Scrapy抓取第一頁，但沒有遵循鏈接

Question

我不明白爲什麼Scrapy抓取第一頁但沒有跟蹤鏈接來抓取後續頁面。這必須與規則有關。非常感激。謝謝！

from scrapy.contrib.spiders import CrawlSpider, Rule 
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor 
from scrapy.selector import HtmlXPathSelector 
from craigslist_sample.items import CraigslistItem 

class MySpider(CrawlSpider): 
    name = "craig" 
    allowed_domains = ["sfbay.craigslist.org"] 
    start_urls = ["http://sfbay.craigslist.org/acc/"] 

    rules = (Rule (SgmlLinkExtractor(allow=("index100\.html",),restrict_xpaths=('//p[@id="nextpage"]',)) 
    , callback="parse_items", follow= True), 
    ) 

    def parse_items(self, response): 
     hxs = HtmlXPathSelector(response) 
     titles = hxs.select("//p") 
     items = [] 
     for titles in titles: 
      item = CraigslistItem() 
      item ["title"] = titles.select("a/text()").extract() 
      item ["link"] = titles.select("a/@href").extract() 
      items.append(item) 
     return(items) 

spider = MySpider() 

Answer 1

克雷格使用index100，index200，index300 ...下一頁，最多是index900。

rules = (Rule (SgmlLinkExtractor(allow=("index\d00\.html",),restrict_xpaths=('//p[@id="nextpage"]',)) 
, callback="parse_items", follow= True), 
) 

適合我。