JAVA高级面试进阶训练营视频教程

admin

仅仅列出我用到的，不全。

 

划重点：

　　1. urllib2 用 urllib.request 代替

　　2. urllib.urlencode 用 urllib.parse.urlencode 代替

　　3. cookielib 用 http.cookiejar 代替

　　4. print " "  用 print(" ") 代替

　　5. urllib2.URLError 用 urllib.error.URLError 代替

　　6. urllib2.HTTPError 用 urllib.error.HTTPError 代替

　　7. except urllib2.URLError, e:  用  except urllib.error.URLError as e: 代替

 

在python3.4.3自带的IDLE中写代码，经常出现缩进错误，很难查找。

解决方案：拷贝到Notepad++里面，视图中显示空格和制表符，就可以明显看出问题在哪了。

 

 

设置了header的网络请求，在Python2.x中的写法

import urllib  
import urllib2  

url = 'http://www.server.com/login'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'  
values = {'username' : 'kzy',  'password' : '123' }  
headers = { 'User-Agent' : user_agent }  
data = urllib.urlencode(values)  
request = urllib2.Request(url, data, headers)  
response = urllib2.urlopen(request)  
page = response.read() 

 

在Python3.x中的写法

import urllib.parse
import urllib.request

url = 'http://www.baidu.com'
user_agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.93 Safari/537.36'
values = {'username':'kzy','password':'123'}
headers = {'User-Agent':user_agent}
data = urllib.parse.urlencode(values).encode(encoding='UTF8') #这里要指明编码方式
request = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(request)
page = response.read()

 

 

我在学习静觅的爬虫教程，照着把里面的基础部分的代码都写了一遍。

教程地址：http://cuiqingcai.com/1052.html

 

里面原本的代码都是2.x的，我全部用3.x学着写了一遍。如下：

import urllib.parse
import urllib.request

"""
response = urllib.request.urlopen("http://www.baidu.com")
print(response.read())
"""


"""
#设置了header和data的请求

url = 'http://www.baidu.com'
user_agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.93 Safari/537.36'
values = {'username':'kzy','password':'123'}

headers = {'User-Agent':user_agent}

data = urllib.parse.urlencode(values).encode(encoding='UTF8')

request = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(request)

page = response.read()
"""



"""
#设置代理  避免因为某个IP的访问次数过多导致的禁止访问
enable_proxy = True
proxy_handler = urllib.request.ProxyHandler({"http":'http://some-proxy.com:8080'})

null_proxy_handler = urllib.request.ProxyHandler({})

if enable_proxy:
    opener = urllib.request.build_opener(proxy_handler)
else:
    opener = urllib.request.build_opener(null_proxy_handler)


urllib.request.install_opener(opener)    
       
"""


"""

#设置Timeout
response = urllib.request.urlopen('http://www.baidu.com', timeout = 10)
"""


"""
#使用http的 put或delete方法
url = 'http://www.baidu.com'
request = urllib.request.Request(url, data=data)
request.get_method = lambda:'PUT' #or 'DELETE'
response = urllib.request.urlopen(request)
"""


"""
#使用DebugLog 把收发包的内容在屏幕上打印出来 方便调试
httpHandler = urllib.request.HTTPHandler(debuglevel=1)

httpsHandler = urllib.request.HTTPSHandler(debuglevel=1)
opener = urllib.request.build_opener(httpHandler, httpsHandler)

urllib.request.install_opener(opener)
response = urllib.request.urlopen('https://its.pku.edu.cn/netportal/netportal_UTF-8.jsp', timeout = 5)
"""


"""
#URLError异常处理

from urllib.error import URLError, HTTPError
request = urllib.request.Request('http://www.baidu.com')
try:
    urllib.request.urlopen(request, timeout = 5)
except HTTPError as e:
    print('Error code:', e.code)
except URLError as e:
    
       print('Reason:', e.reason)
"""


"""
#URLError异常处理 属性判断
request = urllib.request.Request('https://its.pku.edu.cn/netportal/netportal_UTF-8.jsp')
try:
    urllib.request.urlopen(request, timeout = 5)
except urllib.error.URLError as e:
    if hasattr(e, "code"):     #hasattr 判断变量是否有某个属性
        print(e.code)
    if hasattr(e, "reason"):        
        print(e.reason) 
else:
    print("OK")
"""


"""
#获取cookie保存到变量
import http.cookiejar
#声明一个CookieJar对象实例来保存cookie
cookie = http.cookiejar.CookieJar()
#利用HTTPCookieProcessor对象来创建cookie处理器
handler = urllib.request.HTTPCookieProcessor(cookie)
#通过handler来构建opener
opener = urllib.request.build_opener(handler)
#此处的open方法同urlopen
response = opener.open('https://its.pku.edu.cn/netportal/netportal_UTF-8.jsp')
for item in cookie:
    print('Name = '+item.name)
    print('Value = '+item.value)
"""


"""

#获取cookie保存到文件

import http.cookiejar

#设置保存的文件

filename = 'cookie.txt'

#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = http.cookiejar.MozillaCookieJar(filename)

#创建cookie处理器

handler = urllib.request.HTTPCookieProcessor(cookie)
#构建opener

opener = urllib.request.build_opener(handler)



response = opener.open("https://its.pku.edu.cn/netportal/netportal_UTF-8.jsp")

#保存到cookie文件

cookie.save(ignore_discard=True,ignore_expires=True)
"""

"""
#从文件中获取cookie并访问

import http.cookiejar

#创建MozillaCookieJar实例对象

cookie = http.cookiejar.MozillaCookieJar()

#从文件中读取cookie内容到变量

cookie.load('cookie.txt',ignore_discard=True,ignore_expires=True)

#创建请求的request
req = urllib.request.Request('https://its.pku.edu.cn/netportal/netportal_UTF-8.jsp')
#创建opener

opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie))
response = opener.open(req)
print(response.read())
"""

#模拟登陆 登陆不成功 
import http.cookiejar

filename = 'cookie.txt'
cookie = http.cookiejar.MozillaCookieJar(filename)
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie))
postdata = urllib.parse.urlencode({'stuid':'******','pwd':'******'}).encode(encoding='UTF8') #这里怎么知道名字分别是stuid和pwd呢？？？
loginUrl = 'http://xxxxxx.com'
result = opener.open(loginUrl, postdata)
cookie.save(ignore_discard=True, ignore_expires=True)
gradeUrl='http://xxxxxx.com'
result = opener.open(gradeUrl)
print(result.read())