1.爬蟲入門程式

import cookielib

import urllib2

url = "http://www.baidu.com"

response1 = urllib2.urlopen(url)

2.爬蟲程式新增data、header，然後post請求

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()

3.爬蟲程式新增cookie

import cookielib

import urllib2

#設定儲存cookie的檔案，同級目錄下的cookie.txt

filename = 'cookie.txt'

#宣告一個MozillaCookieJar物件例項來儲存cookie，之後寫入檔案

cookie = cookielib.MozillaCookieJar(filename)

#利用urllib2庫的HTTPCookieProcessor物件來建立cookie處理器

handler = urllib2.HTTPCookieProcessor(cookie)

#通過handler來構建opener

opener = urllib2.build_opener(handler)

4.正則表示式

import re

# 將正則表示式編譯成Pattern物件

pattern = re.compile(r'xxxxx')

paxg=re.match(patter,"xxxx")

print(paxg)