import requests from bs4 import BeautifulSoup import os headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36' } total_pages = 20 # 遍历爬取页面 for i in range(2195306, 3000000): url = f"https://www.bernama.com/bm/news.php?id={i}" res = requests.get(url, headers=headers) soup = BeautifulSoup(res.text, "html.parser") # 获取需要写入的文本内容 div = soup.find("div", {"class": "col-12 col-sm-12 col-md-12 col-lg-8"}) if not div: print(f"id{i} has no data, skipped.") continue text = div.text # 保存到txt文件 file = str(i) + ".txt" with open(file, "w", encoding="utf-8") as f: f.write(text) print(f"id {i} saved successfully.") print("All pages saved successfully.")修改这段代码，设置如果不存在div就跳过，不需要写进txt代码，下一个存在dive的就写进txt，txt重命名为1~500，txt命名需连续，不能跳过，再加上遍历爬取50个网站就休息10秒的代码

可以将代码修改为以下形式：

import requests
from bs4 import BeautifulSoup
import os
import time

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36'
}

page_count = 0
for page_num in range(1, 51):
    for i in range(2195306, 3000000):
        url = f"https://www.bernama.com/bm/news.php?id={i}"
        res = requests.get(url, headers=headers)
        soup = BeautifulSoup(res.text, "html.parser")
        div = soup.find("div", {"class": "col-12 col-sm-12 col-md-12 col-lg-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"id {i} saved successfully.")
        page_count += 1
        if page_count >= 500:
            break
    if page_count >= 500:
        break
    time.sleep(10)

print("All pages saved successfully.")

这里通过嵌套循环，先遍历50个网站，再在每个网站中遍历id，如果存在`div`标签则写入txt文件，并将文件命名为1~500。同时，每写入一个文件，就将计数器`page_count`加1，当`page_count`达到500时退出循环。每遍历完一个网站，就休息10秒钟。