declared loaders api stable and updated example project to use them

--HG--
rename : docs/experimental/loaders.rst => docs/topics/loaders.rst

docs/experimental/index.rst

@@ -19,6 +19,5 @@ it's properly merged) . Use at your own risk.
 .. toctree::
    :maxdepth: 1
 
-   loaders
    exporters
    images

docs/topics/index.rst

@@ -14,8 +14,9 @@ Chapter 1. Main topics
    architecture
    shell
    spiders
-   selectors
    items
+   loaders
+   selectors
    request-response
 
 Chapter 2. Extension Mechanisms

examples/googledir/googledir/items.py

@@ -8,4 +8,3 @@ class GoogledirItem(Item):
 
     def __str__(self):
         return "Google Category: name=%s url=%s" % (self['name'], self['url'])
-

examples/googledir/googledir/spiders/google_directory.py

@@ -1,6 +1,7 @@
 from scrapy.xpath import HtmlXPathSelector
 from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
 from scrapy.contrib.spiders import CrawlSpider, Rule
+from scrapy.contrib.loader import XPathItemLoader
 from googledir.items import GoogledirItem
 
 class GoogleDirectorySpider(CrawlSpider):
@@ -16,18 +17,25 @@ class GoogleDirectorySpider(CrawlSpider):
     )
     
     def parse_category(self, response):
-        # The selector we're going to use in order to extract data from the page
-        hxs = HtmlXPathSelector(response)
+        # The main selector we're using to extract data from the page
+        main_selector = HtmlXPathSelector(response)
 
-        # The path to website links in directory page
-        links = hxs.select('//td[descendant::a[contains(@href, "#pagerank")]]/following-sibling::td/font')
+        # The XPath to website links in the directory page
+        xpath = '//td[descendant::a[contains(@href, "#pagerank")]]/following-sibling::td/font'
 
-        for link in links:
+        # Get a list of (sub) selectors to each website node pointed by the XPath
+        sub_selectors = main_selector.select(xpath)
+
+        # Iterate over the sub-selectors to extract data for each website
+        for selector in sub_selectors:
             item = GoogledirItem()
 
-            item['name'] = link.select('a/text()').extract()
-            item['url'] = link.select('a/@href').extract()
-            item['description'] = link.select('font[2]/text()').extract()
-            yield item
+            l = XPathItemLoader(item=item, selector=selector)
+            l.add_xpath('name', 'a/text()')
+            l.add_xpath('url', 'a/@href')
+            l.add_xpath('description', 'font[2]/text()')
+
+            # Here we populate the item and yield it
+            yield l.load_item()
 
 SPIDER = GoogleDirectorySpider()

scrapy/contrib/loader/__init__.py

@@ -75,7 +75,7 @@ class XPathItemLoader(ItemLoader):
 
     def __init__(self, item=None, selector=None, response=None, **context):
         if selector is None and response is None:
-            raise RuntimeError("%s must be instantiated with a selector" \
+            raise RuntimeError("%s must be instantiated with a selector " \
                 "or response" % self.__class__.__name__)
         if selector is None:
             selector = self.default_selector_class(response)