Python3网络爬虫开发实战爬虫基础库

import requests
from bs4 import BeautifulSoup
import re
import time
import random
 
# 设置请求头信息，模拟浏览器访问
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'}
 
def get_html(url):
    """发送请求，获取网页内容"""
    try:
        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，提取有效信息"""
    soup = BeautifulSoup(html, 'html.parser')
    # 提取帖子标题
    titles = soup.find_all('a', class_='j_thread_title')
    for title in titles:
        yield title.get_text()
 
def save_data(data, filename):
    """将数据保存到文件"""
    with open(filename, 'a', encoding='utf-8') as f:
        f.write(data + '\n')
 
def crawl_page(url, filename):
    """爬取页面内容"""
    html = get_html(url)
    if html:
        for title in parse_html(html):
            print(title)
            save_data(title, filename)
            # 为了避免爬虫被封，这里随机休眠几秒
            time.sleep(random.randint(1, 3))
 
if __name__ == '__main__':
    url = 'https://www.example.com/page/number/1'
    filename = 'example.txt'
    crawl_page(url, filename)

这个示例代码展示了如何使用requests库获取网页内容，使用BeautifulSoup进行网页解析，以及如何使用简单的正则表达式提取帖子标题。同时，代码中还包含了异常处理和随机休眠，以防被服务器封禁。这些技巧对于开发健壮的网络爬虫至关重要。