Python爬虫 scrapy框架爬取某招聘网存入mongodb解析

站长资源 2024/11/25 佚名

2 0 1

创建项目

scrapy startproject zhaoping

创建爬虫

cd zhaoping
scrapy genspider hr zhaopingwang.com

目录结构

items.py

  title = scrapy.Field()
  position = scrapy.Field()
  publish_date = scrapy.Field()

pipelines.py

from pymongo import MongoClient

mongoclient = MongoClient(host='192.168.226.150',port=27017)
collection = mongoclient['zhaoping']['hr']

class TencentPipeline(object):
  def process_item(self, item, spider):
    print(item)
    # 需要转换为 dict
    collection.insert(dict(item))
    return item

spiders/hr.py

def parse(self, response):
    # 不要第一个 和最后一个
    tr_list = response.xpath("//table[@class='tablelist']/tr")[1:-1]
    for tr in tr_list:
      item = TencentItem()
      # xpath 从1 开始数起
      item["title"] = tr.xpath("./td[1]/a/text()").extract_first()
      item["position"] = tr.xpath("./td[2]/text()").extract_first()
      item["publish_date"] = tr.xpath("./td[5]/text()").extract_first()
      yield item

    next_url = response.xpath("//a[@id='next']/@href").extract_first()
    # 构造url
    if next_url != "javascript:;":
      print(next_url)
      next_url = "https://hr.tencent.com/" + next_url
      yield scrapy.Request(url=next_url,callback=self.parse,)

就是这么简单，就获取到数据