#無論哪種方法，先導(dǎo)包
import urllib.request

'''
urllib.request.urlopen(url, data, timeout) 發(fā)送request請求（3個參數(shù)不需都寫，但必須有url）
url：目標(biāo)網(wǎng)址
data：訪問url時發(fā)送的數(shù)據(jù)包，默認為null
timeout：等待時長
'''
response = urllib.request.urlopen('http://www.baidu.com/')
# decode()：解碼，將字節(jié)流格式數(shù)據(jù)以相應(yīng)的形式轉(zhuǎn)化為字符串
print(response.read().decode('utf-8'))

'''
urllib.request.urlretrieve(url,filename) 直接將目標(biāo)網(wǎng)址的網(wǎng)頁信息保存到本地
filename：想保存到的路徑文件名
然后用urllib.request.urlcleanup()清除緩存
'''
filename = urllib.request.urlretrieve('http://www.baidu.com/',filename='baidu.html')
urllib.request.urlcleanup()

# 定義關(guān)鍵詞
keyword = input('輸入你想查詢的關(guān)鍵詞:')
# 處理中文，進行編碼，轉(zhuǎn)成字節(jié)流格式
keyword = urllib.request.quote(keyword)
# url重構(gòu)
url = 'http://www.baidu.com/s?wd='+keyword
response = urllib.request.urlopen(url).read()
# 保存到本地
f = open('baidu_search.html','wb') #wb存儲字節(jié)流數(shù)據(jù)，所以上述response不需要用decode解碼
f.write(response)
f.close()

import urllib.request
import urllib.parse #上傳用戶名和密碼，需要先用parse模塊進行編碼處理
url = 'https://www.iqianyue.com/mypost/'
# urlencode():將上傳的數(shù)據(jù)進行編碼處理
# encode():將字符串轉(zhuǎn)化為相應(yīng)編碼的字節(jié)流數(shù)據(jù)
postdata = urllib.parse.urlencode({
    'name':'vicky',
    'pass':'12345'
}).encode('utf-8')
response = urllib.request.urlopen(url,data=postdata).read()
# 保存網(wǎng)頁
f = open('post.html','wb')
f.write(response)
f.close()

import urllib.request
import urllib.parse
# 主頁面：'http://blog.chinaunix.net/'
# 登錄頁面：'http://account.chinaunix.net/login?url=http%3a%2f%2fblog.chinaunix.net'
# 登錄跳轉(zhuǎn)頁面：'http://account.chinaunix.net/login/sso?url=http%3A%2F%2Fblog.chinaunix.net'
url = 'http://account.chinaunix.net/login/sso?url=http%3A%2F%2Fblog.chinaunix.net'
postdata = urllib.parse.urlencode({
    'username':'***',
    'password':'******'
}).encode('utf-8')
response = urllib.request.urlopen(url,postdata).read()
f = open('chinaunix.html','wb')
f.write(response)
f.close()

import urllib.request
import urllib.parse
import http.cookiejar
url = 'http://account.chinaunix.net/login/sso?url=http%3A%2F%2Fblog.chinaunix.net'
postdata = urllib.parse.urlencode({
    'username':'***',
    'password':'***'
}).encode('utf-8')
response = urllib.request.urlopen(url,postdata).read()
# 創(chuàng)建cookiejar對象
cjar = http.cookiejar.CookieJar()
# 創(chuàng)建cookie處理器，并以此為參數(shù)構(gòu)建opener對象
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cjar))
# 加載為全局默認的opener
urllib.request.install_opener(opener)
f = open('chinaunix_2.html','wb')
f.write(response)
f.close()

import urllib.request
url = 'http://t.dianping.com/hangzhou'
# 構(gòu)建headers
h = {
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'
}
# 構(gòu)建Request請求對象
request = urllib.request.Request(url=url, headers=h)
response = urllib.request.urlopen(request).read()
# 保存文件
f = open('headers.html','wb')
f.write(response)
f.close()

import urllib.request
def use_Proxy(proxy_addr,url):
    # ProxyHandler()設(shè)置對應(yīng)的代理服務(wù)器信息
    proxy = urllib.request.ProxyHandler({'http':proxy_addr})
    # build_opener()創(chuàng)建一個自定義的opener對象
    opener = urllib.request.build_opener(proxy)
    # 將opener加載為全局使用的opener
    urllib.request.install_opener(opener)
    response = urllib.request.urlopen(url).read().decode('utf-8')
    return response
proxy_addr = '183.146.213.157:80'  # IP地址:端口號  自行百度“代理IP”
url = 'http://www.taobao.com'
print(len(use_Proxy(proxy_addr,url)))  #隨便打印一個長度，看看這個代理IP能否使用

import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen('http://www.ijinqian.com')
except urllib.error.URLError as e:
    print('發(fā)生異常--->'+str(e))