import urllib
r = urllib.urlopen('//www.dhdzp.com/')
datatLine = r.readline() #讀取html頁面的第一行
data=file.read() #讀取全部
f=open("./1.html","wb") # 網(wǎng)頁保存在本地
f.write(data)
f.close()

import urllib.request
import urllib.parse
url = 'https://passport.jb51.net/user/signin?'
post = {
'username': 'xxx',
'password': 'xxxx'
}
postdata = urllib.parse.urlencode(post).encode('utf-8')
req = urllib.request.Request(url, postdata)
r = urllib.request.urlopen(req)

import urllib.request
import urllib.parse
url = 'https://passport.jb51.net/user/signin?'
post = {
'username': 'xxx',
'password': 'xxxx'
}
postdata = urllib.parse.urlencode(post).encode('utf-8')
req = urllib.request.Request(url, postdata)
r = urllib.request.urlopen(req)

def use_proxy(proxy_addr,url):
import urllib.request
#構(gòu)建代理
proxy=urllib.request.ProxyHandler({'http':proxy_addr})
# 構(gòu)建opener對象
opener=urllib.request.build_opener(proxy,urllib.request.HTTPHandler)
# 安裝到全局
# urllib.request.install_opener(opener)
# data=urllib.request.urlopen(url).read().decode('utf8') 以全局方式打開
data=opener.open(url) # 直接用句柄方式打開
return data
proxy_addr='61.163.39.70:9999'
data=use_proxy(proxy_addr,'//www.dhdzp.com')
print(len(data))
## 異常處理以及日輸出

import http.cookiejar, urllib.request
#使用http.cookiejar.CookieJar()創(chuàng)建CookieJar對象
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
#使用HTTPCookieProcessor創(chuàng)建cookie處理器，并以其為參數(shù)構(gòu)建opener對象
opener = urllib.request.build_opener(handler)
#將opener安裝為全局
urllib.request.install_opener(opener)
response = urllib.request.urlopen('//www.dhdzp.com')
#response = opener.open('//www.dhdzp.com')
for item in cookie:
print 'Name = '+item.name
print 'Value = '+item.value

import cookielib
import urllib
#設(shè)置保存cookie的文件，同級目錄下的cookie.txt
filename = 'cookie.txt'
#聲明一個(gè)MozillaCookieJar對象實(shí)例來保存cookie，之后寫入文件
cookie = cookielib.MozillaCookieJar(filename)
#利用urllib庫的HTTPCookieProcessor對象來創(chuàng)建cookie處理器
handler = urllib.request.HTTPCookieProcessor(cookie)
#通過handler來構(gòu)建opener
opener = urllib.request.build_opener(handler)
#創(chuàng)建一個(gè)請求，原理同urllib2的urlopen
response = opener.open("http://www.dhdzp.com")
#保存cookie到文件
cookie.save(ignore_discard=True, ignore_expires=True)

try:
# 要執(zhí)行的代碼
print(...)
except:
#try代碼塊里的代碼如果拋出異常了，該執(zhí)行什么內(nèi)容
print(...)
else:
#try代碼塊里的代碼如果沒有跑出異常，就執(zhí)行這里
print(...)
finally:
#不管如何，finally里的代碼，是總會(huì)執(zhí)行的
print(...)

from urllib import request, error
try:
r=request.urlopen('//www.dhdzp.com')
except error.URLError as e:
print(e.reason)

from urllib imort request, error
try:
response = request.urlopen('//www.dhdzp.com')
except error.HTTPError as e:
print(e.reason, e.code, e.headers, sep='\n')
else:
print("Request Successfully')
# 加入 hasattr屬性提前對屬性,進(jìn)行判斷原因
from urllib import request,error
try:
response=request.urlopen('http://blog.jb51.net')
except error.HTTPError as e:
if hasattr(e,'code'):
print('the server couldn\'t fulfill the request')
print('Error code:',e.code)
elif hasattr(e,'reason'):
print('we failed to reach a server')
print('Reason:',e.reason)
else:
print('no exception was raised')
# everything is ok

import urllib.request
response = urllib.request.urlopen('http://jb51.net/')
html = response.read()

import urllib.request
req = urllib.request.Request('http://jb51.net/')
response = urllib.request.urlopen(req)
the_page = response.read()

#! /usr/bin/env python3
import urllib.parse
import urllib.request
url = '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', '//www.dhdzp.com/')
response = urllib.request.urlopen(req)
the_page = response.read()
print(the_page.decode("utf8"))

#! /usr/bin/env python3
import urllib.parse
import urllib.request
url = '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 python3
import urllib.request
req = urllib.request.Request('//www.dhdzp.com ')
try:
urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
print(e.code)
print(e.read().decode("utf8"))

#! /usr/bin/env python3
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("http://www.dhdzp.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"))

from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("http://www.dhdzp.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 python3
import urllib.request
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = "http://www.dhdzp.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 URL
a_url = "http://www.dhdzp.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 python3
import urllib.request
proxy_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.dhdzp.com ").read().decode("utf8")
print(a)

#! /usr/bin/env python3
import socket
import urllib.request
# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)
# this call to urllib.request.urlopen now uses the default timeout
# we have set in the socket module
req = urllib.request.Request('//www.dhdzp.com /')
a = urllib.request.urlopen(req).read()
print(a)

header=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36')]
#創(chuàng)建opener對象
opener=urllib.request.build_opener()
opener.addheaders=header
#設(shè)置opener對象作為urlopen()使用的全局opener
urllib.request.install_opener(opener)
response =urllib.request.urlopen('//www.dhdzp.com/')
buff = response.read()
html = buff .decode("utf8")
response.close()
print(the_page)

header=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36')]
#創(chuàng)建opener對象
opener=urllib.request.build_opener()
opener.addheaders=header
#設(shè)置opener對象作為urlopen()使用的全局opener
urllib.request.install_opener(opener)
#下載文件到當(dāng)前文件夾
urllib.request.urlretrieve('//www.dhdzp.com/','baidu.html')
#清除urlretrieve產(chǎn)生的緩存
urlib.resquest.urlcleanup()

import urllib.request
import urllib.parse
url='//www.dhdzp.com/mypost/'
#將數(shù)據(jù)使用urlencode編碼處理后，使用encode()設(shè)置為utf-8編碼
postdata=urllib.parse.urlencode({name:'測試名',pass:"123456"}).encode('utf-8')
#urllib.request.quote()接受字符串，
#urllib.parse.urlencode()接受字典或者列表中的二元組[(a,b),(c,d)],將URL中的鍵值對以連接符&劃分
req=urllib.request.Request(url,postdata)
#urllib.request.Request(url, data=None, header={}, origin_req_host=None, unverifiable=False, #method=None)
#url：包含URL的字符串。
#data：http request中使用，如果指定，則發(fā)送POST而不是GET請求。
#header：是一個(gè)字典。
#后兩個(gè)參數(shù)與第三方cookie有關(guān)。
req.add_header('user-agent','User-Agent', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/
537.36 (KHTML, like Gecko) Chrome/38.0.2125.122 Safari/537.36 SE 2.X MetaSr 1.0')
data=urllib.request.urlopen(req).read()
//urlopen（）的data參數(shù)默認(rèn)為None，當(dāng)data參數(shù)不為空的時(shí)候，urlopen（）提交方式為Post。

 import urllib.request
 import http.cookie
 # 聲明一個(gè)CookieJar對象實(shí)例來保存cookie
 cookie = cookielib.CookieJar()
 # 利用urllib庫的HTTPCookieProcessor對象來創(chuàng)建cookie處理器
 handler = urllib.request.HTTPCookieProcessor(cookie)
 # 通過handler來構(gòu)建opener
 opener = urllib.request.build_opener(handler)
 # 此處的open方法同urllib.request的urlopen方法，也可以傳入request
 urllib.request.install_opener(opener)
 #使用opener或者urlretrieve方法來獲取需要的網(wǎng)站cookie
 urllib.request.urlretrieve('//www.dhdzp.com/','baidu.html')
 # data=urllib.request.urlopen('//www.dhdzp.com/')

import http.cookie
import urllib.request
# 設(shè)置保存cookie的文件，同級目錄下的cookie.txt
filename = 'cookie.txt'
# 聲明一個(gè)MozillaCookieJar對象實(shí)例來保存cookie，之后寫入文件
cookie = http.cookie.MozillaCookieJar(filename)
# 利用urllib庫的HTTPCookieProcessor對象來創(chuàng)建cookie處理器
handler = urllib.request.HTTPCookieProcessor(cookie)
# 通過handler來構(gòu)建opener
opener = urllib.request.build_opener(handler)
# 創(chuàng)建一個(gè)請求，原理同urllib的urlopen
response = opener.open("http://www.dhdzp.com")
# 保存cookie到文件
cookie.save(ignore_discard=True, ignore_expires=True)

import http.cookielib
import urllib.request
# 創(chuàng)建MozillaCookieJar實(shí)例對象
cookie = http.cookie.MozillaCookieJar()
# 從文件中讀取cookie內(nèi)容到變量
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
# 創(chuàng)建請求的request
req = urllib.Request("http://www.dhdzp.com")
# 利用urllib的build_opener方法創(chuàng)建一個(gè)opener
opener = urllib.build_opener(urllib.request.HTTPCookieProcessor(cookie))
response = opener.open(req)
print (response.read())

import socket
#設(shè)置Socket連接超時(shí)時(shí)間,同時(shí)決定了urlopen的超時(shí)時(shí)間
socket.setdefaulttimeout(1)
import urllib.request
#代理服務(wù)器信息，http代理使用地址
startime = time.time()
#設(shè)置http和https代理
proxy=request.ProxyHandler({'https':'175.155.25.91:808','http':'175.155.25.91:808'})
opener=request.build_opener(proxy)
opener.addheaders=[('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0'),
# ("Accept","text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8"),
# ("Accept-Language", "zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3"),
# ("Accept-Encoding","gzip, deflate, br"),
# ("Connection","keep-alive"),
# ("Pragma","no-cache"),
# ("Cache-Control","no-cache")
  ]
request.install_opener(opener)
# data = request.urlopen('http://www.dhdzp.com/find-ip-address').read()
data = request.urlopen( 'http://www.ipip.net/' ).read().decode('utf-8')
# data=gzip.decompress(data).decode('utf-8','ignore')
endtime = time.time()
delay = endtime-startime
print(data)