深入理解Python requests库的重定向处理与3xx状态码获取

import requests

url_to_check = "http://example.com/old-page" # 假设这个URL会302重定向到 /new-page
response = requests.get(url_to_check, timeout=5)
print(response.status_code) # 预期302，但可能输出200

import requests

url_to_check = "http://example.com/old-page" # 假设这个URL会302重定向到 /new-page
response = requests.get(url_to_check, timeout=5, allow_redirects=False)
print(response.status_code) # 现在将准确输出302

import csv
import requests

def check_url_status(url: str) -> str:
    """
    检查URL的状态，并返回描述性状态字符串。
    通过设置allow_redirects=False来捕获原始的重定向状态码。
    """
    try:
        # 禁用自动重定向，以便捕获3xx状态码
        response = requests.get(url, timeout=5, allow_redirects=False)
        status_code = response.status_code

        # 如果需要查看重定向历史，可以在这里检查 response.history
        # 例如：
        # if response.history:
        #     print(f"URL: {url} - 重定向路径: {[r.url for r in response.history]}")

        if 200 <= status_code <= 299:
            return f"活动 ({status_code})"
        elif status_code == 300:
            return f"多重选择重定向 ({status_code})"
        elif status_code == 301:
            return f"永久移动重定向 ({status_code})"
        elif status_code == 302:
            return f"临时移动重定向 ({status_code})"
        elif 303 <= status_code <= 399: # 涵盖303 See Other, 307 Temporary Redirect, 308 Permanent Redirect
            return f"重定向 ({status_code})"
        elif 400 <= status_code <= 499:
            return f"客户端错误 ({status_code})"
        elif 500 <= status_code <= 599:
            return f"服务器错误 ({status_code})"
        else:
            return f"未知状态 ({status_code})"
    except requests.exceptions.Timeout:
        return "错误: 请求超时"
    except requests.exceptions.ConnectionError:
        return "错误: 连接失败"
    except requests.exceptions.RequestException as e:
        return f"错误: {e}"
    except Exception as e:
        return f"未知错误: {e}"

# 假设 urls.csv 文件存在，并且每行包含一个待检查的URL。
# 示例 urls.csv 内容：
# http://www.google.com
# http://httpbin.org/status/404
# http://httpbin.org/redirect-to?url=http://example.com
# http://www.nonexistent-domain-12345.com

# 读取URL列表
urls_to_check = []
try:
    with open("urls.csv", "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())
except FileNotFoundError:
    print("错误: urls.csv 文件未找到。请确保文件存在并包含URL列表。")
    exit()
except Exception as e:
    print(f"读取urls.csv时发生错误: {e}")
    exit()

# 检查每个URL并写入结果
if urls_to_check:
    with open("url_status.csv", "w", newline="", encoding="utf-8") as outfile:
        writer = csv.writer(outfile)
        writer.writerow(["URL", "状态"])
        for url in urls_to_check:
            status = check_url_status(url)
            print(f"检查 {url}: {status}") # 实时输出进度
            writer.writerow([url, status])
    print("\nURL状态已成功写入 url_status.csv!")
else:
    print("未从 urls.csv 中读取到任何URL。")