re实战练习

 1 import re
 2 import requests
 3 
 4 class Spider():
 5     def __init__(self):
 6         self.page=self.page
 7         #self.switch=True
 8 
 9 
10     def loadpage(self,page):
11         url='http://www.neihan8.com/article/index_'+str(page)+'.html'
12         headers={"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36"}
13         response=requests.get(url,headers=headers)
14         html=response.text
15         pattern=re.compile('<div\sclass="desc"(.*?)</div>',re.S)
16         content_list=pattern.findall(html)
17         self.dealpage(content_list)
18 
19     def dealpage(self,content_list):
20         for item in content_list:
21             self.write(item)
22 
23     def write(self,item):
24         with open("duanzi.txt","a") as f:
25             b=item.encode('utf-8')
26             f.write(str(b))
27 
28     def start(self):
29         #d=True
30         #command=input("继续：（退出quit)")
31         page=3
32         self.loadpage(page)
33         #page=4
34 
35 
36 
37 
38 
39 if __name__=="__main__":
40     duanzi=Spider()
41     duanzi.start()

 

转载于:https://www.cnblogs.com/realmonkeykingsun/p/7871469.html