51job_selenium测试

Python爬虫视频教程零基础小白到scrapy爬虫高手-轻松入门

https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import requests,bs4,openpyxl,time,selenium
from openpyxl.cell import get_column_letter,column_index_from_string
from selenium import webdriver
excelName="51job.xlsx"
sheetName="Sheet1"
wb1=openpyxl.load_workbook(excelName)
sheet=wb1.get_sheet_by_name(sheetName)
start=1

charset="gb2312"
site="http://jobs.51job.com/all/co198308.html"
browser=webdriver.Firefox()
browser.get(site)
linkElem=browser.find_element_by_link_text("下一页")
linkElem.click()
#elem = browser.find_element_by_class_name('el')
#返回标签的值
#elem.text
#elems = browser.find_elements_by_class_name('el')
elem=browser.find_element_by_id('joblistdata')
elem.text
'''
'洛阳医药代表（学术专员）\n大专\n洛阳\n4500-5999/月\n03-07\n新乡医药代表（学术专员）\n大专\n新乡\n4500-5999/月\n03-07\n郑州医药代表（学术专员）\n大专\n郑州-二七区\n4500-5999/月\n03-07\n河南医药代表（学术专员）\n大专\n郑州-二七区\n4500-5999/月\n03-07\n苏州医药代表(学术专员)\n连云港\n4500-5999/月\n03-07\n宁波医药代表(学术专员)\n大专\n宁波\n6000-7999/月\n03-07\n杭州医药代表(学术专员)\n大专\n杭州\n6000-7999/月\n03-07\n上海医药代表(学术专员)\n大专\n上海\n4500-5999/月\n03-07\n盐城医药代表(学术专员)\n大专\n连云港\n6000-7999/月\n03-07\n淮安医药代表(学术专员)\n大专\n连云港\n6000-7999/月\n03-07\n徐州医药代表(学术专员)\n大专\n连云港\n4500-5999/月\n03-07\n连云港医药代表(学术专员)\n大专\n连云港\n4500-5999/月\n03-07\n会计\n本科\n连云港\n3000-4499/月\n03-07\n工艺研究员\n本科 | 招聘5人\n连云港\n4500-5999/月\n03-07\n药物合成\n本科 | 招聘10人\n连云港\n3000-4499/月\n03-07\n财会专员\n本科 | 招聘2人\n连云港\n2000-2999/月\n03-07\n会计主管\n3-4年 | 本科 | 招聘1人\n南京-玄武区\n8-10万/年\n03-07\n福建产品专员\n硕士\n连云港\n6000-7999/月\n03-07\n上海产品专员\n硕士\n上海\n6000-7999/月\n03-07\n浙江商业代表\n大专\n杭州\n6000-7999/月\n03-07\n上一页\n1\n2\n3\n4\n5\n6\n7\n下一页'
'''

#每个网站爬取相应数据
def Craw(site):

    res=requests.get(site)
    res.encoding = charset
    soup1=bs4.BeautifulSoup(res.text,"lxml")
    div=soup1.select('.el')
    len_div=len(div)
    for i in range(len_div):
        #print ("i:",i)
        content=div[i].getText()
        content_list=content.split('\n')

        name=content_list[1]
        #print ("name:",name)
        education=content_list[2]
        #print ("education:",education)
        position=content_list[3]
        #print ("position:",position)
        salary=content_list[4]
        #print ("salary:",salary)
        date=content_list[5]
        #print ("date:",date)

        sheet['A'+str(i+2)].value=name
        sheet['B'+str(i+2)].value=education
        sheet['C'+str(i+2)].value=position
        sheet['D'+str(i+2)].value=salary
        sheet['E'+str(i+2)].value=date

'''
Craw(site)
wb1.save(excelName)
    '''