1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-14 03:19:58 +01:00
This commit is contained in:
rzhxeo 2013-10-27 01:59:26 +02:00
parent 49a25557b0
commit 7b2212e954
2 changed files with 71 additions and 0 deletions
youtube_dl/extractor

View File

@ -109,6 +109,7 @@ from .slideshare import SlideshareIE
from .sohu import SohuIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE, SoundcloudUserIE
from .southparkstudios import SouthParkStudiosIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
from .statigram import StatigramIE

View File

@ -0,0 +1,70 @@
import os
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse_urlparse,
compat_urllib_request,
compat_urllib_parse,
unescapeHTML,
)
from ..aes import (
aes_decrypt_text
)
class SpankwireIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
_TEST = {
u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
u'file': u'103545.mp4',
u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
u'info_dict': {
u"uploader": u"oreusz",
u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
u"description": u"Crazy Bitch X rated music video.",
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = 'http://www.' + mobj.group('url')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
video_uploader = self._html_search_regex(r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
thumbnail = self._html_search_regex(r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
description = self._html_search_regex(r'>\s*Description:</div>\s*<[^>]*>([^<]+)', webpage, u'description', fatal=False)
if len(description) == 0:
description = None
video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
if webpage.find('flashvars\.encrypted = "true"') != -1:
password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
formats = []
for video_url in video_urls:
path = compat_urllib_parse_urlparse( video_url ).path
extension = os.path.splitext( path )[1][1:]
format = path.split('/')[4].split('_')[:2]
format = "-".join( format )
formats.append({
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
})
formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
return {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'thumbnail': thumbnail,
'description': description,
'formats': formats,
}