python爬虫--房产数据爬取并保存本地

import requests
import csv
from bs4 import BeautifulSoup
headers={'user-agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.79 Safari/537.36 Maxthon/5.2.6.1000'}
for i in range(1,10):
link='https://fz.anjuke.com/sale/p'+str(i)+'/#filtersort'
r=requests.get(link,headers=headers)
print(str(i + 1), "页响应状态码:", r.status_code)
soup=BeautifulSoup(r.text,'lxml')
house_list=soup.find_all('li',class_="list-item")
with open('test.csv', 'a',newline='',encoding='utf-8-sig')as csvfile:
w=csv.writer(csvfile)
w.writerow(('标题','价格','均价','面积','楼层'))
for house in house_list:
temp = []
name=house.find('div',class_='house-title').a.text.strip()
price=house.find('div',class_='pro-price').contents[1].text.strip()
price_ave=house.find('div',class_='pro-price').contents[2].text.strip()
area=house.find('div',class_='details-item').span.text
floor=house.find('div',class_='details-item').contents[5].text
temp=[name,price,price_ave,area,floor]
print(temp)
w.writerow(temp)

几个注意点：

1、with open('test.csv', 'a',newline='',encoding='utf-8-sig')as csvfile:，注意utf8转码，否则数据保存本地会为乱码形式

2、插入标题的方式，数组的写入

 

转载于:https://www.cnblogs.com/leon507/p/10401091.html