import requests

from bs4 import BeautifulSoup

from sklearn.cluster import KMeans

import os



# 定义一个函数来获取网页内容

def get_html(url):

    headers = {

        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}

    response = requests.get(url, headers=headers)

    soup = BeautifulSoup(response.text, 'lxml')

    return soup



# 定义一个函数来提取文件夹名称

def extract_folder_names(soup):

    folder_names = []

    for link in soup.find_all('a', href=True):

        if 'data' in link['href']:

            folder_names.append(link['href'].split('/')[-1])

    return folder_names



# 定义一个函数来获取所有网页

def get_all_websites():

    urls = []

    for i in range(1, 11):

        url = f'http://www.example.com/rooms/{i}'

        urls.append(url)

    return urls



# 定义一个函数来获取所有网页的内容

def get_all_content(urls):

    contents = []

    for url in urls:

        content = get_html(url)

        contents.append(content)

    return contents



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(contents):

    folder_names = []

    for content in contents:

        soup = BeautifulSoup(content, 'lxml')

        folder_names.extend(extract_folder_names(soup))

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names



# 定义一个函数来获取所有网页的文件夹名称

def get_all_folder_names(urls):

    contents = get_all_content(urls)

    folder_names = get_all_folder_names(contents)

    return folder_names