豆瓣top250求救

dow

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.     #使用代理
   
7.     #proxies = {"http":"127.0.0.1:1080","https":"127.0.0.1:1080"}
   
8.     headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/57.0.2987.95 Safari/537.36'}
   
9.     # res = requests.get （url, headers = headers, proxies = proxies)
   
10.     res = requests,get(url, headers = headers)
    
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 targets:
    
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.         try:
    
25.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
26.         except:
    
27.             continue
    
28. 
    
29.     result = []
    
30.     length = len(movies)
    
31.     for i in range (length):
    
32.         result.append(movies[i] + ranks[i] + messages[i] + '\n')
    
33.     return result
    
34. 
    
35. #找出一共有多少个页面
    
36. def find_depth(res):
    
37.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
38.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
39.     return int(depth)
    
40. 
    
41. def main():
    
42.     host = "http://movie.douban.com/top250"
    
43.     res = open_url(host)
    
44.     depth = find_depth(res)
    
45. 
    
46.     result = []
    
47.     for i in range (depth):
    
48.         url = host + '/?start=' + str(25*i)
    
49.         res = open_url(url)
    
50.         result.append(find_movies(res))
    
51. 
    
52.     with open ("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
    
53.         for each in result:
    
54.             f.write(each)
    
55. 
    
56. if_ _name_ _ == "_ _main_ _":
    
57.     main()

复制代码

到底是咋回事，这个下面的问题

    if_ _name_ _ == "_ _main_ _":
             ^
SyntaxError: invalid syntax

Sebass

兄嘚，SyntaxError 最最最最最常见的是你用了中文符号

z5560636

if _ _name_ _ == "_ _main_ _":
if后面少了一个空格、
if __name__ == "__main__":

情绪z

if __name__ == '__main__':

逃兵

代码错误挺多
看一下源码

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.     # 使用代理
   
7.     # proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
   
8.     headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
   
9. 
   
10.     # res = requests.get(url, headers=headers, proxies=proxies)
    
11.     res = requests.get(url, headers=headers)
    
12. 
    
13.     return res
    
14. 
    
15. def find_movies(res):
    
16.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
17. 
    
18.     # 电影名
    
19.     movies = []
    
20.     targets = soup.find_all("div", class_="hd")
    
21.     for each in targets:
    
22.         movies.append(each.a.span.text)
    
23. 
    
24.     # 评分
    
25.     ranks = []
    
26.     targets = soup.find_all("span", class_="rating_num")
    
27.     for each in targets:
    
28.         ranks.append(' 评分：%s ' % each.text)
    
29. 
    
30.     # 资料
    
31.     messages = []
    
32.     targets = soup.find_all("div", class_="bd")
    
33.     for each in targets:
    
34.         try:
    
35.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
36.         except:
    
37.             continue
    
38. 
    
39.     result = []
    
40.     length = len(movies)
    
41.     for i in range(length):
    
42.         result.append(movies[i] + ranks[i] + messages[i] + '\n')
    
43. 
    
44.     return result
    
45. 
    
46. # 找出一共有多少个页面
    
47. def find_depth(res):
    
48.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
49.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
50. 
    
51.     return int(depth)
    
52. 
    
53. def main():
    
54.     host = "https://movie.douban.com/top250"
    
55.     res = open_url(host)
    
56.     depth = find_depth(res)
    
57. 
    
58.     result = []
    
59.     for i in range(depth):
    
60.         url = host + '/?start=' + str(25 * i)
    
61.         res = open_url(url)
    
62.         result.extend(find_movies(res))
    
63. 
    
64.     with open("豆瓣TOP250电影.txt", "w", encoding="utf-8") as f:
    
65.         for each in result:
    
66.             f.write(each)
    
67.    
    
68. if __name__ == "__main__":
    
69.     main()

复制代码

第十行res = requests,get(url, headers = headers)改成res = requests.get(url, headers = headers)
第二十三行之后抄错行了
# 资料的部分和#评分的部分抄混了，代码逻辑就乱套了
第56行if_ _name_ _ == "_ _main_ _": 改为 if __name__ == "__main__":