笔记-python编写ZH爬虫实践

import requests
from bs4 import BeautifulSoup
import re
import os
 
def get_html(url):
    """
    获取网页内容
    """
    try:
        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)
        if response.status_code == 200:
            return response.text
        return None
    except requests.RequestException:
        return None
 
def parse_html(html):
    """
    解析网页内容，提取标题和内容
    """
    soup = BeautifulSoup(html, 'lxml')
    title = soup.select('.entry-header h1')[0].text
    content = soup.select('.entry')[0].text
    return title, content
 
def save_note(title, content, save_dir):
    """
    保存笔记
    """
    with open(os.path.join(save_dir, f'{title}.txt'), 'w', encoding='utf-8') as f:
        f.write(content)
 
def main(url):
    html = get_html(url)
    title, content = parse_html(html)
    save_note(title, content, 'notes')
 
if __name__ == '__main__':
    url = 'http://example.com/some-article'  # 替换为目标文章的URL
    main(url)

这段代码实现了一个简单的网页爬取和保存文本内容的功能。首先定义了获取网页内容的函数get_html，使用了请求库requests获取网页。其次定义了解析网页内容的函数parse_html，使用了BeautifulSoup进行HTML内容的解析。最后定义了保存笔记的函数save_note，将解析得到的标题和内容保存到指定的目录。主函数main组合了这些功能，实现了一个简单的爬虫流程。