]>
Commit | Line | Data |
---|---|---|
02e4ebbb | 1 | # coding: utf-8 |
71aa656d S |
2 | from __future__ import unicode_literals |
3 | ||
02e4ebbb | 4 | import re |
02e4ebbb PH |
5 | |
6 | from .common import InfoExtractor | |
6e6bc8da | 7 | from ..utils import ( |
84dcd1c4 | 8 | ExtractorError, |
6e6bc8da S |
9 | sanitized_Request, |
10 | urlencode_postdata, | |
11 | ) | |
02e4ebbb PH |
12 | |
13 | ||
14 | class StreamcloudIE(InfoExtractor): | |
71aa656d | 15 | IE_NAME = 'streamcloud.eu' |
3c6af203 | 16 | _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?' |
02e4ebbb | 17 | |
84dcd1c4 | 18 | _TESTS = [{ |
71aa656d S |
19 | 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', |
20 | 'md5': '6bea4c7fa5daaacc2a946b7146286686', | |
21 | 'info_dict': { | |
22 | 'id': 'skp9j99s4bpz', | |
23 | 'ext': 'mp4', | |
24 | 'title': 'youtube-dl test video \'/\\ ä ↭', | |
02e4ebbb | 25 | }, |
71aa656d | 26 | 'skip': 'Only available from the EU' |
84dcd1c4 S |
27 | }, { |
28 | 'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html', | |
29 | 'only_matching': True, | |
30 | }] | |
02e4ebbb PH |
31 | |
32 | def _real_extract(self, url): | |
3c6af203 NJ |
33 | video_id = self._match_id(url) |
34 | url = 'http://streamcloud.eu/%s' % video_id | |
02e4ebbb PH |
35 | |
36 | orig_webpage = self._download_webpage(url, video_id) | |
37 | ||
84dcd1c4 S |
38 | if '>File Not Found<' in orig_webpage: |
39 | raise ExtractorError( | |
40 | 'Video %s does not exist' % video_id, expected=True) | |
41 | ||
02e4ebbb PH |
42 | fields = re.findall(r'''(?x)<input\s+ |
43 | type="(?:hidden|submit)"\s+ | |
44 | name="([^"]+)"\s+ | |
45 | (?:id="[^"]+"\s+)? | |
46 | value="([^"]*)" | |
47 | ''', orig_webpage) | |
6e6bc8da | 48 | post = urlencode_postdata(fields) |
02e4ebbb | 49 | |
6f9b5493 | 50 | self._sleep(12, video_id) |
02e4ebbb PH |
51 | headers = { |
52 | b'Content-Type': b'application/x-www-form-urlencoded', | |
53 | } | |
5c2266df | 54 | req = sanitized_Request(url, post, headers) |
02e4ebbb PH |
55 | |
56 | webpage = self._download_webpage( | |
71aa656d | 57 | req, video_id, note='Downloading video page ...') |
02e4ebbb | 58 | title = self._html_search_regex( |
71aa656d | 59 | r'<h1[^>]*>([^<]+)<', webpage, 'title') |
02e4ebbb | 60 | video_url = self._search_regex( |
71aa656d | 61 | r'file:\s*"([^"]+)"', webpage, 'video URL') |
02e4ebbb | 62 | thumbnail = self._search_regex( |
71aa656d | 63 | r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False) |
02e4ebbb PH |
64 | |
65 | return { | |
66 | 'id': video_id, | |
67 | 'title': title, | |
68 | 'url': video_url, | |
02e4ebbb PH |
69 | 'thumbnail': thumbnail, |
70 | } |