Implement the METAREFRESH_IGNORE_TAGS setting

docs/topics/downloader-middleware.rst

@@ -805,6 +805,7 @@ The :class:`MetaRefreshMiddleware` can be configured through the following
 settings (see the settings documentation for more info):
 
 * :setting:`METAREFRESH_ENABLED`
+* :setting:`METAREFRESH_IGNORE_TAGS`
 * :setting:`METAREFRESH_MAXDELAY`
 
 This middleware obey :setting:`REDIRECT_MAX_TIMES` setting, :reqmeta:`dont_redirect`,
@@ -826,6 +827,15 @@ Default: ``True``
 
 Whether the Meta Refresh middleware will be enabled.
 
+.. setting:: METAREFRESH_IGNORE_TAGS
+
+METAREFRESH_IGNORE_TAGS
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Default: ``['script', 'noscript']``
+
+Meta tags within these tags are ignored.
+
 .. setting:: METAREFRESH_MAXDELAY
 
 METAREFRESH_MAXDELAY

scrapy/downloadermiddlewares/redirect.py

@@ -88,6 +88,7 @@ class MetaRefreshMiddleware(BaseRedirectMiddleware):
 
     def __init__(self, settings):
         super(MetaRefreshMiddleware, self).__init__(settings)
+        self._ignore_tags = settings.getlist('METAREFRESH_IGNORE_TAGS')
         self._maxdelay = settings.getint('REDIRECT_MAX_METAREFRESH_DELAY',
                                          settings.getint('METAREFRESH_MAXDELAY'))
 
@@ -96,7 +97,8 @@ def process_response(self, request, response, spider):
                 not isinstance(response, HtmlResponse):
             return response
 
-        interval, url = get_meta_refresh(response)
+        interval, url = get_meta_refresh(response,
+                                         ignore_tags=self._ignore_tags)
         if url and interval < self._maxdelay:
             redirected = self._redirect_request_using_get(request, url)
             return self._redirect(redirected, request, spider, 'meta refresh')

scrapy/settings/default_settings.py

@@ -221,6 +221,7 @@
 MEMUSAGE_WARNING_MB = 0
 
 METAREFRESH_ENABLED = True
+METAREFRESH_IGNORE_TAGS = ['script', 'noscript']
 METAREFRESH_MAXDELAY = 100
 
 NEWSPIDER_MODULE = ''

scrapy/utils/response.py

@@ -31,12 +31,12 @@ def get_base_url(response):
 
 
 _metaref_cache = weakref.WeakKeyDictionary()
-def get_meta_refresh(response):
+def get_meta_refresh(response, ignore_tags=('script', 'noscript')):
     """Parse the http-equiv refrsh parameter from the given response"""
     if response not in _metaref_cache:
         text = response.text[0:4096]
         _metaref_cache[response] = html.get_meta_refresh(text, response.url,
-            response.encoding, ignore_tags=('script', 'noscript'))
+            response.encoding, ignore_tags=ignore_tags)
     return _metaref_cache[response]
 
 

tests/test_downloadermiddleware_redirect.py

@@ -279,5 +279,24 @@ def test_redirect_reasons(self):
         self.assertEqual(req2.meta['redirect_reasons'], ['meta refresh'])
         self.assertEqual(req3.meta['redirect_reasons'], ['meta refresh', 'meta refresh'])
 
+    def test_ignore_tags_default(self):
+        req = Request(url='http://example.org')
+        body = ('''<noscript><meta http-equiv="refresh" '''
+                '''content="0;URL='http://example.org/newpage'"></noscript>''')
+        rsp = HtmlResponse(req.url, body=body.encode())
+        response = self.mw.process_response(req, rsp, self.spider)
+        assert isinstance(response, Response)
+
+    def test_ignore_tags_empty_list(self):
+        crawler = get_crawler(Spider, {'METAREFRESH_IGNORE_TAGS': []})
+        mw = MetaRefreshMiddleware.from_crawler(crawler)
+        req = Request(url='http://example.org')
+        body = ('''<noscript><meta http-equiv="refresh" '''
+                '''content="0;URL='http://example.org/newpage'"></noscript>''')
+        rsp = HtmlResponse(req.url, body=body.encode())
+        req2 = mw.process_response(req, rsp, self.spider)
+        assert isinstance(req2, Request)
+        self.assertEqual(req2.url, 'http://example.org/newpage')
+
 if __name__ == "__main__":
     unittest.main()