Python3中使用urllib的方法详解(header,代理,超时,认证,异常处理)

import urllib.requestresponse = urllib.request.urlopen('http://python.org/')html = response.read()

import urllib.requestreq = urllib.request.Request('http://python.org/')response = urllib.request.urlopen(req)the_page = response.read()

#! /usr/bin/env python3import urllib.parseimport urllib.requesturl = 'http://localhost/login.php'user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'values = {'act' : 'login','login[email]' : 'yzhang@i9i8.com','login[password]' : '123456'}data = urllib.parse.urlencode(values)req = urllib.request.Request(url, data)req.add_header('Referer', 'http://www.python.org/')response = urllib.request.urlopen(req)the_page = response.read()print(the_page.decode("utf8"))

#! /usr/bin/env python3import urllib.parseimport urllib.requesturl = 'http://localhost/login.php'user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'values = {'act' : 'login','login[email]' : 'yzhang@i9i8.com','login[password]' : '123456'}headers = { 'User-Agent' : user_agent }data = urllib.parse.urlencode(values)req = urllib.request.Request(url, data, headers)response = urllib.request.urlopen(req)the_page = response.read()print(the_page.decode("utf8"))

#! /usr/bin/env python3import urllib.requestreq = urllib.request.Request('http://www.vevb.com ')try:urllib.request.urlopen(req)except urllib.error.HTTPError as e:print(e.code)print(e.read().decode("utf8"))

#! /usr/bin/env python3from urllib.request import Request, urlopenfrom urllib.error import URLError, HTTPErrorreq = Request("http://www.vevb.com /")try:response = urlopen(req)except HTTPError as e:print('The server couldn't fulfill the request.')print('Error code: ', e.code)except URLError as e:print('We failed to reach a server.')print('Reason: ', e.reason)else:print("good!")print(response.read().decode("utf8"))

#! /usr/bin/env python3from urllib.request import Request, urlopenfrom urllib.error import URLErrorreq = Request("http://www.vevb.com /")try:response = urlopen(req)except URLError as e:if hasattr(e, 'reason'):print('We failed to reach a server.')print('Reason: ', e.reason)elif hasattr(e, 'code'):print('The server couldn't fulfill the request.')print('Error code: ', e.code)else:print("good!")print(response.read().decode("utf8"))

#! /usr/bin/env python3import urllib.request# create a password managerpassword_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()# Add the username and password.# If we knew the realm, we could use it instead of None.top_level_url = "https://www.vevb.com /"password_mgr.add_password(None, top_level_url, 'rekfan', 'xxxxxx')handler = urllib.request.HTTPBasicAuthHandler(password_mgr)# create "opener" (OpenerDirector instance)opener = urllib.request.build_opener(handler)# use the opener to fetch a URLa_url = "https://www.vevb.com /"x = opener.open(a_url)print(x.read())# Install the opener.# Now all calls to urllib.request.urlopen use our opener.urllib.request.install_opener(opener)a = urllib.request.urlopen(a_url).read().decode('utf8')print(a)

#! /usr/bin/env python3import urllib.requestproxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})opener = urllib.request.build_opener(proxy_support)urllib.request.install_opener(opener)a = urllib.request.urlopen("http://www.vevb.com ").read().decode("utf8")print(a)

#! /usr/bin/env python3import socketimport urllib.request# timeout in secondstimeout = 2socket.setdefaulttimeout(timeout)# this call to urllib.request.urlopen now uses the default timeout# we have set in the socket modulereq = urllib.request.Request('http://www.vevb.com /')a = urllib.request.urlopen(req).read()print(a)