import requests from bs4 import BeautifulSoup import os import time headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.0.3 Safari/605.1.15'} page_count = 0 for page_num in range(1,10000): for i in range(3579989,4580785): url = f" https://www.antaranews.com/berita/{i}/sekjen-puji-indonesia-selenggarakan-ktt-ke-42-asean-dengan-baik?utm_source=antaranews&utm_medium=desktop&utm_campaign=menu_news" res = requests.get(url, headers=headers) soup = BeautifulSoup(res.text, "html.parser") div = soup.find("div", {"class": "col-md-8"}) if not div: continue text = div.text file = f"{page_count + 1}.txt" with open(file, "w", encoding="utf-8") as f: f.write(text) print(f"{i} saved successfully.") page_count += 1 if page_count >= 500: break if page_count >= 500: break time.sleep(15) print("All pages saved successfully.")检查这段代码，并修改

这段代码是用来爬取新闻网站文章并保存到本地的，但是有一些问题需要修改。

1. 需要将导入 requests 和 bs4 的代码分别写在两行。
2. 在 url 变量中，链接中有空格，需要去除。
3. 在 range 函数中，第二个参数应该是 4580786，因为 range 函数不包括最后一个数。
4. 在写文件时，文件名应该为 f"{page_count + 1}.txt"，而不是 f"{i}.txt"，因为每一页可能会保存多篇文章。
5. 在爬取过程中，应该加上异常处理，防止程序因为网络连接问题而中断。

修改后的代码如下：

import requests
from bs4 import BeautifulSoup
import os
import time

headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/12.0.3 Safari/605.1.15'}

page_count = 0
for page_num in range(1,10000):
    for i in range(3579989,4580786):
        url = f"https://www.antaranews.com/berita/{i}/sekjen-puji-indonesia-selenggarakan-ktt-ke-42-asean-dengan-baik?utm_source=antaranews&utm_medium=desktop&utm_campaign=menu_news"
        try:
            res = requests.get(url, headers=headers)
            soup = BeautifulSoup(res.text, "html.parser")
            div = soup.find("div", {"class": "col-md-8"})
            if not div:
                continue
            text = div.text
            file = f"{page_count + 1}.txt"
            with open(file, "w", encoding="utf-8") as f:
                f.write(text)
                print(f"{i} saved successfully.")
            page_count += 1
            if page_count >= 500:
                break
            time.sleep(15)
        except Exception as e:
            print(f"Error occurred: {e}")
            continue

    if page_count >= 500:
        break

print("All pages saved successfully.")