#Python urllib 使用教程（2024最新版）

from urllib.request import urlopen

# 一个公共的测试 API，返回一条待办事项
TEST_URL = "https://jsonplaceholder.typicode.com/todos/1"

with urlopen(TEST_URL) as response:
    # 看看状态码和原因（比如 200 OK）
    print(f"状态码：{response.status} | 原因：{response.reason}")
    
    # 获取响应头中的 Content-Type
    content_type = response.getheader('Content-Type')
    print(f"Content-Type: {content_type}")
    
    # 读取内容（原始字节流）
    raw_data = response.read()
    # 解码成字符串（默认 utf-8 能覆盖99%场景）
    text = raw_data.decode("utf-8")
    print(f"\n响应内容：\n{text}")

from urllib.request import Request, urlopen

URL = "https://jsonplaceholder.typicode.com/todos/1"

# 先创建 Request 对象
req = Request(URL)

# 添加常见的请求头
req.add_header("User-Agent",
               "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
               "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36")
req.add_header("Accept", "application/json")  # 告诉服务器我只想要 JSON

# 然后像之前一样打开
with urlopen(req) as resp:
    print(resp.read().decode("utf-8"))

from urllib.request import Request, urlopen
from urllib.parse import urlencode

# 模拟登录信息
login_data = {
    "username": "test_user",
    "password": "test_pass_123",
    "remember": "true"
}

# 第1步：把字典变成 URL 编码字符串
encoded_str = urlencode(login_data)
# 第2步：字符串转换成 UTF-8 字节流（urllib 只接受 bytes 作为 POST 数据）
encoded_bytes = encoded_str.encode("utf-8")

# 第3步：创建 Request，指定方法和数据
req = Request(
    url="https://jsonplaceholder.typicode.com/posts",  # 测试用的 POST 接口
    data=encoded_bytes,
    method="POST"   # 默认就是 POST 当提供了 data，但显式写更清楚
)

# 第4步：告诉服务器我们传的是表单格式
req.add_header("Content-Type", "application/x-www-form-urlencoded")
req.add_header("User-Agent", "Chrome/130.0.0.0")

with urlopen(req) as resp:
    print(resp.read().decode("utf-8"))

import json
from urllib.request import Request, urlopen

def get_todo(todo_id: int) -> dict:
    """封装的函数：根据 ID 获取待办事项，返回字典"""
    url = f"https://jsonplaceholder.typicode.com/todos/{todo_id}"
    req = Request(url, headers={"User-Agent": "Chrome/130.0.0.0"})
    
    with urlopen(req) as resp:
        if resp.status != 200:
            raise Exception(f"请求失败，状态码：{resp.status}")
        # 直接读取字节并解析为 JSON
        return json.loads(resp.read())

# 调用测试
try:
    todo = get_todo(2)
    print(f"任务标题：{todo['title']}")
    print(f"是否完成：{todo['completed']}")
except Exception as e:
    print(f"出错啦：{e}")

from urllib.request import ProxyHandler, build_opener, install_opener, urlopen

# 假设你的代理运行在 127.0.0.1:7890
PROXY = {
    "http": "http://127.0.0.1:7890",
    "https": "http://127.0.0.1:7890"
}

# 创建代理处理器
proxy_handler = ProxyHandler(PROXY)
# 构建一个 opener
opener = build_opener(proxy_handler)
# 全局安装（之后所有 urlopen 都走代理）
install_opener(opener)

# 测试：查看当前出口 IP
with urlopen("https://ifconfig.me/ip") as resp:
    print(f"代理后的 IP：{resp.read().decode('utf-8').strip()}")

import ssl
from urllib.request import urlopen

# 创建一个不验证证书的上下文
ctx = ssl._create_unverified_context()

# 测试一个著名的自签名站点
with urlopen("https://self-signed.badssl.com/", context=ctx) as resp:
    print(f"成功访问，状态码：{resp.status}")

from urllib.request import urlopen

try:
    with urlopen("https://httpbin.org/delay/10", timeout=5) as resp:
        print(resp.read().decode())
except Exception as e:
    print(f"超时或其它错误：{e}")

from urllib.request import Request, urlopen
from urllib.error import HTTPError, URLError
import socket

def safe_get(url: str, timeout: int = 10) -> str | None:
    """带完整exception-handling的 GET 请求函数"""
    req = Request(url, headers={"User-Agent": "Chrome/130.0.0.0"})
    
    try:
        with urlopen(req, timeout=timeout) as resp:
            return resp.read().decode("utf-8")
    except HTTPError as e:
        # 服务器返回了错误状态码（4xx, 5xx）
        print(f"HTTP 错误：{e.code} - {e.reason}")
        # 有时错误响应里也有内容，可以尝试读取 e.read()
        return None
    except URLError as e:
        # 网络层面的错误：DNS 解析失败、连接拒绝等
        if isinstance(e.reason, socket.timeout):
            print(f"请求超时（>{timeout}秒）")
        else:
            print(f"URL 错误：{e.reason}")
        return None
    except Exception as e:
        # 兜底：其他未知异常
        print(f"未知错误：{e}")
        return None

# 几个典型错误场景
safe_get("https://jsonplaceholder.typicode.com/todos/999999")  # 可能 404
safe_get("https://不存在的域名.com")          # URLError
safe_get("https://httpbin.org/delay/15", timeout=5)   # 超时

import requests

# GET + JSON 解析
todo = requests.get("https://jsonplaceholder.typicode.com/todos/1").json()
print(todo["title"])

# POST
resp = requests.post("https://jsonplaceholder.typicode.com/posts",
                     data={"username": "test", "password": "123"},
                     headers={"User-Agent": "Chrome/130.0.0.0"},
                     timeout=10)
print(resp.status_code)

from urllib.request import Request, urlopen
from urllib.error import HTTPError, URLError

def get_weather(city: str) -> str | None:
    """返回城市的精简天气信息（格式：城市: 天气 温度）"""
    url = f"https://wttr.in/{city}?format=3"   # ?format=3 返回一行文本
    req = Request(url, headers={"User-Agent": "curl/7.68.0"})
    
    try:
        with urlopen(req, timeout=10) as resp:
            return resp.read().decode("utf-8").strip()
    except HTTPError as e:
        print(f"城市名可能不存在（{e.code}）")
        return None
    except URLError as e:
        print(f"网络连接出错：{e.reason}")
        return None

if __name__ == "__main__":
    city_name = input("请输入城市名（拼音或英文）：")
    weather = get_weather(city_name)
    if weather:
        print(f"\n{weather}")