Merge pull request #3716 from naglis/nosvideo

[nosvideo] Check for deleted video
This commit is contained in:
Sergey M. 2014-09-11 19:20:13 +07:00
commit de00ff6494

View File

@ -5,8 +5,9 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, ExtractorError,
compat_urllib_request, compat_urllib_request,
urlencode_postdata,
xpath_with_ns, xpath_with_ns,
) )
@ -18,11 +19,12 @@ class NosVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \ _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
'(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?' '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
_PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml' _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
_FILE_DELETED_REGEX = r'<b>File Not Found</b>'
_TEST = { _TEST = {
'url': 'http://nosvideo.com/?v=drlp6s40kg54', 'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c', 'md5': '6124ed47130d8be3eacae635b071e6b6',
'info_dict': { 'info_dict': {
'id': 'drlp6s40kg54', 'id': 'mu8fle7g7rpq',
'ext': 'mp4', 'ext': 'mp4',
'title': 'big_buck_bunny_480p_surround-fix.avi.mp4', 'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
@ -38,11 +40,14 @@ def _real_extract(self, url):
'op': 'download1', 'op': 'download1',
'method_free': 'Continue to Video', 'method_free': 'Continue to Video',
} }
post = compat_urllib_parse.urlencode(fields) req = compat_urllib_request.Request(url, urlencode_postdata(fields))
req = compat_urllib_request.Request(url, post)
req.add_header('Content-type', 'application/x-www-form-urlencoded') req.add_header('Content-type', 'application/x-www-form-urlencoded')
webpage = self._download_webpage(req, video_id, webpage = self._download_webpage(req, video_id,
'Downloading download page') 'Downloading download page')
if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
raise ExtractorError('Video %s does not exist' % video_id,
expected=True)
xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID') xml_id = self._search_regex(r'php\|([^\|]+)\|', webpage, 'XML ID')
playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id) playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
playlist = self._download_xml(playlist_url, video_id) playlist = self._download_xml(playlist_url, video_id)