Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py
index 837c915595777c7688665d00344a7a1eaa75dc1c..d68c1ad7923ac56c6bef68343a20df24e4aa5ffb 100644 (file)
--- a/youtube_dl/extractor/novamov.py
+++ b/youtube_dl/extractor/novamov.py
@@ -17,15 +17,16 @@ class NovaMovIE(InfoExtractor):
     IE_NAME = 'novamov'
     IE_DESC = 'NovaMov'
 
-    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
+    _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video|mobile/#/videos)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<id>[a-z\d]{13})'
     _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
 
     _HOST = 'www.novamov.com'
 
     _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>'
-    _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";'
+    _FILEKEY_REGEX = r'flashvars\.filekey=(?P<filekey>"?[^"]+"?);'
     _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>'
     _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>'
+    _URL_TEMPLATE = 'http://%s/video/%s'
 
     _TEST = {
         'url': 'http://www.novamov.com/video/4rurhn9x446jj',
@@ -39,20 +40,28 @@ class NovaMovIE(InfoExtractor):
         'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)'
     }
 
+    def _check_existence(self, webpage, video_id):
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        url = 'http://%s/video/%s' % (self._HOST, video_id)
+        url = self._URL_TEMPLATE % (self._HOST, video_id)
 
         webpage = self._download_webpage(
             url, video_id, 'Downloading video page')
 
-        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
-            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+        self._check_existence(webpage, video_id)
 
         def extract_filekey(default=NO_DEFAULT):
-            return self._search_regex(
+            filekey = self._search_regex(
                 self._FILEKEY_REGEX, webpage, 'filekey', default=default)
+            if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'):
+                return self._search_regex(
+                    r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default)
+            else:
+                return filekey
 
         filekey = extract_filekey(default=None)
 
@@ -69,6 +78,7 @@ class NovaMovIE(InfoExtractor):
             request.add_header('Referer', post_url)
             webpage = self._download_webpage(
                 request, video_id, 'Downloading continue to the video page')
+            self._check_existence(webpage, video_id)
 
         filekey = extract_filekey()
 
@@ -127,19 +137,18 @@ class NowVideoIE(NovaMovIE):
     _HOST = 'www.nowvideo.to'
 
     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
-    _FILEKEY_REGEX = r'var fkzd="([^"]+)";'
     _TITLE_REGEX = r'<h4>([^<]+)</h4>'
     _DESCRIPTION_REGEX = r'</h4>\s*<p>([^<]+)</p>'
 
     _TEST = {
-        'url': 'http://www.nowvideo.to/video/0mw0yow7b6dxa',
-        'md5': 'f8fbbc8add72bd95b7850c6a02fc8817',
+        'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b',
+        'md5': '12c82cad4f2084881d8bc60ee29df092',
         'info_dict': {
-            'id': '0mw0yow7b6dxa',
+            'id': 'f1d6fce9a968b',
             'ext': 'flv',
-            'title': 'youtubedl test video _BaW_jenozKc.mp4',
+            'title': 'youtubedl test video BaWjenozKc',
             'description': 'Description',
-        }
+        },
     }
 
 
@@ -153,6 +162,7 @@ class VideoWeedIE(NovaMovIE):
 
     _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<'
     _TITLE_REGEX = r'<h1 class="text_shadow">([^<]+)</h1>'
+    _URL_TEMPLATE = 'http://%s/file/%s'
 
     _TEST = {
         'url': 'http://www.videoweed.es/file/b42178afbea14',