CrawlSpider一直无法进入回调函数

Posted 2020-12-17 wlj-axia

 

CrawlSpider一直无法进入回调函数的

碰到的两个坑：

1、正则表达式写的不对

start_urls = [‘http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1‘]

link = LinkExtractor(allow=r‘id=1&page=d+‘)

2、回调函数中的xpath路径写的不对

附本次代码:

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from sunCrawlSpider.items import SuncrawlspiderItem
from sunCrawlSpider.items import Detail_item


class SunSpider(CrawlSpider):
    name = ‘sun‘
    # allowed_domains = [‘www.xxx.com‘]
    start_urls = [‘http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1‘]

    link = LinkExtractor(allow=r‘id=1&page=d+‘)

    link_detail = LinkExtractor(allow=r‘political/politics/index?id=d+‘)

    rules = (
        Rule(link, callback=‘parse_item‘, follow=False),
        Rule(link_detail, callback=‘parse_detail‘, follow=False),
    )

    def parse_item(self, response):
        li_list = response.xpath(‘/html/body/div[2]/div[3]/ul[2]/li‘)
        for li in li_list:
            num = li.xpath(‘./span[1]/text()‘).extract_first()
            title = li.xpath(‘./span[3]/a/text()‘).extract_first()
            # url = ‘http://wz.sun0769.com/‘ + li.xpath(‘./span[3]/a/@href‘).extract_first()
            item = SuncrawlspiderItem()
            item[‘title‘] = title
            item[‘num‘] = num

            yield item

    def parse_detail(self, response):
        content = response.xpath(‘/html/body/div[3]/div[2]/div[2]/div[2]/pre/text()‘).extract_first()
        num = response.xpath(‘/html/body/div[3]/div[2]/div[2]/div[1]/span[4]/text()‘).extract_first()
        num = num.split(‘:‘)[-1]
        item = Detail_item()
        item[‘num‘] = num
        item[‘content‘] = content

        yield item