代码:
# coding=utf-8
import sys
import csv
import requests
from bs4 import BeautifulSoup
'''
遇到不懂的问题?Python学习交流群:821460695满足你的需求,资料都已经上传群文件,可以自行下载!
'''
reload(sys)
sys.setdefaultencoding('utf-8')
# 请求头设置
def download(url):
db_data = requests.get(url)
soup = BeautifulSoup(db_data.text, 'lxml')
titles = soup.select(
'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > h2 > a:nth-of-type(1)')
houses = soup.select('body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.room')
oneaddresss = soup.select(
'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.add > a:nth-of-type(1)')
twoaddresss = soup.select(
'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.add > a:nth-of-type(2)')
prices = soup.select(
'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.listliright > div.money > b')
for title, house, oneaddress, twoaddress, price in zip(titles, houses, oneaddresss, twoaddresss, prices):
data = [
(
str(title.string).replace(' ', '').replace('\n', ''),
house.get_text().split(' ')[0].replace(' ', '').replace("\n", ""),
house.get_text().split(' ')[-1].replace(' ', '').replace("\n", ""),
oneaddress.get_text().replace(' ', '').replace("\n", ""),
twoaddress.get_text().replace(' ', '').replace("\n", ""),
price.get_text().replace(' ', '').replace("\n", "")
)
]
csvfile = open('kf.csv', 'ab')
writer = csv.writer(csvfile)
print('write one house')
writer.writerows(data)
csvfile.close()
# 初始化csv文件
def info():
csvinfo = open('kf.csv', 'ab')
begcsv = csv.writer(csvinfo)
begcsv.writerow(['title', 'house', 'area', 'address1', 'address2', 'price'])
csvinfo.close()
if __name__ == '__main__':
info()
download(url)
来源:CSDN
作者:嗨学编程
链接:https://blog.csdn.net/fei347795790/article/details/101025181