BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-26 16:23:57 +00:00
Code Releases Wiki Activity

adapted project template to use the new Link Extractors location

Browse Source
This commit is contained in:
Pablo Hoffman 2009-07-28 12:27:25 -03:00
parent 64d9155572
commit 75cf903e24
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
scrapy/templates/project/module/templates/spider_crawl.tmpl
View File

@ -2,7 +2,7 @@
import re import re
from scrapy.xpath import HtmlXPathSelector from scrapy.xpath import HtmlXPathSelector
from scrapy.link.extractors import RegexLinkExtractor from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
from scrapy.contrib.spiders import CrawlSpider, Rule from scrapy.contrib.spiders import CrawlSpider, Rule
from $project_name.items import ${ProjectName}Item from $project_name.items import ${ProjectName}Item
@ -11,7 +11,7 @@ class $classname(CrawlSpider):
start_urls = ['http://www.$site/'] start_urls = ['http://www.$site/']
rules = ( rules = (
Rule(RegexLinkExtractor(allow=(r'Items/', )), 'parse_item', follow=True), Rule(SgmlLinkExtractor(allow=(r'Items/', )), 'parse_item', follow=True),
) )
def parse_item(self, response): def parse_item(self, response):