简单爬取微医网

Posted 2021-02-14 tjp40922

一.利用request和xpath爬取微医网

　　

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#author tom
import requests
from lxml import etree
import pymongo

#爬取微医网类
class DoctorSpider():
    #初始化应该具有的一些属性
    def __init__(self):
        self.headers={‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/72.0.3626.109 Safari/537.36‘}
        self.base_url=‘https://www.guahao.com/expert/all/%E5%85%A8%E5%9B%BD/all/%E4%B8%8D%E9%99%90/p‘
        self.page_num=1
        self.info_list = []
        self.client=pymongo.MongoClient(host=‘127.0.0.1‘,port=27017)
        self.db=self.client[‘test‘]
        #抓取网页数据
    def crwal(self):
        print(‘正在爬取第{}页‘.format(self.page_num))
        url=self.base_url+str(self.page_num)
        res=requests.get(url=url,headers=self.headers).text
        #中国有38页
        if self.page_num<=38:
            self.page_num+=1
        return res
    # 网页内容解析
    def parse(self,res):
        page_text=res
        tree=etree.HTML(page_text)
        li_list=tree.xpath(‘//div[@class="g-doctor-items to-margin"]/ul/li‘)
        for li in li_list:
            name=li.xpath("./div[2]/a/text()")[0]
            skill=li.xpath("./div[2]/div[1]/p/text()")[0]
            #解析出来的有很多空格,回车,制表符,
            skill=skill.replace(‘
‘,‘‘).replace(‘
‘,‘‘).replace(‘ ‘,‘‘).strip()
            position=li.xpath("./div[1]/dl/dt/text()")[1]
            position = position.replace(‘
‘,‘‘).strip()
            score=li.xpath("./div[1]/dl/dd/p[3]/span/em/text()")[0]
            num=li.xpath("./div[1]/dl/dd/p[3]/span/i/text()")[0]
            office=li.xpath("./div[1]/dl/dd/p[1]/text()")[0]
            hospital=li.xpath("./div[1]/dl/dd/p[2]/span/text()")[0]
            dic={
                ‘name‘:name,
                ‘skill‘:skill,
                ‘position‘:position,
                ‘score‘:score,
                ‘num‘:num,
                ‘office‘:office,
                ‘hospital‘:hospital,
            }
            self.save(dic)

    #保存函数(保存到mongodb)
    def save(self,dic):
        collection=self.db[‘weiyiwang‘]
        collection.save(dic)

    #项目启动函数
    def run(self):
        while self.page_num<=38:
            response=self.crwal()
            a=self.parse(response)

if __name__ == ‘__main__‘:
    doctor=DoctorSpider()
    doctor.run()