Python爬虫：urllib内置库基本使用

2022-02-06 12:42:29

可参考：

Urllib库的基本使用
官方文档：https://docs.python.org/3/library/urllib.html

urllib库包含以下模块

urllib.request 请求模块
urllib.error 异常处理模块
urllib.parse url解析模块
urllib.robotparser robots.txt解析模块

py2 vs. py3

python2
urllib.urlopen()

python3
urllin.request.urlopen()

用于http测试的网站：http://httpbin.org/

引入需要的模块

from urllib import request
from urllib import parse
from urllib import error
from http import cookiejar
import socket

request请求

请求url，请求参数，请求数据，请求头

urlopen

urlopen(url, data=None, timeout, *, cafile=None, 
    capath=None, cadefault=False, context=None)


# 发送get请求
def foo1():
    response = request.urlopen("http://www.baidu.com")
    # 字节 -> utf-8解码 -> 字符串
    print(response.read().decode("utf-8"))


# 发送post请求
def foo2():
    data = bytes(parse.urlencode({"word": "hello"}), encoding="utf-8")
    response = request.urlopen("http://httpbin.org/post", data=data)
    print(response.read())


# 设置超时时间并捕获异常
def foo3():
    try:
        response = request.urlopen("http://httpbin.org/post", timeout=0.1)
        print(response.read())
    except error.URLError as e:
        print(type(e.reason)) # <class 'socket.timeout'>
        if isinstance(e.reason, socket.timeout):
            print("超时错误：", e)

response响应


# 状态码，响应头
def foo4():
    response = request.urlopen("http://www.baidu.com")
    print(type(response))
    # from http.client import HTTPResponse
    # <class 'http.client.HTTPResponse'>

    print(response.status)
    print(response.getheaders())
    print(response.getheader("Server"))

Request请求对象

def foo5():
    req = request.Request("http://www.baidu.com")
    response = request.urlopen(req)
    print(response.read().decode("utf-8"))

# 带浏览器信息的请求1
def foo6():
    url = "http://httpbin.org/post"
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6)",
        "Host": "httpbin.org"
    }
    dct = {"name": "Tom"}

    data = bytes(parse.urlencode(dct), encoding="utf-8")
    req = request.Request(url=url, data=data, headers=headers)
    response = request.urlopen(req)
    print(response.read().decode("utf-8"))


# 带浏览器信息的请求2
def foo7():
    url = "http://httpbin.org/post"
    dct = {"name": "Tom"}
    data = bytes(parse.urlencode(dct), encoding="utf-8")

    req = request.Request(url=url, data=data, method="POST")
    req.add_header("User-Agent",
            "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6)")

    response = request.urlopen(req)

    print(response.read().decode("utf-8"))

代理


def foo8():
    proxy_handler = request.ProxyHandler({
        "http": "http://183.159.94.185:18118",
        "https": "https://183.159.94.187:18118",
        })
    opener = request.build_opener(proxy_handler)
    response = opener.open("http://www.baidu.com")
    print(response.read())

cookie


def foo9():
    cookie = cookiejar.CookieJar()
    cookie_handler = request.HTTPCookieProcessor(cookie)
    opener = request.build_opener(cookie_handler)
    response = opener.open("http://www.baidu.com")
    print(response.status)
    for item in cookie:
        print(item.name, item.value)

# 保存cookie1
def foo10():
    filename = "cookie.txt"
    cookie = cookiejar.MozillaCookieJar(filename)
    cookie_handler = request.HTTPCookieProcessor(cookie)
    opener = request.build_opener(cookie_handler)
    response = opener.open("http://www.baidu.com")
    cookie.save(ignore_discard=True, ignore_expires=True)

# 保存cookie2
def foo11():
    filename = "cookie1.txt"
    cookie = cookiejar.LWPCookieJar(filename)
    cookie_handler = request.HTTPCookieProcessor(cookie)
    opener = request.build_opener(cookie_handler)
    response = opener.open("http://www.baidu.com")
    cookie.save(ignore_discard=True, ignore_expires=True)

# 读取cookie
def foo12():
    filename = "cookie1.txt"
    cookie = cookiejar.LWPCookieJar()
    cookie.load(filename, ignore_discard=True, ignore_expires=True)
    cookie_handler = request.HTTPCookieProcessor(cookie)
    opener = request.build_opener(cookie_handler)
    response = opener.open("http://www.baidu.com")
    print(response.read().decode("utf-8"))

异常处理

error主要有：’URLError’, ‘HTTPError’, ‘ContentTooShortError’


def foo13():
    try:
        response = request.urlopen("http://www.xxooxxooxox.com/xxx")
        print(response.status)
    except error.HTTPError as e:  # 子类异常
        print(e.name, e.reason, e.code, e.headers, sep="\n")
    except error.URLError as e:  # 父类异常
        print(e.reason)
    else:
        print("successful")

parse 模块解析url

urlparse(url, scheme='', allow_fragments=True)


def foo14():
    result = parse.urlparse("http://www.baidu.com/xxx.html;user?id=5#comment")
    print(type(result), result, sep="\n")
    """
    <class 'urllib.parse.ParseResult'>
    ParseResult(scheme='http', netloc='www.baidu.com', path='/xxx.html', 
            params='user', query='id=5', fragment='comment')
    """

    # scheme 为默认协议信息 链接中协议信息优先
    result = parse.urlparse("www.baidu.com", scheme="https")
    print(result)
    """
    ParseResult(scheme='https', netloc='', path='www.baidu.com',
          params='', query='', fragment='')
    """

    result = parse.urlparse("http://www.baidu.com", scheme="https")
    print(result)
    """
    ParseResult(scheme='http', netloc='www.baidu.com', path='', 
            params='', query='', fragment='')
    """

    # allow_fragments 参数决定锚点拼接的位置
    result = parse.urlparse("http://www.baidu.com/xxx.html;user?id=5#comment",
                    allow_fragments=True)
    print(result)
    """
    ParseResult(scheme='http', netloc='www.baidu.com', path='/xxx.html', 
            params='user', query='id=5', fragment='comment')
    """

    result = parse.urlparse("http://www.baidu.com/xxx.html;user?id=5#comment",
                    allow_fragments=False)
    print(result)
    """
    ParseResult(scheme='http', netloc='www.baidu.com', path='/xxx.html', 
            params='user', query='id=5#comment', fragment='')

    """

    result = parse.urlparse("http://www.baidu.com/xxx.html;user#comment",
                    allow_fragments=False)
    print(result)
    """
    ParseResult(scheme='http', netloc='www.baidu.com', path='/xxx.html', 
            params='user#comment', query='', fragment='')

    """

# urlunparse 拼接url链接，注意顺序
def foo15():
    data = ["http", "www.baidu.com", "index.html", "user", "a=6", "comment"]
    print(parse.urlunparse(data))
    # http://www.baidu.com/index.html;user?a=6#comment

# urljoin 拼接url，类似os.path.join, 后者优先级高
def foo16():
    print(parse.urljoin("http://www.baidu.com", "index.html"))
    print(parse.urljoin("http://www.baidu.com", "http://www.qq.com/index.html"))
    print(parse.urljoin("http://www.baidu.com/index.html", "http://www.qq.com/?id=6"))
    """
    http://www.baidu.com/index.html
    http://www.qq.com/index.html
    http://www.qq.com/?id=6
    """

# urlencode将字典转为url中的参数形式
def foo17():
    params ={
        "name": "Tom",
        "age": 18
    }
    # 这里 ？ 没了
    url = parse.urljoin("http://www.baidu.com/?", parse.urlencode(params))
    print(url)
    # http://www.baidu.com/name=Tom&age=18

    url = "http://www.baidu.com/?" + parse.urlencode(params)
    print(url)
    # http://www.baidu.com/?name=Tom&age=18

码农公寓

urllib库包含以下模块

py2 vs. py3

引入需要的模块

request请求

urlopen

response响应

Request请求对象

代理

cookie

异常处理

parse 模块解析url

相关文章