change Scraper API to call internal `_parse` method

A Spider class using internal pre-processing can have first dibs
at this and then call a public `parse` method for subclass hooking.

scrapy/core/scraper.py

@@ -145,7 +145,7 @@ class Scraper(object):
     def call_spider(self, result, request, spider):
         result.request = request
         dfd = defer_result(result)
-        callback = request.callback or spider.parse
+        callback = request.callback or spider._parse
         warn_on_generator_with_return_value(spider, callback)
         warn_on_generator_with_return_value(spider, request.errback)
         dfd.addCallbacks(callback=callback,

scrapy/spiders/__init__.py

@@ -80,6 +80,9 @@ class Spider(object_ref):
         """ This method is deprecated. """
         return Request(url, dont_filter=True)
 
+    def _parse(self, response):
+        return self.parse(response)
+
     def parse(self, response):
         raise NotImplementedError('{}.parse callback is not defined'.format(self.__class__.__name__))
 

scrapy/spiders/crawl.py

@@ -74,7 +74,7 @@ class CrawlSpider(Spider):
         super(CrawlSpider, self).__init__(*a, **kw)
         self._compile_rules()
 
-    def parse(self, response):
+    def _parse(self, response):
         return self._parse_response(response, self.parse_start_url, cb_kwargs={}, follow=True)
 
     def parse_start_url(self, response):

scrapy/spiders/feed.py

@@ -61,7 +61,7 @@ class XMLFeedSpider(Spider):
             for result_item in self.process_results(response, ret):
                 yield result_item
 
-    def parse(self, response):
+    def _parse(self, response):
         if not hasattr(self, 'parse_node'):
             raise NotConfigured('You must define parse_node method in order to scrape this XML feed')
 
@@ -128,7 +128,7 @@ class CSVFeedSpider(Spider):
             for result_item in self.process_results(response, ret):
                 yield result_item
 
-    def parse(self, response):
+    def _parse(self, response):
         if not hasattr(self, 'parse_row'):
             raise NotConfigured('You must define parse_row method in order to scrape this CSV feed')
         response = self.adapt_response(response)

tests/test_spider.py

@@ -142,7 +142,7 @@ class XMLFeedSpiderTest(SpiderTest):
 
         for iterator in ('iternodes', 'xml'):
             spider = _XMLSpider('example', iterator=iterator)
-            output = list(spider.parse(response))
+            output = list(spider._parse(response))
             self.assertEqual(len(output), 2, iterator)
             self.assertEqual(output, [
                 {'loc': [u'http://www.example.com/Special-Offers.html'],