]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/aparat.py
63429780e8abf528165daf7e50a6317bce9a6c7d
[youtubedl] / youtube_dl / extractor / aparat.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import (
8 ExtractorError,
9 HEADRequest,
10 )
11
12
13 class AparatIE(InfoExtractor):
14 _VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
15
16 _TEST = {
17 'url': 'http://www.aparat.com/v/wP8On',
18 'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
19 'info_dict': {
20 'id': 'wP8On',
21 'ext': 'mp4',
22 'title': 'تیم گلکسی 11 - زومیت',
23 'age_limit': 0,
24 },
25 # 'skip': 'Extremely unreliable',
26 }
27
28 def _real_extract(self, url):
29 video_id = self._match_id(url)
30
31 # Note: There is an easier-to-parse configuration at
32 # http://www.aparat.com/video/video/config/videohash/%video_id
33 # but the URL in there does not work
34 embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
35 video_id + '/vt/frame')
36 webpage = self._download_webpage(embed_url, video_id)
37
38 video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
39 r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
40 for i, video_url in enumerate(video_urls):
41 req = HEADRequest(video_url)
42 res = self._request_webpage(
43 req, video_id, note='Testing video URL %d' % i, errnote=False)
44 if res:
45 break
46 else:
47 raise ExtractorError('No working video URLs found')
48
49 title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
50 thumbnail = self._search_regex(
51 r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
52
53 return {
54 'id': video_id,
55 'title': title,
56 'url': video_url,
57 'ext': 'mp4',
58 'thumbnail': thumbnail,
59 'age_limit': self._family_friendly_search(webpage),
60 }