Merge pull request #2337 from muriloviana/add-middleware-template

[MRG+1] Add middleware to template project (closes #2335)

scrapy/commands/startproject.py

@@ -17,6 +17,7 @@ TEMPLATES_TO_RENDER = (
     ('${project_name}', 'settings.py.tmpl'),
     ('${project_name}', 'items.py.tmpl'),
     ('${project_name}', 'pipelines.py.tmpl'),
+    ('${project_name}', 'middlewares.py.tmpl'),
 )
 
 IGNORE = ignore_patterns('*.pyc', '.svn')

scrapy/templates/project/module/middlewares.py.tmpl

@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+
+class ${ProjectName}SpiderMiddleware(object):
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, dict or Item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Response, dict
+        # or Item objects.
+        pass
+
+    def process_start_requests(start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info('Spider opened: %s' % spider.name)

scrapy/templates/project/module/settings.py.tmpl

@@ -47,7 +47,7 @@ ROBOTSTXT_OBEY = True
 # Enable or disable spider middlewares
 # See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
 #SPIDER_MIDDLEWARES = {
-#    '$project_name.middlewares.MyCustomSpiderMiddleware': 543,
+#    '$project_name.middlewares.${ProjectName}SpiderMiddleware': 543,
 #}
 
 # Enable or disable downloader middlewares