python学习-爬虫

import urrlib2
response = urllib2.urlopen("http://www.baidu.com")
print response.read()

import urllib
import urllib2

values = {"username":"*****", "password":"*****"}
url = "   "
request = urllib2.Request(url,urllib.urlencode(values))
response = urllib2.urlopen(request)
print response.read()

import urllib
import urllib2

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

import urllib2
import urllib

values = {}
values["username"] =
values["password"] =
data = urlencode(values)
url =
geturl = url + "?" + data
request = urllib2.Request(geturl)
response = urllib2.urlopen(request)
print response.read()

import urllib2
enable_proxy = True
proxy_handler = urllib2.ProxyHandler({"http" : 'http://some-proxy.com:8080'})
null_proxy_handler = urllib2.ProxyHandler({})
if enable_proxy:
opener = urllib2.build_opener(proxy_handler)
else:
opener = urllib2.build_opener(null_proxy_handler)
urllib2.install_opener(opener)

import urllib2
response = urllib2.urlopen('http://www.baidu.com',data, 10)

import urllib2

req = urllib2.Request('http://blog.csdn.net/cqcre')
try:
urllib2.urlopen(req)
except urllib2.URLError, e:
if hasattr(e,"code"):
print e.code
if hasattr(e,"reason"):
print e.reason
else:
print "OK"

import urllib
import urllib2
import cookielib

filename = 'cookie.txt'
#声明一个MozillaCookieJar对象实例来保存cookie，之后写入文件
cookie = cookielib.MozillaCookieJar(filename)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
postdata = urllib.urlencode({
'stuid':'201200131012',
'pwd':'23342321'
})
#登录教务系统的URL
loginUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bks_login2.login'
#模拟登录，并把cookie保存到变量
result = opener.open(loginUrl,postdata)
#保存cookie到cookie.txt中
cookie.save(ignore_discard=True, ignore_expires=True)
#利用cookie请求访问另一个网址，此网址是成绩查询网址
gradeUrl = 'http://jwxt.sdu.edu.cn:7890/pls/wwwbks/bkscjcx.curscopre'
#请求访问成绩查询网址
result = opener.open(gradeUrl)
print result.read()