more patches sent by Patrick

--HG--
extra : convert_revision : svn%3Ab85faa78-f9eb-468e-a121-7cced6da292c%40779

scrapy/trunk/docs/topics/adaptors.rst

@@ -204,6 +204,7 @@ Ok, done! Let's now sum this up into a spider::
         }
 
         def parse_page(self, response):
+            items = []
             rows = hxs.x('//tr[child::td[@class="prod_attrib"]]')
             for product in rows:
                 item = ScrapedItem()
@@ -214,8 +215,9 @@ Ok, done! Let's now sum this up into a spider::
                 item.attribute('description', product.x('td[@class="prod_attrib"][3]/text()'))
                 item.attribute('weight', product.x('td[@class="prod_attrib"][4]/text()'))
                 item.attribute('price', product.x('td[@class="prod_attrib"][5]/text()').re('(\d+)'))
+                items.append(item)
 
-            return [item]
+            return items
 
     SPIDER = MySpider()
 

scrapy/trunk/scrapy/conf/project_template/scrapy_settings.py

@@ -13,6 +13,12 @@ TEMPLATES_DIR = '%s/templates' % $project_name.__path__[0]
 ENABLED_SPIDERS_FILE = '%s/conf/enabled_spiders.list' % $project_name.__path__[0]
 DEFAULT_ITEM_CLASS = 'scrapy.item.ScrapedItem'
 USER_AGENT = '%s/%s' % (BOT_NAME, BOT_VERSION)
+
+# The amount of time (in secs) that the downloader should wait before
+# downloading consecutive pages from the same spider. This can be used
+# to throttle the crawling speed to avoid hitting servers too
+# hard. Decimal numbers are supported. Example:
+# DOWNLOAD_DELAY = 2.5
 DOWNLOAD_TIMEOUT = 600
 
 # use this spider class as default when no spider was found for a given url