R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

fixes spankwire

Browse Source
This commit is contained in:
Vijayanand Nandam 2019-03-18 23:04:49 +05:30
parent 0a8e251b35
commit f8340f7d1d
1 changed files with 23 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
youtube_dl/extractor/spankwire.py
View File

@ -10,6 +10,7 @@ from ..compat import (
from ..utils import ( from ..utils import (
sanitized_Request, sanitized_Request,
str_to_int, str_to_int,
int_or_none,
unified_strdate, unified_strdate,
) )
from ..aes import aes_decrypt_text from ..aes import aes_decrypt_text
@ -54,62 +55,40 @@ class SpankwireIE(InfoExtractor):
req = sanitized_Request('http://www.' + mobj.group('url')) req = sanitized_Request('http://www.' + mobj.group('url'))
req.add_header('Cookie', 'age_verified=1') req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id) webpage = self._download_webpage(req, video_id)
json_req = sanitized_Request('https://www.spankwire.com/api/video/'+video_id+'.json')
video_data = self._download_json(json_req, video_id)
title = self._html_search_regex( title = video_data['title']
r'<h1>([^<]+)', webpage, 'title') description = video_data['description']
description = self._html_search_regex( thumbnail = video_data['poster']
r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex( uploader = self._search_regex(
r'by:\s*<a [^>]*>(.+?)</a>', r'<a[^>]+class="uploaded__by"[^>]*>(.+?)</a>',
webpage, 'uploader', fatal=False) webpage, 'uploader', flags=re.DOTALL, fatal=False)
uploader_id = self._html_search_regex( uploader_id = self._html_search_regex(
r'by:\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"', r'by\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"',
webpage, 'uploader id', fatal=False) webpage, 'uploader id', fatal=False)
upload_date = unified_strdate(self._html_search_regex( upload_date = unified_strdate(self._html_search_regex(
r'</a> on (.+?) at \d+:\d+', # r'</a> on (.+?) at \d+:\d+',
r'</span>(.+?) at \d+:\d+ (AM|PM) by',
webpage, 'upload date', fatal=False)) webpage, 'upload date', fatal=False))
view_count = str_to_int(self._html_search_regex( view_count = int_or_none(video_data['viewed'])
r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>', comment_count = int_or_none(video_data['comments'])
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
videos = re.findall(
r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
heights = [int(video[0]) for video in videos]
video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
if webpage.find(r'flashvars\.encrypted = "true"') != -1:
password = self._search_regex(
r'flashvars\.video_title = "([^"]+)',
webpage, 'password').replace('+', ' ')
video_urls = list(map(
lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
video_urls))
formats = [] formats = []
for height, video_url in zip(heights, video_urls): videos = video_data['videos']
path = compat_urllib_parse_urlparse(video_url).path for quality, video_url in videos.items():
m = re.search(r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', path) height = quality.split('_')[1].replace('p','')
if m: self.to_screen(height)
tbr = int(m.group('tbr'))
height = int(m.group('height'))
else:
tbr = None
formats.append({ formats.append({
'url': video_url, 'url': video_url,
'format_id': '%dp' % height, 'format_id': quality,
'height': height, 'height': int_or_none(height),
'tbr': tbr, 'tbr': None
}) })
self._sort_formats(formats)
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
return { return {