Python requests库获取HTTP重定向状态码的技巧与实践

import csv
import requests
from requests.exceptions import RequestException # 导入更具体的异常类型

def check_url_status(url):
    """
    检查URL状态并返回描述性状态字符串，支持捕获重定向。
    :param url: 待检查的URL字符串。
    :return: 描述URL状态的字符串。
    """
    try:
        # 禁用自动重定向，以便捕获3xx状态码
        # timeout参数用于设置请求超时时间，防止长时间等待
        response = requests.get(url, timeout=5, allow_redirects=False)
        status_code = response.status_code

        if 200 <= status_code < 300:
            return f"活动 ({status_code})"
        elif 300 <= status_code < 400:
            # 捕获到重定向状态码，可以进一步细分
            if status_code == 301:
                return f"永久重定向 ({status_code})"
            elif status_code == 302:
                return f"临时重定向 ({status_code})"
            elif status_code == 303:
                return f"查看其他 ({status_code})"
            elif status_code == 307:
                return f"临时重定向 (HTTP/1.1) ({status_code})"
            elif status_code == 308:
                return f"永久重定向 (HTTP/1.1) ({status_code})"
            else:
                return f"其他重定向 ({status_code})"
        elif 400 <= status_code < 500:
            return f"客户端错误 ({status_code})"
        elif 500 <= status_code < 600:
            return f"服务器错误 ({status_code})"
        else:
            return f"未知状态 ({status_code})"
    except RequestException as e:
        # 捕获requests库特有的请求异常，如连接错误、超时等
        return f"请求错误: {e}"
    except Exception as e:
        # 捕获其他未知异常
        return f"其他错误: {e}"

# 示例用法：
if __name__ == "__main__":
    # 为了演示，我们先创建一个示例的urls.csv文件
    # 实际应用中，您可能已经有了这个文件
    sample_urls_data = [
        "http://httpbin.org/redirect/1",  # 会重定向一次 (302)
        "http://httpbin.org/status/200",  # 正常 (200)
        "http://httpbin.org/status/404",  # 客户端错误 (404)
        "http://httpbin.org/status/500",  # 服务器错误 (500)
        "https://www.google.com",         # 外部正常网站 (200)
        "http://invalid-domain-example.com" # 可能导致请求错误
    ]
    csv_filename_input = "urls.csv"
    csv_filename_output = "url_status.csv"

    print(f"正在创建示例文件 {csv_filename_input}...")
    with open(csv_filename_input, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        for url in sample_urls_data:
            writer.writerow([url])
    print(f"示例文件 {csv_filename_input} 创建成功。")

    # 从CSV文件读取URL
    urls_to_check = []
    try:
        with open(csv_filename_input, "r", encoding="utf-8") as csvfile:
            reader = csv.reader(csvfile)
            for row in reader:
                if row: # 确保行不为空
                    urls_to_check.append(row[0].strip()) # strip()去除可能的空白字符
    except FileNotFoundError:
        print(f"错误: {csv_filename_input} 文件未找到。请确保文件存在并包含URL列表。")
        exit()

    print(f"\n正在检查 {len(urls_to_check)} 个URL的状态...")
    results = []
    for url in urls_to_check:
        status = check_url_status(url)
        print(f"URL: {url} -> 状态: {status}")
        results.append([url, status])

    # 将结果写入新的CSV文件
    print(f"\n正在将结果写入 {csv_filename_output}...")
    with open(csv_filename_output, "w", newline="", encoding="utf-8") as outfile:
        writer = csv.writer(outfile)
        writer.writerow(["URL", "状态"])
        writer.writerows(results)

    print(f"\nURL状态已成功写入 {csv_filename_output}！")