[promptfile] Improve and modernize

This commit is contained in:
Sergey M․ 2016-09-26 23:39:54 +07:00
parent d3dbb46330
commit 72c3d02d29
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -7,7 +7,6 @@
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
sanitized_Request,
urlencode_postdata, urlencode_postdata,
) )
@ -33,20 +32,23 @@ def _real_extract(self, url):
raise ExtractorError('Video %s does not exist' % video_id, raise ExtractorError('Video %s does not exist' % video_id,
expected=True) expected=True)
chash_pattern = r'\$\("#chash"\)\.val\("(.+)"\+\$\("#chash"\)' chash = self._search_regex(
chash = self._html_search_regex(chash_pattern, webpage, "chash") r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash')
fields = self._hidden_inputs(webpage) fields = self._hidden_inputs(webpage)
k = list(fields)[0] keys = list(fields.keys())
fields[k] = chash + fields[k] chash_key = keys[0] if len(keys) == 1 else next(
key for key in keys if key.startswith('cha'))
fields[chash_key] = chash + fields[chash_key]
post = urlencode_postdata(fields)
req = sanitized_Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage( webpage = self._download_webpage(
req, video_id, 'Downloading video page') url, video_id, 'Downloading video page',
data=urlencode_postdata(fields),
headers={'Content-type': 'application/x-www-form-urlencoded'})
url_pattern = r'<a href="(http://www\.promptfile\.com/file/[^"]+)' video_url = self._search_regex(
url = self._html_search_regex(url_pattern, webpage, 'URL') (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File',
r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'),
webpage, 'video url', group='url')
title = self._html_search_regex( title = self._html_search_regex(
r'<span.+title="([^"]+)">', webpage, 'title') r'<span.+title="([^"]+)">', webpage, 'title')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
@ -55,7 +57,7 @@ def _real_extract(self, url):
formats = [{ formats = [{
'format_id': 'sd', 'format_id': 'sd',
'url': url, 'url': video_url,
'ext': determine_ext(title), 'ext': determine_ext(title),
}] }]
self._sort_formats(formats) self._sort_formats(formats)