Question

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
#scrapy crawl dmoz -o items.json -t json
from scrapy.http import Request
from urlparse import urlparse

from manga.items import MangaItem

class MangaHere(CrawlSpider):
    name = "mangahs"
    allowed_domains = ["mangahere.com"]
    start_urls = ["http://www.mangahere.com/seinen/"]
    rules = [Rule(SgmlLinkExtractor(allow = ('//a[@class="next"]')), follow=True, 

        callback='parse_item'),]


#def parse(self, response):
    # get indext depth for every page
   # hxs = HtmlXPathSelector(response)
   # next_link = hxs.select('//a[@class="next"]')
   # index_depth = int(next_link.select('preceding-sibling::a[1]/text()').extract()[0])        
    #create a request for the first page

  #  url = urlparse("http://www.mangahere.com/seinen/")
  #  yield Request(url.geturl(), callback=self.parse_item)

    #create a request for each subsequent page in the form "./seinen/x.html"
 #   for x in xrange(2, index_depth):
 #       pageURL = "http://www.mangahere.com/seinen/%s.htm" % x
 #       url = urlparse(pageURL)
  #      yield Request(url.geturl(), callback=self.parse_item)
    def parse_start_url(self, response):
        list(self.parse_item(response))

    def parse_item(self,response):
        hxs = HtmlXPathSelector(response)
        sites = hxs.select('//ul/li/div')
        items = []
        for site in sites:
            rating = site.select("p/span/text()").extract()      
            desc = site.select("p[2]/text()").extract()
            for i in rating: 
                for p in desc:
                    if float(i) > 4.8 and "ecchi" not in str(p):
                        item = MangaItem()
                        item['title'] = site.select("div/a/text()").extract()
                        item['link'] = site.select("div/a/@href").extract()
                        item['desc'] = site.select("p[2]/text()").extract()
                        item['rate'] = site.select("p/span/text()").extract()         

                        items.append(item)
        return items

评论的内容是一种抓取页面的方法，而不是像这里有人帮助我的爬虫。但我仍然想学习如何使crawlspider为了知道而工作。

我没有错误，但它抓了0页，我检查了很多线程，听起来好像我必须添加parse_start_url由于某种原因，但这没有帮助，改变了解析函数的名称也没有帮助。

什么不起作用？我的规则不正确还是我错过了什么？

Answer 1

对于不是allow的网址，REGEX应为xpath http://doc.scrapy.org/en/0.12/topics/spiders.html

如果您想使用xpath，则需要使用restrict_xpath

Answer 2

您需要将规则更改为以下内容：

rules = [Rule(SgmlLinkExtractor(allow = ('/\d+.htm')), follow=True, 
    callback='parse_item'),]

Answer 3

规则中的回调与方法不符。 CrawlSpider有一个名为parse的默认方法，因此def parse(CrawlSpider)应更改为def parse_item以匹配您的回调

Crawlspider没有刮刮任何东西

3 个答案: