第二版书上爬虫的问题

阿妃

为什么报错了说是变量未定义      NameError: name 'depth' is not defined


# p14_2.py
import requests
import bs4
import re

def open_url(url):
    # 使用代理
    # proxies = {"http":"127.0.0.1:1080","https":"127.0.0.1:1080"}
    headers = {'user-agent':'Mozilla/5.0 (windows NT 10.0; WOW64)AppleWebKit/537.36(KHTML,like Gecko)Chrome/57.0.298.98 Safari/537.36'}
    # res = requests.get(url,headers=headers,proxies=proxies)
    return res

def find_movies(res):
    soup = bs4.BeautifulSoup(res.text,'html.parser')
    #电影名
    movies = []
    targets = soup.find_all("div",class_="hd")
    for each in tergets:
        movies.append(each.a.span.text)
    #评分
    ranks = []
    targets = soup.find_all("span",class_="rating_num")
    for each in targets:
        ranks.append('评分: %s ' % each.text)
    #资料
    messages = []
    targets = soup.find_all("div",class_="bd")
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip()+each.p.text.split('\n')[2].strip())
        except:
            continue

    result = []
    length = len(movies)
    for i in range(length):
        result.append(movies[i] + ranks[i] + messages[i] + '\n')
    return result

    #找出一共有多少个页面
def find_depth(res):
    soup = bs4.BeautifulSoup(res.text,'html.parser')
    depth = soup.find('span',class_='next').previous_sibling.previous_sibling.text
    return int(depth)


def main():
    host = "https://movie.douban.com/top250"
    res = open_url(host)
    depth = find_depth(res)
    result = []
   
for i in range(depth):
    ulr = host + '/?start=' + str(25 + 1)
    res = open_url(url)
    result.extend(find_movies(res))

with open("豆瓣 TOP250 电影.txt","w",encoding="utf-8") as f:
    for each in result:
        f.write(each)

if __name__ == "__main__":
    main()

Python3005

你的depth定义是在main函数下的，最后for循环引用不了

zltzlt

应该把 for i in range(depth): 以及后面的内容增加一个缩进，同时 ulr 要改成 url

1. # p14_2.py
   
2. import requests
   
3. import bs4
   
4. import re
   
5. 
   
6. def open_url(url):
   
7.     # 使用代理
   
8.     # proxies = {"http":"127.0.0.1:1080","https":"127.0.0.1:1080"}
   
9.     headers = {'user-agent':'Mozilla/5.0 (windows NT 10.0; WOW64)AppleWebKit/537.36(KHTML,like Gecko)Chrome/57.0.298.98 Safari/537.36'}
   
10.     # res = requests.get(url,headers=headers,proxies=proxies)
    
11.     return res
    
12. 
    
13. def find_movies(res):
    
14.     soup = bs4.BeautifulSoup(res.text,'html.parser')
    
15.     #电影名
    
16.     movies = []
    
17.     targets = soup.find_all("div",class_="hd")
    
18.     for each in tergets:
    
19.         movies.append(each.a.span.text)
    
20.     #评分
    
21.     ranks = []
    
22.     targets = soup.find_all("span",class_="rating_num")
    
23.     for each in targets:
    
24.         ranks.append('评分: %s ' % each.text)
    
25.     #资料
    
26.     messages = []
    
27.     targets = soup.find_all("div",class_="bd")
    
28.     for each in targets:
    
29.         try:
    
30.             messages.append(each.p.text.split('\n')[1].strip()+each.p.text.split('\n')[2].strip())
    
31.         except:
    
32.             continue
    
33. 
    
34.     result = []
    
35.     length = len(movies)
    
36.     for i in range(length):
    
37.         result.append(movies[i] + ranks[i] + messages[i] + '\n')
    
38.     return result
    
39. 
    
40.     #找出一共有多少个页面
    
41. def find_depth(res):
    
42.     soup = bs4.BeautifulSoup(res.text,'html.parser')
    
43.     depth = soup.find('span',class_='next').previous_sibling.previous_sibling.text
    
44.     return int(depth)
    
45. 
    
46. 
    
47. def main():
    
48.     host = "https://movie.douban.com/top250"
    
49.     res = open_url(host)
    
50.     depth = find_depth(res)
    
51.     result = []
    
52.    
    
53.     for i in range(depth):
    
54.         url = host + '/?start=' + str(25 + 1)
    
55.         res = open_url(url)
    
56.         result.extend(find_movies(res))
    
57. 
    
58.     with open("豆瓣 TOP250 电影.txt","w",encoding="utf-8") as f:
    
59.         for each in result:
    
60.             f.write(each)
    
61. 
    
62. if __name__ == "__main__":
    
63.     main()

复制代码