[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / nosvideo.py

diff --git a/youtube_dl/extractor/nosvideo.py b/youtube_dl/extractor/nosvideo.py
index dbb03613bf397a84db911b14ec19767141a29a65..53c500c351690cf82872f3c724d6a5c60a6b5f93 100644 (file)
--- a/youtube_dl/extractor/nosvideo.py
+++ b/youtube_dl/extractor/nosvideo.py
@@ -5,59 +5,66 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
-    determine_ext,
+    ExtractorError,
+    sanitized_Request,
+    urlencode_postdata,
+    xpath_text,
     xpath_with_ns,
 )
 
 _x = lambda p: xpath_with_ns(p, {'xspf': 'http://xspf.org/ns/0/'})
-_find = lambda el, p: el.find(_x(p)).text.strip()
 
 
 class NosVideoIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?nosvideo\.com/' + \
-                 '(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
+                 r'(?:embed/|\?v=)(?P<id>[A-Za-z0-9]{12})/?'
     _PLAYLIST_URL = 'http://nosvideo.com/xml/{xml_id:s}.xml'
+    _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
     _TEST = {
-        'url': 'http://nosvideo.com/?v=drlp6s40kg54',
-        'md5': '4b4ac54c6ad5d70ab88f2c2c6ccec71c',
+        'url': 'http://nosvideo.com/?v=mu8fle7g7rpq',
+        'md5': '6124ed47130d8be3eacae635b071e6b6',
         'info_dict': {
-            'id': 'drlp6s40kg54',
+            'id': 'mu8fle7g7rpq',
             'ext': 'mp4',
             'title': 'big_buck_bunny_480p_surround-fix.avi.mp4',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
         }
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
 
         fields = {
             'id': video_id,
             'op': 'download1',
             'method_free': 'Continue to Video',
         }
-        post = compat_urllib_parse.urlencode(fields)
-        req = compat_urllib_request.Request(url, post)
+        req = sanitized_Request(url, urlencode_postdata(fields))
         req.add_header('Content-type', 'application/x-www-form-urlencoded')
         webpage = self._download_webpage(req, video_id,
                                          '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')
         playlist_url = self._PLAYLIST_URL.format(xml_id=xml_id)
         playlist = self._download_xml(playlist_url, video_id)
 
         track = playlist.find(_x('.//xspf:track'))
-        title = _find(track, './xspf:title')
-        url = _find(track, './xspf:file')
-        thumbnail = _find(track, './xspf:image')
-        ext = determine_ext(title)
+        if track is None:
+            raise ExtractorError(
+                'XML playlist is missing the \'track\' element',
+                expected=True)
+        title = xpath_text(track, _x('./xspf:title'), 'title')
+        url = xpath_text(track, _x('./xspf:file'), 'URL', fatal=True)
+        thumbnail = xpath_text(track, _x('./xspf:image'), 'thumbnail')
+        if title is not None:
+            title = title.strip()
 
         formats = [{
             'format_id': 'sd',
             'url': url,
-            'ext': ext,
         }]
 
         return {