X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/f19349c26118065acbe21509383c63465df794fe..87046f03007c9b8a95c6297423e5660f795b186d:/youtube_dl/extractor/streamcloud.py diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 77841b9..6a6bb90 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -4,15 +4,17 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_parse -from ..utils import sanitized_Request +from ..utils import ( + ExtractorError, + urlencode_postdata, +) class StreamcloudIE(InfoExtractor): IE_NAME = 'streamcloud.eu' _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': { @@ -21,7 +23,10 @@ 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): video_id = self._match_id(url) @@ -29,26 +34,36 @@ class StreamcloudIE(InfoExtractor): 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)