python爬虫笔记（二）：urllib基础了解

1.什么是Urllib    Python内置的HTTP请求库
    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
2.urlopen:访问网页
    #直接打开网页
    response = urllib.request.urlopen('http://www.baidu.com')
    #post请求网页
    data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf8')
    response = urllib.request.urlopen('http://httpbin.org/post', data=data)
    #设定请求时间
    response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
    #超出响应时间报错
    try:
        response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1)
    except urllib.error.URLError as e:
        if isinstance(e.reason, socket.timeout):
            print('TIME OUT')
3.响应
    response = urllib.request.urlopen('https://www.python.org')
    #响应类型
    print(type(response))
    #状态码
    print(response.status)
    #响应头
    print(response.getheaders())
    #服务器
    print(response.getheader('Server'))
    #响应内容
    print(response.read().decode('utf-8'))
4.Request：通过构造一个request访问
    #构造一个带有url的request通过urlopen访问
    request = urllib.request.Request('https://python.org')
    response = urllib.request.urlopen(request)
    print(response.read().decode('utf-8'))
    #这是一个内容全面的request
    url = 'http://httpbin.org/post'
    headers = {
        'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
        'Host': 'httpbin.org'
    }
    dict = {
        'name': 'Germey'
    }
    data = bytes(parse.urlencode(dict), encoding='utf8')
    req = request.Request(url=url, data=data, headers=headers, method='POST')
    response = request.urlopen(req)
    print(response.read().decode('utf-8'))
    #补充request的响应头，add_header可多次调用
    url = 'http://httpbin.org/post'
    dict = {
        'name': 'Germey'
    }
    data = bytes(parse.urlencode(dict), encoding='utf8')
    req = request.Request(url=url, data=data, method='POST')
    req.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
    response = request.urlopen(req)
    print(response.read().decode('utf-8'))
5.Handler
    #代理访问
    proxy_handler = urllib.request.ProxyHandler({
        'http': 'http://',
        'https': 'https://'
    })
    opener = urllib.request.build_opener(proxy_handler)
    response = opener.open('http://httpbin.org/get')
    print(response.read())
    #cookie:维持登录状态
    #获取cookie
    cookie = http.cookiejar.CookieJar()
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    response = opener.open('http://www.baidu.com')
    for item in cookie:
        print(item.name+"="+item.value)
    #保存cookie到文件里
    filename = "cookie.txt"
    cookie = http.cookiejar.MozillaCookieJar(filename)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    response = opener.open('http://www.baidu.com')
    cookie.save(ignore_discard=True, ignore_expires=True)
    #另一种保存方式
    filename = 'cookie.txt'
    cookie = http.cookiejar.LWPCookieJar(filename)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    response = opener.open('http://www.baidu.com')
    cookie.save(ignore_discard=True, ignore_expires=True)
    #读取cookie
    cookie = http.cookiejar.LWPCookieJar()
    cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
    handler = urllib.request.HTTPCookieProcessor(cookie)
    opener = urllib.request.build_opener(handler)
    response = opener.open('http://www.baidu.com')
    print(response.read().decode('utf-8'))
6.异常处理
    #抛出异常
    try:
        response = request.urlopen('http://cuiqingcai.com/index.htm')
    except error.HTTPError as e:
        print(e.reason, e.code, e.headers, sep=' ')
    except error.URLError as e:
        print(e.reason)
    else:
        print('Request Successfully')
    #判断异常
    try:
        response = urllib.request.urlopen('https://www.baidu.com', timeout=0.01)
    except urllib.error.URLError as e:
        print(type(e.reason))
        if isinstance(e.reason, socket.timeout):
            print('TIME OUT')
7.url解析
    #urlparse
    urllib.parse.urlparse(urlstring, scheme='', allow_fragments=True)
    #urlunparse构造一个url
    data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
    print(urlunparse(data))
    #urljoin拼接新的url，以后一个为基准，用前一个url补足后一个url
    print(urljoin('http://www.baidu.com', 'FAQ.html'))
    print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/FAQ.html'))
    print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html'))
    print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html?question=2'))
    print(urljoin('http://www.baidu.com?wd=abc', 'https://cuiqingcai.com/index.php'))
    print(urljoin('http://www.baidu.com', '?category=2#comment'))
    print(urljoin('www.baidu.com', '?category=2#comment'))
    print(urljoin('www.baidu.com#comment', '?category=2'))
    #urlcode组合url
    params = {
        'name': 'germey',
        'age': 22
    }
    base_url = 'http://www.baidu.com?'
    url = base_url + urlencode(params)
    print(url)