今天我们将学习Python网络编程，包括HTTP请求、API调用和简单的网络爬虫。这是Python非常重要的应用领域。

第一部分：HTTP协议基础

1.1 HTTP协议简介

• HTTP（超文本传输协议）是Web通信的基础
• 常见的HTTP方法：GET、POST、PUT、DELETE
• HTTP状态码：200（成功）、404（未找到）、500（服务器错误）等

1.2 安装必要的库

# 在命令行中安装requests库
pip install requests beautifulsoup4

第二部分：使用requests库进行HTTP请求

import requests
import json
from bs4 import BeautifulSoup
import time
import os
from urllib.parse import urljoin, urlparse
import csv

class HTTPDemo:
    def __init__(self):
        self.session = requests.Session()
        # 设置通用的请求头，模拟浏览器访问
        self.headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
        }
    
    def get_request_demo(self):
        """GET请求示例"""
        print("=== GET请求演示 ===")
        
        # 使用公开的测试API
        url = "https://httpbin.org/get"
        
        try:
            response = self.session.get(url, headers=self.headers, params={"name": "Python", "day": 25})
            
            print(f"状态码: {response.status_code}")
            print(f"响应头: {dict(response.headers)}")
            print(f"响应内容: {response.text}")
            
            # 将响应解析为JSON
            if response.status_code == 200:
                data = response.json()
                print(f"解析后的JSON: {json.dumps(data, indent=2, ensure_ascii=False)}")
                
        except requests.exceptions.RequestException as e:
            print(f"请求失败: {e}")
    
    def post_request_demo(self):
        """POST请求示例"""
        print("\n=== POST请求演示 ===")
        
        url = "https://httpbin.org/post"
        
        # 准备数据
        data = {
            "name": "Python学习者",
            "course": "Python网络编程",
            "day": 25
        }
        
        try:
            response = self.session.post(url, headers=self.headers, json=data)
            
            print(f"状态码: {response.status_code}")
            
            if response.status_code == 200:
                result = response.json()
                print(f"服务器返回的数据: {json.dumps(result, indent=2, ensure_ascii=False)}")
                
        except requests.exceptions.RequestException as e:
            print(f"POST请求失败: {e}")
    
    def download_file(self, url, filename=None):
        """下载文件示例"""
        print(f"\n=== 文件下载演示 ===")
        
        if filename is None:
            filename = os.path.basename(urlparse(url).path) or "download.file"
        
        try:
            response = self.session.get(url, headers=self.headers, stream=True)
            
            if response.status_code == 200:
                # 获取文件大小
                total_size = int(response.headers.get('content-length', 0))
                
                with open(filename, 'wb') as f:
                    downloaded_size = 0
                    for chunk in response.iter_content(chunk_size=8192):
                        if chunk:
                            f.write(chunk)
                            downloaded_size += len(chunk)
                            
                            # 显示下载进度
                            if total_size > 0:
                                percent = (downloaded_size / total_size) * 100
                                print(f"\r下载进度: {percent:.1f}%", end='')
                
                print(f"\n文件已下载: {filename}")
                return True
            else:
                print(f"下载失败，状态码: {response.status_code}")
                return False
                
        except Exception as e:
            print(f"下载过程中出错: {e}")
            return False
    
    def check_website_status(self, url):
        """检查网站状态"""
        try:
            start_time = time.time()
            response = self.session.get(url, headers=self.headers, timeout=10)
            end_time = time.time()
            
            response_time = (end_time - start_time) * 1000  # 转换为毫秒
            
            return {
                'url': url,
                'status_code': response.status_code,
                'response_time': f"{response_time:.2f}ms",
                'content_length': len(response.content),
                'server': response.headers.get('Server', 'Unknown')
            }
        except requests.exceptions.RequestException as e:
            return {
                'url': url,
                'error': str(e)
            }

# 运行HTTP演示
def run_http_demo():
    demo = HTTPDemo()
    demo.get_request_demo()
    demo.post_request_demo()
    
    # 下载一个小文件示例（使用一个公开的测试文件）
    demo.download_file("https://httpbin.org/image/jpeg", "sample_image.jpg")
    
    # 检查网站状态
    websites = [
        "https://www.baidu.com",
        "https://www.google.com",
        "https://httpbin.org/status/404",
        "https://invalid-website-that-does-not-exist.com"
    ]
    
    print("\n=== 网站状态检查 ===")
    for website in websites:
        result = demo.check_website_status(website)
        if 'error' in result:
            print(f"{result['url']} - 错误: {result['error']}")
        else:
            print(f"{result['url']} - 状态: {result['status_code']}, "
                  f"响应时间: {result['response_time']}, "
                  f"服务器: {result['server']}")

if __name__ == "__main__":
    run_http_demo()

第三部分：API调用实战