数据提取

import requests
from bs4 import BeautifulSoup
import re

def extract_news_data(url):
    """提取新闻数据"""
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'lxml')
    
    news_list = []
    items = soup.find_all('div', class_='news-item')
    
    for item in items:
        # 提取并清洗数据
        title = item.find('h2', class_='title').text.strip()
        time_str = item.find('span', class_='time').text.strip()
        author = item.find('span', class_='author').text.strip()
        views_text = item.find('span', class_='views').text.strip()
        
        # 数据清洗
        views = clean_views_count(views_text)
        
        news_list.append({
            'title': title,
            'time': time_str,
            'author': author,
            'views': views
        })
    
    return news_list

def clean_views_count(text):
    """清洗阅读量数据"""
    match = re.search(r'(\d+\.?\d*)万?', text)
    if match:
        count = float(match.group(1))
        if '万' in text:
            count *= 10000
        return int(count)
    return 0