view_count': data['displays'],
'formats': formats,
}

View File

@@ -9,7 +9,7 @@ from ..utils import (
class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$'
_TEST = {
'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
'file': '2189178.flv',

View File

@@ -199,7 +199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
IE_DESC = u'YouTube.com'
_VALID_URL = r"""(?x)^
(
(?:https?://|//)? # http(s):// or protocol-independent URL (optional)
(?:https?://|//) # http(s):// or protocol-independent URL
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
(?:www\.)?deturl\.com/www\.youtube\.com/|
(?:www\.)?pwnyoutube\.com/|
@@ -217,7 +217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
)
))
|youtu\.be/ # just youtu.be/xxxx
|https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
)? # all until now is optional -> you can pass the naked ID
([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID

View File

@@ -617,7 +617,7 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
self.sock = sock
self._tunnel()
try:
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv3)
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_TLSv1)
except ssl.SSLError:
self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file, ssl_version=ssl.PROTOCOL_SSLv23)
@@ -625,8 +625,14 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs):
def https_open(self, req):
return self.do_open(HTTPSConnectionV3, req)
return HTTPSHandlerV3(**kwargs)
else:
context = ssl.SSLContext(ssl.PROTOCOL_SSLv3)
elif hasattr(ssl, 'create_default_context'): # Python >= 3.4
context = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
context.options &= ~ssl.OP_NO_SSLv3 # Allow older, not-as-secure SSLv3
if opts_no_check_certificate:
context.verify_mode = ssl.CERT_NONE
return compat_urllib_request.HTTPSHandler(context=context, **kwargs)
else: # Python < 3.4
context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
context.verify_mode = (ssl.CERT_NONE
if opts_no_check_certificate
else ssl.CERT_REQUIRED)

View File

@@ -1,2 +1,2 @@
__version__ = '2014.09.06'
__version__ = '2014.09.12'