[http://users.skynet.be/sbi/libxml-python/] 4. PyOpenSSL for Windows [http://sourceforge.net/project/showfiles.php?group_id=31249] Step 3. Install Scrapy There are three ways to download and install Scrapy: 1. Installing 'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item')

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))) ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item'), ) def parse_item(self, response): self MySpider(BaseSpider): ... def parse(self, response): if response.url == 'http://www.example.com/products.php': from scrapy.shell import inspect_response inspect_response(response) # ... your parsing code .

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item') followed. This is is only for sites that use Sitemap index files [http://www.sitemaps.org/protocol.php#index] that point to other sitemap files. By default, all sitemaps are followed. SitemapSpider examples

[http://users.skynet.be/sbi/libxml-python/] 4. PyOpenSSL for Windows [http://sourceforge.net/project/showfiles.php?group_id=31249] 5. Download the Windows installer from the Downloads page [http://scrapy.org/download/] 'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item')

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))) ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item'), ) def parse_item(self, response): self MySpider(BaseSpider): ... def parse(self, response): if response.url == 'http://www.example.com/products.php': from scrapy.shell import inspect_response inspect_response(response) # ... your parsing code .

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))) ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item'), ) def parse_item(self, response): self MySpider(BaseSpider): ... def parse(self, response): if response.url == 'http://www.example.com/products.php': from scrapy.shell import inspect_response inspect_response(response) # ... your parsing code .

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item') followed. This is is only for sites that use Sitemap index files [http://www.sitemaps.org/protocol.php#index] that point to other sitemap files. By default, all sitemaps are followed. SitemapSpider examples

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item') followed. This is is only for sites that use Sitemap index files [http://www.sitemaps.org/protocol.php#index] that point to other sitemap files. By default, all sitemaps are followed. sitemap_alternate_links

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny= deny= ('subsection\.php', ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item') followed. This is is only for sites that use Sitemap index files [http://www.sitemaps.org/protocol.php#index] that point to other sitemap files. By default, all sitemaps are followed. SitemapSpider examples

'category.php' (but not matching 'subsection.php') # and follow links from them (since no callback means follow=True by default). Rule(SgmlLinkExtractor(allow=('category\.php', ), deny=('subsection\.php', ))) ))), # Extract links matching 'item.php' and parse them with the spider's method parse_item Rule(SgmlLinkExtractor(allow=('item\.php', )), callback='parse_item'), ) def parse_item(self, response): self MySpider(BaseSpider): ... def parse(self, response): if response.url == 'http://www.example.com/products.php': from scrapy.shell import inspect_response inspect_response(response) # ... your parsing code .