Switch codebase to use sanitized_Request instead of

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

diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py
index dde9bea693b080fd086defa7462766898982849b..6163e885558859bb00abb4be7d40da9852132c08 100644 (file)
--- a/youtube_dl/extractor/novamov.py
+++ b/youtube_dl/extractor/novamov.py
@@ -3,9 +3,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     ExtractorError,
-    compat_urlparse
+    NO_DEFAULT,
+    encode_dict,
+    sanitized_Request,
+    urlencode_postdata,
 )
 
 
@@ -13,7 +17,7 @@ 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<videoid>[a-z\d]{13})'
+    _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 = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'}
 
     _HOST = 'www.novamov.com'
@@ -36,20 +40,40 @@ class NovaMovIE(InfoExtractor):
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
+        video_id = self._match_id(url)
 
-        page = self._download_webpage(
-            'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page')
+        url = 'http://%s/video/%s' % (self._HOST, video_id)
 
-        if re.search(self._FILE_DELETED_REGEX, page) is not None:
-            raise ExtractorError(u'Video %s does not exist' % video_id, expected=True)
+        webpage = self._download_webpage(
+            url, video_id, 'Downloading video page')
 
-        filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey')
+        if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
+            raise ExtractorError('Video %s does not exist' % video_id, expected=True)
 
-        title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False)
+        def extract_filekey(default=NO_DEFAULT):
+            return self._search_regex(
+                self._FILEKEY_REGEX, webpage, 'filekey', default=default)
 
-        description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False)
+        filekey = extract_filekey(default=None)
+
+        if not filekey:
+            fields = self._hidden_inputs(webpage)
+            post_url = self._search_regex(
+                r'<form[^>]+action=(["\'])(?P<url>.+?)\1', webpage,
+                'post url', default=url, group='url')
+            if not post_url.startswith('http'):
+                post_url = compat_urlparse.urljoin(url, post_url)
+            request = sanitized_Request(
+                post_url, urlencode_postdata(encode_dict(fields)))
+            request.add_header('Content-Type', 'application/x-www-form-urlencoded')
+            request.add_header('Referer', post_url)
+            webpage = self._download_webpage(
+                request, video_id, 'Downloading continue to the video page')
+
+        filekey = extract_filekey()
+
+        title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title', fatal=False)
+        description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False)
 
         api_response = self._download_webpage(
             'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id,
@@ -67,4 +91,4 @@ class NovaMovIE(InfoExtractor):
             'url': video_url,
             'title': title,
             'description': description
-        }
\ No newline at end of file
+        }