1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 20:48:04 +01:00
youtube-dl/youtube_dl/extractor/aparat.py

61 lines
1.9 KiB
Python
Raw Normal View History

2014-11-23 20:41:03 +01:00
# coding: utf-8
2014-08-22 01:44:35 +02:00
from __future__ import unicode_literals
2013-12-20 17:05:28 +01:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
)
class AparatIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TEST = {
2014-08-22 01:44:35 +02:00
'url': 'http://www.aparat.com/v/wP8On',
'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'age_limit': 0,
2013-12-20 17:05:28 +01:00
},
2014-08-22 01:44:35 +02:00
# 'skip': 'Extremely unreliable',
2013-12-20 17:05:28 +01:00
}
def _real_extract(self, url):
2014-11-26 12:40:51 +01:00
video_id = self._match_id(url)
2013-12-20 17:05:28 +01:00
# 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
2014-08-22 01:44:35 +02:00
embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + '/vt/frame')
2013-12-20 17:05:28 +01:00
webpage = self._download_webpage(embed_url, video_id)
2015-02-08 12:30:29 +01:00
video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
2013-12-20 17:05:28 +01:00
for i, video_url in enumerate(video_urls):
req = HEADRequest(video_url)
res = self._request_webpage(
2014-11-26 12:40:51 +01:00
req, video_id, note='Testing video URL %d' % i, errnote=False)
2013-12-20 17:05:28 +01:00
if res:
break
else:
2014-11-26 12:40:51 +01:00
raise ExtractorError('No working video URLs found')
2013-12-20 17:05:28 +01:00
2014-11-26 12:40:51 +01:00
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
2013-12-20 17:05:28 +01:00
thumbnail = self._search_regex(
2015-02-08 12:30:29 +01:00
r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
2013-12-20 17:05:28 +01:00
return {
'id': video_id,
'title': title,
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage),
2013-12-20 17:05:28 +01:00
}