[已解决]没有生成Excel文件

FengHL

使用Python读写Excel文件（1）课程，按照视频把代码改了，没有生成Excel文件！

1. import requests
   
2. import bs4
   
3. import re
   
4. import openpyxl
   
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/57.0.2987.98 Safari/537.36'}
   
10. 
    
11.     # res = requests.get(url, headers=headers, proxies=proxies)
    
12.     res = requests.get(url, headers=headers)
    
13. 
    
14.     return res
    
15. 
    
16. def find_movies(res):
    
17.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
18. 
    
19.     # 电影名
    
20.     movies = []
    
21.     targets = soup.find_all("div", class_="hd")
    
22.     for each in targets:
    
23.         movies.append(each.a.span.text)
    
24. 
    
25.     # 评分
    
26.     ranks = []
    
27.     targets = soup.find_all("span", class_="rating_num")
    
28.     for each in targets:
    
29.         ranks.append(each.text)
    
30. 
    
31.     # 资料
    
32.     messages = []
    
33.     targets = soup.find_all("div", class_="bd")
    
34.     for each in targets:
    
35.         try:
    
36.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
37.         except:
    
38.             continue
    
39. 
    
40.     result = []
    
41.     length = len(movies)
    
42.     for i in range(length):
    
43.         result.append([movies[i],ranks[i],messages[i]])
    
44. 
    
45.     return result
    
46. 
    
47. # 找出一共有多少个页面
    
48. def find_depth(res):
    
49.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
50.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
51. 
    
52.     return int(depth)
    
53. 
    
54. def main():
    
55.     host = "https://movie.douban.com/top250"
    
56.     res = open_url(host)
    
57.     depth = find_depth(res)
    
58. 
    
59.     result = []
    
60.     for i in range(depth):
    
61.         url = host + '/?start=' + str(25 * i)
    
62.         res = open_url(url)
    
63.         result.extend(find_movies(res))
    
64. 
    
65. def save_to_excel(result):
    
66.     wb = openpyxl.Workbook()
    
67.     ws = wb.active
    
68. 
    
69.     ws['A1'] = "电影名称"
    
70.     ws['B1'] = "评分"
    
71.     ws['C1'] = "资料"
    
72. 
    
73.     for each in result:
    
74.         ws.append(each)
    
75. 
    
76.     wb.save("豆瓣top250电影。xlsx")
    
77.    
    
78. if __name__ == "__main__":
    
79.     main()
    
80.    
    

复制代码

最佳答案

月排行榜 / 总排行榜

Twilight6

2021-6-6 15:37:10

你的 main 函数忘记调用 save_to_excel(result) 了，在 main 的函数最后加上 save_to_excel(result)

你 wb.save("豆瓣top250电影。xlsx") 写成 中文的 句号了... 改成英文的

参考代码：

1. import requests
   
2. import bs4
   
3. import re
   
4. import openpyxl
   
5. 
   
6. 
   
7. def open_url(url):
   
8.     # 使用代理
   
9.     # proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
   
10.     headers = {
    
11.         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
    
12. 
    
13.     # res = requests.get(url, headers=headers, proxies=proxies)
    
14.     res = requests.get(url, headers=headers)
    
15. 
    
16.     return res
    
17. 
    
18. 
    
19. def find_movies(res):
    
20.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
21. 
    
22.     # 电影名
    
23.     movies = []
    
24.     targets = soup.find_all("div", class_="hd")
    
25.     for each in targets:
    
26.         movies.append(each.a.span.text)
    
27. 
    
28.     # 评分
    
29.     ranks = []
    
30.     targets = soup.find_all("span", class_="rating_num")
    
31.     for each in targets:
    
32.         ranks.append(each.text)
    
33. 
    
34.     # 资料
    
35.     messages = []
    
36.     targets = soup.find_all("div", class_="bd")
    
37.     for each in targets:
    
38.         try:
    
39.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
40.         except:
    
41.             continue
    
42. 
    
43.     result = []
    
44.     length = len(movies)
    
45.     for i in range(length):
    
46.         result.append([movies[i], ranks[i], messages[i]])
    
47. 
    
48.     return result
    
49. 
    
50. 
    
51. # 找出一共有多少个页面
    
52. def find_depth(res):
    
53.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
54.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
55. 
    
56.     return int(depth)
    
57. 
    
58. 
    
59. def main():
    
60.     host = "https://movie.douban.com/top250"
    
61.     res = open_url(host)
    
62.     depth = find_depth(res)
    
63. 
    
64.     result = []
    
65.     for i in range(depth):
    
66.         url = host + '/?start=' + str(25 * i)
    
67.         res = open_url(url)
    
68.         result.extend(find_movies(res))
    
69.     save_to_excel(result)
    
70. 
    
71. 
    
72. def save_to_excel(result):
    
73.     wb = openpyxl.Workbook()
    
74.     ws = wb.active
    
75. 
    
76.     ws['A1'] = "电影名称"
    
77.     ws['B1'] = "评分"
    
78.     ws['C1'] = "资料"
    
79. 
    
80.     for each in result:
    
81.         ws.append(each)
    
82. 
    
83.     wb.save("豆瓣top250电影.xlsx")
    
84. 
    
85. 
    
86. if __name__ == "__main__":
    
87.     main()
    
88. 
    

复制代码

跳转到最佳答案楼层

Twilight6

你的 main 函数忘记调用 save_to_excel(result) 了，在 main 的函数最后加上 save_to_excel(result)

你 wb.save("豆瓣top250电影。xlsx") 写成 中文的 句号了... 改成英文的

参考代码：

1. import requests
   
2. import bs4
   
3. import re
   
4. import openpyxl
   
5. 
   
6. 
   
7. def open_url(url):
   
8.     # 使用代理
   
9.     # proxies = {"http": "127.0.0.1:1080", "https": "127.0.0.1:1080"}
   
10.     headers = {
    
11.         'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
    
12. 
    
13.     # res = requests.get(url, headers=headers, proxies=proxies)
    
14.     res = requests.get(url, headers=headers)
    
15. 
    
16.     return res
    
17. 
    
18. 
    
19. def find_movies(res):
    
20.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
21. 
    
22.     # 电影名
    
23.     movies = []
    
24.     targets = soup.find_all("div", class_="hd")
    
25.     for each in targets:
    
26.         movies.append(each.a.span.text)
    
27. 
    
28.     # 评分
    
29.     ranks = []
    
30.     targets = soup.find_all("span", class_="rating_num")
    
31.     for each in targets:
    
32.         ranks.append(each.text)
    
33. 
    
34.     # 资料
    
35.     messages = []
    
36.     targets = soup.find_all("div", class_="bd")
    
37.     for each in targets:
    
38.         try:
    
39.             messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
    
40.         except:
    
41.             continue
    
42. 
    
43.     result = []
    
44.     length = len(movies)
    
45.     for i in range(length):
    
46.         result.append([movies[i], ranks[i], messages[i]])
    
47. 
    
48.     return result
    
49. 
    
50. 
    
51. # 找出一共有多少个页面
    
52. def find_depth(res):
    
53.     soup = bs4.BeautifulSoup(res.text, 'html.parser')
    
54.     depth = soup.find('span', class_='next').previous_sibling.previous_sibling.text
    
55. 
    
56.     return int(depth)
    
57. 
    
58. 
    
59. def main():
    
60.     host = "https://movie.douban.com/top250"
    
61.     res = open_url(host)
    
62.     depth = find_depth(res)
    
63. 
    
64.     result = []
    
65.     for i in range(depth):
    
66.         url = host + '/?start=' + str(25 * i)
    
67.         res = open_url(url)
    
68.         result.extend(find_movies(res))
    
69.     save_to_excel(result)
    
70. 
    
71. 
    
72. def save_to_excel(result):
    
73.     wb = openpyxl.Workbook()
    
74.     ws = wb.active
    
75. 
    
76.     ws['A1'] = "电影名称"
    
77.     ws['B1'] = "评分"
    
78.     ws['C1'] = "资料"
    
79. 
    
80.     for each in result:
    
81.         ws.append(each)
    
82. 
    
83.     wb.save("豆瓣top250电影.xlsx")
    
84. 
    
85. 
    
86. if __name__ == "__main__":
    
87.     main()
    
88. 
    

复制代码

FengHL

Twilight6 发表于 2021-6-6 15:46
你的 main 函数忘记调用 save_to_excel(result) 了，在 main 的函数最后加上 save_to_excel(result)

...

Twilight6

FengHL 发表于 2021-6-6 15:49
改了，好像还是不行

main 函数加了 save_to_excel(result) 了嘛？

FengHL

Twilight6 发表于 2021-6-6 15:50
main 函数加了 save_to_excel(result) 了嘛？

可以了，万分感谢