[aparat] Fix extraction

This commit is contained in:
Yen Chi Hsuan 2016-08-08 12:59:07 +08:00
parent 412abb8760
commit b1c6f21c74
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
2 changed files with 7 additions and 8 deletions

View file

@ -2,6 +2,7 @@ version <unreleased>
Extractors
* [kuwo:singer] Fix extraction
* [aparat] Fix extraction
version 2016.08.07

View file

@ -1,8 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
@ -15,7 +13,7 @@ class AparatIE(InfoExtractor):
_TEST = {
'url': 'http://www.aparat.com/v/wP8On',
'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
@ -31,13 +29,13 @@ def _real_extract(self, url):
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + '/vt/frame')
embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
webpage = self._download_webpage(embed_url, video_id)
video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
for i, video_url in enumerate(video_urls):
file_list = self._parse_json(self._search_regex(
r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
for i, item in enumerate(file_list[0]):
video_url = item['file']
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note='Testing video URL %d' % i, errnote=False)