Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Add template for a downloader middleware

Paul Tremberthaaaa4da7a4e1
diff --git a/scrapy/templates/project/module/middlewares.py.tmpl b/scrapy/templates/project/module/middlewares.py.tmpl
index 292bf572e..1a4b0caa5 100644
--- a/scrapy/templates/project/module/middlewares.py.tmpl
+++ b/scrapy/templates/project/module/middlewares.py.tmpl
@@ -54,3 +54,50 @@ class ${ProjectName}SpiderMiddleware(object):
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
+
+
+class ${ProjectName}DownloaderMiddleware(object):
+ # Not all methods need to be defined. If a method is not defined,
+ # scrapy acts as if the downloader middleware does not modify the
+ # passed objects.
+
+ @classmethod
+ def from_crawler(cls, crawler):
+ # This method is used by Scrapy to create your spiders.
+ s = cls()
+ crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+ return s
+
+ def process_request(self, request, spider):
+ # Called for each request that goes through the downloader
+ # middleware.
+
+ # Must either:
+ # - return None: continue processing this request
+ # - or return a Response object
+ # - or return a Request object
+ # - or raise IgnoreRequest: process_exception() methods of
+ # installed downloader middleware will be called
+ return None
+
+ def process_response(self, request, response, spider):
+ # Called with the response returned from the downloader.
+
+ # Must either;
+ # - return a Response object
+ # - return a Request object
+ # - or raise IgnoreRequest
+ return response
+
+ def process_exception(self, request, exception, spider):
+ # Called when a download handler or a process_request()
+ # (from other downloader middleware) raises an exception.
+
+ # Must either:
+ # - return None: continue processing this exception
+ # - return a Response object: stops process_exception() chain
+ # - return a Request object: stops process_exception() chain
+ pass
+
+ def spider_opened(self, spider):
+ spider.logger.info('Spider opened: %s' % spider.name)
diff --git a/scrapy/templates/project/module/settings.py.tmpl b/scrapy/templates/project/module/settings.py.tmpl
index 486df6b71..35a0f9a45 100644
--- a/scrapy/templates/project/module/settings.py.tmpl
+++ b/scrapy/templates/project/module/settings.py.tmpl
@@ -53,7 +53,7 @@ ROBOTSTXT_OBEY = True
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
-# '$project_name.middlewares.MyCustomDownloaderMiddleware': 543,
+# '$project_name.middlewares.${ProjectName}DownloaderMiddleware': 543,
#}
# Enable or disable extensions