用 BeautifulSoup库爬取58同城售房信息
58同城上市仪式
重要的代码在这哦!
#引入requests、BeautifulSoup、 pandas、openpyxl库
import requests
from bs4 import BeautifulSoup
import pandas as pd
import openpyxl
#定义存储变量
xq=[]
hx=[]
mj=[]
cx=[]
#获取网页源代码
for i in range(5):
url='https://cd.58.com/ershoufang/pn'+str(i)+'/'
request=requests.get(url)
html=request.text
#解析源代码,提取所需数据信息
for i in soup.find_all(attrs={'class':'list-info'}):
xq.append(i.find_all('p',class_='baseinfo')[1].find_all('a')[0].text)
hx.append(i.find_all('p')[0].find_all('span')[0].text)
mj.append(i.find_all('p')[0].find_all('span')[1].text.replace('\xa0',''))
cx.append(i.find_all('p')[0].find_all('span')[2].text)
pd.DataFrame({'小区':xq,'户型':hx,'面积':mj,'朝向':cx})
data=pd.DataFrame({'小区':xq,'户型':hx,'面积':mj,'朝向':cx})
writer=pd.ExcelWriter('58tongcheng.xlsx')
data.to_excel(writer,'爬虫数据')
writer.save()
哈哈哈,姚老板笑的好嗨!