yt-dlc/youtube_dl/extractor/aparat.py

59 lines
1.9 KiB
Python
Raw Normal View History

2014-11-23 19:41:03 +00:00
# coding: utf-8
2014-08-21 23:44:35 +00:00
from __future__ import unicode_literals
2013-12-20 16:05:28 +00:00
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 = {
2014-08-21 23:44:35 +00:00
'url': 'http://www.aparat.com/v/wP8On',
2016-08-08 04:59:07 +00:00
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
2014-08-21 23:44:35 +00:00
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
'age_limit': 0,
2013-12-20 16:05:28 +00:00
},
2014-08-21 23:44:35 +00:00
# 'skip': 'Extremely unreliable',
2013-12-20 16:05:28 +00:00
}
def _real_extract(self, url):
2014-11-26 11:40:51 +00:00
video_id = self._match_id(url)
2013-12-20 16:05:28 +00:00
# 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
2016-08-08 04:59:07 +00:00
embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
2013-12-20 16:05:28 +00:00
webpage = self._download_webpage(embed_url, video_id)
2016-08-08 04:59:07 +00:00
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']
2013-12-20 16:05:28 +00:00
req = HEADRequest(video_url)
res = self._request_webpage(
2014-11-26 11:40:51 +00:00
req, video_id, note='Testing video URL %d' % i, errnote=False)
2013-12-20 16:05:28 +00:00
if res:
break
else:
2014-11-26 11:40:51 +00:00
raise ExtractorError('No working video URLs found')
2013-12-20 16:05:28 +00:00
2014-11-26 11:40:51 +00:00
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
2013-12-20 16:05:28 +00:00
thumbnail = self._search_regex(
2015-02-08 11:30:29 +00:00
r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
2013-12-20 16:05:28 +00:00
return {
'id': video_id,
'title': title,
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage),
2013-12-20 16:05:28 +00:00
}