震惊！中国地震台网数据爬取

import scrapy
import re

from scrapy import Request
from urllib import parse

from SpiderDemo.items import SpiderdemoItem
class CeicSpider(scrapy.Spider):
    name = 'ceic'
    allowed_domains = ['www.ceic.ac.cn/speedsearch?time=6']
    start_urls = ['http://www.ceic.ac.cn/speedsearch?time=6/']

    def parse(self, response):
        post_nodes = response.xpath('//*[@align="left"]/a/@href').extract()
        for post_node in post_nodes:
            yield Request(url=parse.urljoin(response.url,post_node),callback=self.parse_detail,dont_filter=True)

        next_url = response.xpath('//*[@id="paging"]/div/div/ul/li[last()-1]/a/@href').extract()[0]
        if next_url:
            yield Request(url=parse.urljoin(response.url,next_url),callback=self.parse,dont_filter=True)


    def parse_detail(self,response):

        spider_item = SpiderdemoItem()


        time = response.xpath('//*[@valign="middle"]/text()').extract()[1].strip()
        latitude = response.xpath('//*[@valign="middle"]/text()').extract()[3].replace("°","")
        longitude = response.xpath('//*[@valign="middle"]/text()').extract()[5].replace("°","")
        depth = response.xpath('//*[@valign="middle"]/text()').extract()[7].replace("千米","")
        level = response.xpath('//*[@valign="middle"]/text()').extract()[9]
        area = response.xpath('//*[@valign="middle"]/text()').extract()[11]


        spider_item["time"] = time
        spider_item["latitude"] = latitude
        spider_item["longitude"] = longitude
        spider_item["depth"] = depth
        spider_item["level"] = level
        spider_item["area"] = area

        return spider_item

Name：Eamonze
Time ： 2020/12/5