[已解决]爬取豆瓣动作类电影报错

isdkz

start 和 limit 参数重复了，你的 data 那里有 start 和 limit 就不要在 base_url 那里写了

1. import urllib.parse
   
2. import urllib.request
   
3. 
   
4. def create_request(page):
   
5.     base_url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&'     # 注意这里，删掉 start 和 limit
   
6. 
   
7.     data = {
   
8.         'start':(page - 1) * 20,
   
9.         'limit':20
   
10.     }
    
11. 
    
12.     data = urllib.parse.urlencode(data)
    
13. 
    
14.     url = base_url + data
    
15.     print(url)
    
16.     headers = {
    
17.         'User-Agent':'Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36'
    
18.     }
    
19. 
    
20.     request = urllib.request.Request(url=url,headers=headers)
    
21.     return request
    
22. 
    
23. def get_content(request):
    
24.     response = urllib.request.urlopen(request)
    
25.     content = response.read().decode('utf-8')
    
26.     return content
    
27. 
    
28. def down_load(page,content):
    
29.     with open('douban_' + str(page) +'.json','w',encoding='utf-8') as fp:
    
30.         fp.write(content)
    
31. 
    
32. if __name__ == '__main__':
    
33.     start_page = int(input('请输入起始页码'))
    
34.     end_page = int(input('请输入结束页码'))
    
35. 
    
36.     for page in range(start_page,end_page+1):
    
37.         request = create_request(page)
    
38.         content = get_content(request)
    
39.         down_load(page,content)

复制代码