爬虫

1. 代码

import re

import scrapy

from Fang.items import esf_FangItem


class ExampleSpider(scrapy.Spider):
    name = 'example'
    allowed_domains = ['www.fang.com']
    start_urls = ['https://www.fang.com/SoufunFamily.htm']

    def parse(self, response):
        trs = response.xpath('//div[@id="c02"]//tr')
        province = None
        for tr in trs:
            province_f = tr.xpath('./td[2]//text()').get()
            province_f = re.sub(r"s", "", province_f)
            if province_f:
                province = province_f
            cities = tr.xpath('./td[3]/a')
            for i in cities:
                city = i.xpath('./text()').get()
                city_url = i.xpath('./@href').get()
                # print(city, city_url)
                yield scrapy.Request(url=city_url, callback=self.parse_url, meta={'info': (province, city)})
            #     break
            # break

    def parse_url(self, response):
        print(2)

2. 问题描述运行项目时，parse_url不执行，即不能打印2

　　日志打印如下：

2020-03-20 17:08:02 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'bj.fang.com': <GET http://bj.fang.com/>
2020-03-20 17:08:02 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'sh.fang.com': <GET http://sh.fang.com/>
2020-03-20 17:08:02 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'tj.fang.com': <GET http://tj.fang.com/>
2020-03-20 17:08:02 [scrapy.spidermiddlewares.offsite] DEBUG: Filtered offsite request to 'cq.fang.com': <GET http://cq.fang.com/>

3. 解答

　　百度得知是二次解析的域名被过滤掉了

　　解决方法：

　　　

方法一：
　　去掉域名：  allowed_domains = ['www.fang.com']

　　或将其改为：  allowed_domains = ['fang.com']

方法二： 
　　加上：dont_filter=True （不推荐此方法）

　　yield scrapy.Request(url=city_url, callback=self.parse_url, meta={'info': (province, city)}, dont_filter=True)