scrapy爬取xx网站招聘信息

爬取某网站招聘爬虫
1、学会如何翻页
思路分析：
a、获取首页的数据
b、寻找下一页的地址，进行翻页，获取数据
步骤：
a、修改start_urls
b、检查allowed_domains
c、parse方法进行解析
2、网页关键词查找：ctrl+f,ctrl+v

1. items.py中进行数据建模

""" 1、items中确定要爬取的字段，规范爬取的数据，防止遗漏 2、创建爬虫，域名xx.com 3、写url,parse解析数据     对数据进行xpath分析，确定数据 """ import scrapy class xxItem(scrapy.Item):     # define the fields for your item here like:     name = scrapy.Field()     link = scrapy.Field()     depart = scrapy.Field()     category = scrapy.Field()     type = scrapy.Field()     address = scrapy.Field()     num = scrapy.Field()     date = scrapy.Field() 

2. 创建爬虫 scrapy genspider job xx.com

# 创建的job.py文件中运行 import scrapy from wangyi.items import xxItem  class JobSpider(scrapy.Spider):     name = 'job'     allowed_domains = ['xx.com']     # 1、更改初始url     start_urls = ['https://hr.xx.com/position/list.do']      def parse(self, response):         # 完成爬虫         # 1、解析响应信息，获取节点列表，         node_list = response.xpath('//*[@class="position-tb"]/tbody/tr')         # print(len(node_list)) 输出40,实际长度20，需要处理数据         # # 2、抽取数据，遍历节点列表，过滤数据         for num, node in enumerate(node_list):             # 设置过滤条件，将目标节点获取出来             if num % 2 == 0:                 item = WangyiItem()                 item['name'] = node.xpath('./td[1]/a/text()').extract_first()                 # response.urljoin()用于拼接相对路径的url                 item['link'] = response.urljoin(node.xpath('./td[1]/a/@href').extract_first())                 item['depart'] = node.xpath('./td[2]/text()').extract_first()                 item['category'] = node.xpath('./td[3]/text()').extract_first()                 item['type'] = node.xpath('./td[4]/text()').extract_first()                 item['address'] = node.xpath('./td[5]/text()').extract_first()                 item['num'] = node.xpath('./td[6]/text()').extract_first().strip()                 item['date'] = node.xpath('./td[7]/text()').extract_first()                 yield item         # 模拟翻页         part_url = response.xpath('/html/body/div[2]/div[2]/div[2]/div/a[last()]/@href').extract_first()          # 判断终止条件         if part_url != 'javascript:;':             next_url = response.urljoin(part_url)             # 构建请求对象，并且返回给引擎,最后去piplines保存数据             yield scrapy.Request(                 url=next_url,                 callback=self.parse             ) 

3. 在piplines.py中保存文件

import json   class xxPipeline:      def __init__(self):         self.file = open('xx.json', 'w')      def process_item(self, item, spider):         item = dict(item)         str_data = json.dumps(item, ensure_ascii=False) + ',\n'          # 写入数据         self.file.write(str_data)         return item      def __del__(self):         self.file.close() 

4. 开启管道，在settings.py中配置ITEM_PIPELINES

ITEM_PIPELINES = {    'xx.pipelines.xxPipeline': 300, }