import requests

import re

import time

def get_page_content(url):

r = requests.get(url)

if r.status_code == 200:

return r.text

return None

def filter_html_tags(html_content):

cleanr = re.compile('<.*?>')

filtered_text = re.sub(cleanr, '', html_content)

return filtered_text

base_url = 'https://bbs.tatans.cn/topic/'

for topic_id in range(1, 50):

url = f'{base_url}{topic_id}'

html_content = get_page_content(url)

if html_content:

# 过滤 HTML 标签，提取纯文本内容

filtered_html = filter_html_tags(html_content)

# 将提取的内容写入文件

file_path = 'D:/filtered_content.txt'

with open(file_path, 'a', encoding='utf-8') as file:

file.write(filtered_html + '\n')

print(f'成功获取并处理页面: {url}')

# 控制请求频率，避免给服务器造成过大压力

time.sleep(1) # 暂停1秒

print('翻页结束')

print('过滤后的内容已写入到文件:', file_path)