X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/a4f82408d9a3d921d9c2af7e4d757f44737dc7ea..903490db3cf588364c9ff08098b1a9193438a7f3:/youtube_dl/extractor/streamcloud.py diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 172def2..6a6bb90 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -2,20 +2,19 @@ from __future__ import unicode_literals import re -import time from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, - compat_urllib_request, + ExtractorError, + urlencode_postdata, ) class StreamcloudIE(InfoExtractor): IE_NAME = 'streamcloud.eu' - _VALID_URL = r'https?://streamcloud\.eu/(?P[a-zA-Z0-9_-]+)/(?P[^#?]*)\.html' + _VALID_URL = r'https?://streamcloud\.eu/(?P[a-zA-Z0-9_-]+)(?:/(?P[^#?]*)\.html)?' - _TEST = { + _TESTS = [{ 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', 'md5': '6bea4c7fa5daaacc2a946b7146286686', 'info_dict': { @@ -24,35 +23,47 @@ class StreamcloudIE(InfoExtractor): 'title': 'youtube-dl test video \'/\\ ä ↭', }, 'skip': 'Only available from the EU' - } + }, { + 'url': 'http://streamcloud.eu/ua8cmfh1nbe6/NSHIP-148--KUC-NG--H264-.mp4.html', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + url = 'http://streamcloud.eu/%s' % video_id orig_webpage = self._download_webpage(url, video_id) + if '>File Not Found<' in orig_webpage: + raise ExtractorError( + 'Video %s does not exist' % video_id, expected=True) + fields = re.findall(r'''(?x)]*>([^<]+)<', webpage, 'title') - video_url = self._search_regex( - r'file:\s*"([^"]+)"', webpage, 'video URL') + url, video_id, data=urlencode_postdata(fields), headers={ + b'Content-Type': b'application/x-www-form-urlencoded', + }) + + try: + title = self._html_search_regex( + r']*>([^<]+)<', webpage, 'title') + video_url = self._search_regex( + r'file:\s*"([^"]+)"', webpage, 'video URL') + except ExtractorError: + message = self._html_search_regex( + r'(?s)]+class=(["\']).*?msgboxinfo.*?\1[^>]*>(?P.+?)', + webpage, 'message', default=None, group='message') + if message: + raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) + raise thumbnail = self._search_regex( r'image:\s*"([^"]+)"', webpage, 'thumbnail URL', fatal=False)