Python爬虫(一)——开封市58同城租房信息

 1 # coding=utf-8
 2 import sys
 3 import csv
 4 import requests
 5 from bs4 import BeautifulSoup
 6 
 7 reload(sys)
 8 sys.setdefaultencoding('utf-8')
 9 # 请求头设置
10 
11 def download(url):
12     db_data = requests.get(url)
13     soup = BeautifulSoup(db_data.text, 'lxml')
14     titles = soup.select(
15         'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > h2 > a:nth-of-type(1)')
16     houses = soup.select('body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.room')
17     oneaddresss = soup.select(
18         'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.add > a:nth-of-type(1)')
19     twoaddresss = soup.select(
20         'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.des > p.add > a:nth-of-type(2)')
21     prices = soup.select(
22         'body > div.mainbox > div.main > div.content > div.listBox > ul > li > div.listliright > div.money > b')
23     for title, house, oneaddress, twoaddress, price in zip(titles, houses, oneaddresss, twoaddresss, prices):
24         data = [
25             (
26                 str(title.string).replace(' ', '').replace('\n', ''),
27                 house.get_text().split(' ')[0].replace(' ', '').replace("\n", ""),
28                 house.get_text().split(' ')[-1].replace(' ', '').replace("\n", ""),
29                 oneaddress.get_text().replace(' ', '').replace("\n", ""),
30                 twoaddress.get_text().replace(' ', '').replace("\n", ""),
31                 price.get_text().replace(' ', '').replace("\n", "")
32             )
33         ]
34 
35         csvfile = open('kf.csv', 'ab')
36         writer = csv.writer(csvfile)
37         print('write one house')
38         writer.writerows(data)
39         csvfile.close()
40 
41 
42 # 初始化csv文件
43 def info():
44     csvinfo = open('kf.csv', 'ab')
45     begcsv = csv.writer(csvinfo)
46     begcsv.writerow(['title', 'house', 'area', 'address1', 'address2', 'price'])
47     csvinfo.close()
48 
49 
50 if __name__ == '__main__':
51     info()
52     download(url)