[已解决]Python,爬取后文件是空的

欧皇肥宅

import requests
import bs4
import re
import random

def open_url(url):
    iplist = ["60.2.44.182:30963","119.254.94.93:46323","113.128.148.50:8118","61.135.155.82:443","124.93.201.59:59618","120.198.76.45:41443"]
    proxies = {"http":random.choice(iplist)}
    headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
    res = requests.get(url,headers=headers,proxies=proxies)
    return res

def find_movies(res):
    soup = bs4.BeautifulSoup(res.text,"html.parser")
    movies = []
    targets1 = soup.find_all("div",class_="p12")
    for each in targets1:
        movies.append(each.a.span.text)

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

def main():
    host = "https://movie.douban.com/chart"
    res = open_url(host)
    result = []
    result.extend(find_movies(res))
    with open("豆瓣排行榜.txt", "w", encoding="utf-8") as f:
        for each in result:
            f.write(each)

if __name__ == "__main__":
    main()
各位大佬帮我看看是怎么回事，运行后没报错，但文件是空的。

最佳答案

月排行榜 / 总排行榜

suchocolate

2020-6-15 17:31:06

欧皇肥宅 发表于 2020-6-15 15:26
我改了class之后。还是报错了。
Traceback (most recent call last):
  File "E:\Python\wor ...

这个页面的第8部电影没有span，所以没有text，你改成这样吧：

1.     for each in targets1:
   
2.         if each.a.string:
   
3.             movies.append(each.a.string)
   
4.         else:
   
5.             movies.append(each.a.span.string)

复制代码

跳转到最佳答案楼层

xiaosi4081

输出一下源码看看

suchocolate

1. targets1 = soup.find_all("div",class_="pl2")

复制代码

class 是 PL2

欧皇肥宅

suchocolate 发表于 2020-6-15 08:43
class 是 PL2

我改了class之后。还是报错了。
Traceback (most recent call last):
  File "E:\Python\work\爬取豆瓣排行榜.py", line 36, in <module>
    main()
  File "E:\Python\work\爬取豆瓣排行榜.py", line 30, in main
    result.extend(find_movies(res))
  File "E:\Python\work\爬取豆瓣排行榜.py", line 18, in find_movies
    movies.append(each.a.span.text)
AttributeError: 'NoneType' object has no attribute 'text'

欧皇肥宅

xiaosi4081 发表于 2020-6-15 07:24
输出一下源码看看

怎么输出源码？

xiaosi4081

欧皇肥宅 发表于 2020-6-15 15:26
怎么输出源码？

1. import requests
   
2. import bs4
   
3. import re
   
4. import random
   
5. 
   
6. def open_url(url):
   
7.     iplist = ["60.2.44.182:30963","119.254.94.93:46323","113.128.148.50:8118","61.135.155.82:443","124.93.201.59:59618","120.198.76.45:41443"]
   
8.     proxies = {"http":random.choice(iplist)}
   
9.     headers = {"user-agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
   
10.     res = requests.get(url,headers=headers,proxies=proxies)
    
11.     print(res.text)
    
12.     return res
    
13. 
    
14. def find_movies(res):
    
15.     soup = bs4.BeautifulSoup(res.text,"html.parser")
    
16.     movies = []
    
17.     targets1 = soup.find_all("div",class_="p12")
    
18.     for each in targets1:
    
19.         movies.append(each.a.span.text)
    
20. 
    
21.     result = []
    
22.     length = len(movies)
    
23.     for i in range(length):
    
24.         result.append(moives[i]+'\n')
    
25.     return result
    
26. 
    
27. def main():
    
28.     host = "https://movie.douban.com/chart"
    
29.     res = open_url(host)
    
30.     result = []
    
31.     result.extend(find_movies(res))
    
32.     with open("豆瓣排行榜.txt", "w", encoding="utf-8") as f:
    
33.         for each in result:
    
34.             f.write(each)
    
35. 
    
36. if __name__ == "__main__":
    
37.     main()

复制代码

suchocolate

欧皇肥宅 发表于 2020-6-15 15:26
我改了class之后。还是报错了。
Traceback (most recent call last):
  File "E:\Python\wor ...

这个页面的第8部电影没有span，所以没有text，你改成这样吧：

1.     for each in targets1:
   
2.         if each.a.string:
   
3.             movies.append(each.a.string)
   
4.         else:
   
5.             movies.append(each.a.span.string)

复制代码

欧皇肥宅

suchocolate 发表于 2020-6-15 17:31
这个页面的第8部电影没有span，所以没有text，你改成这样吧：

谢谢。可以了。