[已解决]极客Python爬起豆瓣出现list index out of range错误怎么办

DSSIMP

代码基本上照抄的小甲鱼的。最后运行出现list index out of range错误怎么解决啊
有没有大佬有现在可运行的完整代码发一下啊

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

复制代码

最佳答案

月排行榜 / 总排行榜

YunGuo

2021-2-3 18:38:24

代码第27句。写错了。
这一句。messages.append(each.p.text.split("\n")[1]后面是'.strip()'，写成了逗号

1. messages.append(each.p.text.split("\n")[1],strip()+each.p.text.split("\n")[2].strip())

复制代码

跳转到最佳答案楼层

°蓝鲤歌蓝

1. headers={'user-agent':'Mozilla/5.0'}

复制代码

这个写错了

YunGuo

代码第27句。写错了。
这一句。messages.append(each.p.text.split("\n")[1]后面是'.strip()'，写成了逗号

1. messages.append(each.p.text.split("\n")[1],strip()+each.p.text.split("\n")[2].strip())

复制代码

DSSIMP

°蓝鲤歌蓝 发表于 2021-2-3 17:26
这个写错了

好的 已修改，但运行没反应

DSSIMP

YunGuo 发表于 2021-2-3 18:38
代码第27句。写错了。
这一句。messages.append(each.p.text.split("\n")[1]后面是'.strip()'，写成了逗号 ...

感谢，已修改，但运行没反应

°蓝鲤歌蓝

报错信息贴出来

DSSIMP

修改后的代码
原先有部分手打的出错了
现在应该跟小甲鱼的一样了
但运行是没反应。。。。

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.         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'}
   
7.         res=requests.get(url,headers=headers)
   
8.         return res
   
9. 
   
10. def find_movies(res):
    
11.     soup=bs4.BeautifulSoup(res.text,"html.parser")
    
12. 
    
13.     movies=[]
    
14.     targets=soup.find_all("div",class_="hd")
    
15.     for each in targets:
    
16.         movies.append(each.a.span.text)
    
17. 
    
18.     ranks=[]
    
19.     targets=soup.find_all("span",class_="rating_num")
    
20.     for each in targets:
    
21.         ranks.append(' 评分：%s ' % each.text)
    
22. 
    
23.     messages=[]
    
24.     targets=soup.find_all("div",class_="bd")
    
25.     for each in targets:
    
26.         try:
    
27.             messages.append(each.p.text.split("\n")[1].strip()+each.p.text.split("\n")[2].strip())
    
28.         except:
    
29.             continue
    
30. 
    
31.     result=[]
    
32.     length=len(movies)
    
33.     for i in range(length):
    
34.         result.append(movies[i]+ranks[i]+messages[i]+"\n")
    
35.     return result
    
36. 
    
37. def find_depth(res):
    
38.     soup=bs4.BeautifulSoup(res.text,"html.parser")
    
39.     depth=soup.find("span",class_="next").previous_sibling.previous_sibling.text
    
40. 
    
41.     return int(depth)
    
42. 
    
43. def main():
    
44.     host="https://movie.douban.com/top250"
    
45.     res=open_url(host)
    
46.     depth=find_depth(res)
    
47. 
    
48.     result=[]
    
49.     for i in range(depth):
    
50.         url=host+"/?start=" + str(25 * i)
    
51.         res=open_url(url)
    
52.         result.extend(find_movies(res))
    
53. 
    
54.     with open("豆瓣TOP250电影.txt","w",encoding="utf-8") as f:
    
55.         for each in result:
    
56.             f.write(each)
    
57. 
    
58. if __name__=="__main__":
    
59.     main()
    

复制代码

DSSIMP

°蓝鲤歌蓝 发表于 2021-2-3 19:16
报错信息贴出来

不报错  就是没反应了

Daniel_Zhang

没反应要么就是没有爬到东西，要么就是你没看到那个生成的文件

你挨个 print 一下，找找问题呗

能 print 的都 print 一下

DSSIMP

Daniel_Zhang 发表于 2021-2-3 19:22
没反应要么就是没有爬到东西，要么就是你没看到那个生成的文件

你挨个 print 一下，找找问题呗

DSSIMP

爬虫成功了 感谢大家

手里尖刀刺

DSSIMP 发表于 2021-2-3 19:59
爬虫成功了 感谢大家

能不能分享下完全体的代码呀  小白路过 还在基础语法趴着 好难

DSSIMP

手里尖刀刺 发表于 2021-8-20 09:55
能不能分享下完全体的代码呀  小白路过 还在基础语法趴着 好难

import requests
import bs4
import re

def open_url(url):
        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'}
        res=requests.get(url,headers=headers)
        return res

def find_movies(res):
    soup=bs4.BeautifulSoup(res.text,"html.parser")

    movies=[]
    targets=soup.find_all("div",class_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    ranks=[]
    targets=soup.find_all("span",class_="rating_num")
    for each in targets:
        ranks.append(' 评分：%s ' % each.text)

    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

    n=len(messages)
    for i in range(n):
        messages[i]=messages[i].replace("\xa0"," ")

    result=[]
    length=len(movies)
    for i in range(length):
        result.append(movies[i]+ranks[i]+messages[i].replace("\xa0"," ")+"\n")
    return result

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):
        url=host+"/?start=" + str(25 * i)
        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()

DSSIMP

DSSIMP 发表于 2021-8-20 14:04
import requests
import bs4
import re

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.         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'}
   
7.         res=requests.get(url,headers=headers)
   
8.         return res
   
9. 
   
10. def find_movies(res):
    
11.     soup=bs4.BeautifulSoup(res.text,"html.parser")
    
12. 
    
13.     movies=[]
    
14.     targets=soup.find_all("div",class_="hd")
    
15.     for each in targets:
    
16.         movies.append(each.a.span.text)
    
17. 
    
18.     ranks=[]
    
19.     targets=soup.find_all("span",class_="rating_num")
    
20.     for each in targets:
    
21.         ranks.append(' 评分：%s ' % each.text)
    
22. 
    
23.     messages=[]
    
24.     targets=soup.find_all("div",class_="bd")
    
25.     for each in targets:
    
26.         try:
    
27.             messages.append(each.p.text.split("\n")[1].strip()+each.p.text.split("\n")[2].strip())
    
28.         except:
    
29.             continue
    
30. 
    
31.     n=len(messages)
    
32.     for i in range(n):
    
33.         messages[i]=messages[i].replace("\xa0"," ")
    
34. 
    
35.     result=[]
    
36.     length=len(movies)
    
37.     for i in range(length):
    
38.         result.append(movies[i]+ranks[i]+messages[i].replace("\xa0"," ")+"\n")
    
39.     return result
    
40. 
    
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. 
    
45.     return int(depth)
    
46. 
    
47. def main():
    
48.     host="https://movie.douban.com/top250"
    
49.     res=open_url(host)
    
50.     depth=find_depth(res)
    
51. 
    
52.     result=[]
    
53.     for i in range(depth):
    
54.         url=host+"/?start=" + str(25 * i)
    
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

DSSIMP

手里尖刀刺 发表于 2021-8-20 09:55
能不能分享下完全体的代码呀  小白路过 还在基础语法趴着 好难

1. import requests
   
2. import bs4
   
3. import re
   
4. 
   
5. def open_url(url):
   
6.         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'}
   
7.         res=requests.get(url,headers=headers)
   
8.         return res
   
9. 
   
10. def find_movies(res):
    
11.     soup=bs4.BeautifulSoup(res.text,"html.parser")
    
12. 
    
13.     movies=[]
    
14.     targets=soup.find_all("div",class_="hd")
    
15.     for each in targets:
    
16.         movies.append(each.a.span.text)
    
17. 
    
18.     ranks=[]
    
19.     targets=soup.find_all("span",class_="rating_num")
    
20.     for each in targets:
    
21.         ranks.append(' 评分：%s ' % each.text)
    
22. 
    
23.     messages=[]
    
24.     targets=soup.find_all("div",class_="bd")
    
25.     for each in targets:
    
26.         try:
    
27.             messages.append(each.p.text.split("\n")[1].strip()+each.p.text.split("\n")[2].strip())
    
28.         except:
    
29.             continue
    
30. 
    
31.     n=len(messages)
    
32.     for i in range(n):
    
33.         messages[i]=messages[i].replace("\xa0"," ")
    
34. 
    
35.     result=[]
    
36.     length=len(movies)
    
37.     for i in range(length):
    
38.         result.append(movies[i]+ranks[i]+messages[i].replace("\xa0"," ")+"\n")
    
39.     return result
    
40. 
    
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. 
    
45.     return int(depth)
    
46. 
    
47. def main():
    
48.     host="https://movie.douban.com/top250"
    
49.     res=open_url(host)
    
50.     depth=find_depth(res)
    
51. 
    
52.     result=[]
    
53.     for i in range(depth):
    
54.         url=host+"/?start=" + str(25 * i)
    
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

手里尖刀刺

C:\Users\gt20180105\Desktop这是什么情况啊 请求无效

ITxiong

手里尖刀刺 发表于 2021-8-20 16:14
这是什么情况啊 请求无效

你没有下载预先下载好requests，先用pip指令下载