python爬虫抓取豆瓣电影

 1 import urllib
 2 import re
 3 from bs4 import BeautifulSoup
 4 def get(p):
 5     t=0
 6     k=1
 7     n=1
 8     book_score=[]
 9     book_a=[]
10     while t<=p:
11         print "正在获取第%d页..."%k
12         k=k+1
13         url="https://movie.douban.com/tag/%s?start=%d&type=T"%(‘%E5%8A%A8%E7%94%BB‘,t)
14         res = urllib.urlopen(url)
15         soup = BeautifulSoup(res.read(),"html.parser")
16         book_div = soup.find(attrs={"class":"article"})
17         book_score.extend(book_div.findAll(attrs={‘class‘:‘rating_nums‘}))
18         book_a.extend(book_div.findAll(attrs={"style":"font-size:12px;"}))
19         t=t+20
20     return book_score,book_a
21 
22 p=input("输入页数")
23 a,b=get((p-1)*20)
24 t=0
25 y=[]
26 x=[]
27 for i in a:
28     y.append((i.string))
29 for i in b:
30     x.append(i)
31 u=min(len(x),len(y))
32 for i in range(u):
33     for j in range(i+1,u):
34         if(y[i]<y[j]):
35             t=y[j]
36             y[j]=y[i]
37             y[i]=t
38             t=x[j]
39             x[j]=x[i]
40             x[i]=t
41             
42 for i in range(u):
43     print y[i],x[i].string