mirrors/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[aparat] modernize

Browse Source
This commit is contained in:
Philipp Hagemeister 2014-08-22 01:44:35 +02:00
parent 91dff03217
commit 5fcf2dbed0
1 changed files with 11 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
youtube_dl/extractor/aparat.py
View File

@ -1,5 +1,7 @@
#coding: utf-8 #coding: utf-8
from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -13,13 +15,14 @@ class AparatIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TEST = { _TEST = {
u'url': u'http://www.aparat.com/v/wP8On', 'url': 'http://www.aparat.com/v/wP8On',
u'file': u'wP8On.mp4', 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
u'md5': u'6714e0af7e0d875c5a39c4dc4ab46ad1', 'info_dict': {
u'info_dict': { 'id': 'wP8On',
u"title": u"تیم گلکسی 11 - زومیت", 'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
}, },
#u'skip': u'Extremely unreliable', # 'skip': 'Extremely unreliable',
} }
def _real_extract(self, url): def _real_extract(self, url):
@ -29,8 +32,8 @@ class AparatIE(InfoExtractor):
# Note: There is an easier-to-parse configuration at # Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id # http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work # but the URL in there does not work
embed_url = (u'http://www.aparat.com/video/video/embed/videohash/' + embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + u'/vt/frame') video_id + '/vt/frame')
webpage = self._download_webpage(embed_url, video_id) webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)