网DAI之家简单爬取

 1 #!/usr/bin/python3
 2 
 3 import requests
 4 from bs4 import BeautifulSoup
 5 import re
 6 
 7 class wdzj_spider:
 8     def request(self, url):
 9         headers = {‘User-Agent‘: "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1"}
10         return requests.get(url, headers=headers)
11 
12     def getLinkFromPage(self, pingtaiLink):
13         pingtaiHtml = self.request(pingtaiLink)
14         #默认编码有问题，需手动转码
15         txtUTF8 = str(pingtaiHtml.content, ‘utf-8‘)
16         briefSec = BeautifulSoup(txtUTF8, "lxml",from_encoding="utf8").find("div", class_="cen-zk")
17         print("简介={0}".format(briefSec.get_text()))
18 
19     def getAllPage(self):
20         startUrl = ‘https://www.wdzj.com/dangan/search?filter=&sort=1&currentPage=1‘
21         mainHtml = self.request(startUrl)
22         pageStr = BeautifulSoup(mainHtml.text, "lxml").find("span", class_="all").text
23         searchObj = re.search(r‘1/([0-9]+)‘, pageStr, re.M | re.I)
24         pageCount = searchObj.group(1)
25 
26         startUrl = ‘https://www.wdzj.com/dangan/search?filter=&sort=1&currentPage=‘
27         baseUrl = ‘https://www.wdzj.com‘
28 
29         print("pageCount={0}".format(pageCount))
30         for i in range(1, int(pageCount)+1):
31         # for i in range(1, 2):
32             urlPage = startUrl + str(i)
33             pageHtml = self.request(urlPage)
34             pageStrs = BeautifulSoup(pageHtml.text, "lxml").find_all(‘a‘,text=‘查看档案‘)
35             for a in pageStrs:
36                 print("查看档案：")
37                 self.getLinkFromPage(baseUrl+a[‘href‘])
38 
39 
40 if __name__ == ‘__main__‘:
41     w = wdzj_spider()
42     w.getAllPage()