代码来了
#引入selenium、 pandas、openpyxl库
from selenium import webdriver
import pandas as pd
import openpyxl
#定义存储变量
xq=[]
hxmj=[]
dj=[]
zj=[]
#获取网页源代码
for i in range(5):
url=’https://cd.58.com/ershoufang/pn’+str(i)+’/’
browser = webdriver.Chrome()
browser.get(url)
#解析源代码，提取所需数据信息
for i in browser.find_elements_by_class_name(‘sendsoj’):
xq.append(i.find_elements_by_class_name(‘baseinfo’)[1].text)
hxmj.append(i.find_elements_by_class_name(‘baseinfo’)[0].text.replace(‘\n’,”))
dj.append(i.find_elements_by_class_name(‘price’)[0].find_elements_by_class_name(‘unit’)[0].text)
zj.append(i.find_elements_by_class_name(‘price’)[0].find_elements_by_class_name(‘sum’)[0].text)
pd.DataFrame({‘小区’:xq,’户型/面积’:hxmj,’单价’:dj,’总价’:zj})
data=pd.DataFrame({‘小区’:xq,’户型/面积’:hxmj,’单价’:dj,’总价’:zj})
writer=pd.ExcelWriter(’58.xlsx’)
data.to_excel(writer,’爬虫数据’)
writer.save()
