import scrapy

from scrapy.linkextractors import LinkExtractor

from scrapy.spiders import CrawlSpider

import re

 

class
QicheSpider(CrawlSpider):

name =
‘qiche’

allowed_domains = [‘autohome.com.cn’]


# 123

start_urls = [‘https://www.autohome.com.cn/grade/carhtml/’+ i.upper() +‘_photo.html’
for i in
map(chr,range(97,99))]

 


# rules = (


# Rule(LinkExtractor(allow=()), callback=’parse_item’),


# )

 


def
parse_start_url(self, response):

brand_node_list = response.xpath(“//dl”)


for brand_node in brand_node_list:


# 商标名

brand_name = brand_node.xpath(“./dt/div/a/text()”).extract_first()

 

producer_list = brand_node.xpath(“./dd/div[@class=’h3-tit’]/text()”).extract()

producer_ul_node_list = brand_node.xpath(“./dd/ul”)


for producer_name, producer_ul_list in
zip(producer_list, producer_ul_node_list):


 

版权声明：本文为ppansj原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：http://www.cnblogs.com/ppansj/p/7954339.html