初学python爬虫

几乎完全抄袭自http://blog.chinaunix.net/uid-23500957-id-3878767.html
由于chinaboywg博文中的代码不规整，写这篇是为了给自已看着方便
初学，懂的不多，见谅
#在百度音乐上搜super
import urllib
query = urllib.quote("super") 
url = ''+query  
response = urllib.urlopen(url)  
text = response.read()
print text
print url
print help(urllib.quote)

def url_get():  
import urllib  
params = urllib.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})  
f = urllib.urlopen("%s" % params)  
print f.read() 
url_get()

#代理IP
import urllib 
def url_proxy():  
    proxies = {'':''}   #or
    # proxies = {'':'211.167.112.14:80'}  
    opener = urllib.FancyURLopener(proxies)  
    f = opener.open("")  
    print f.read()



def url_post():  
import urllib  
params = urllib.urlencode({'spam': 1, 'eggs': 2, 'bacon': 0})  
f = urllib.urlopen("", params)  
print f.read()

#多个代理IP
import urllib 
def url_proxies():  
proxylist = (  '211.167.112.14:80',  '210.32.34.115:8080',  '115.47.8.39:80',  '211.151.181.41:80',  '219.239.26.23:80',  )  
for proxy in proxylist:  
proxies = {'': proxy}  
opener = urllib.FancyURLopener(proxies)  
f = opener.open("")  
print f.read()


url_proxies()

代理IP proxylist = (  '211.167.112.14:80',  '210.32.34.115:8080',  '115.47.8.39:80',  '211.151.181.41:80',  '219.239.26.23:80',  '219.157.200.18:3128',  '219.159.105.180:8080',  '1.63.18.22:8080',  '221.179.173.170:8080',  '125.39.66.153:80',  '125.39.66.151:80',  '61.152.108.187:80',  '222.217.99.153:9000',  '125.39.66.146:80',  '120.132.132.119:8080',  '119.7.221.137:82',  '117.41.182.188:8080',  '202.116.160.89:80',  '221.7.145.42:8080',  '211.142.236.131:80',  '119.7.221.136:80',  '211.151.181.41:80',  '125.39.66.131:80',  '120.132.132.119:8080',  '112.5.254.30:80',  '106.3.98.82:80',  '119.4.250.105:80',  '123.235.12.118:8080',  '124.240.187.79:80',  '182.48.107.219:9000',  '122.72.2.180:8080',  '119.254.90.18:8080',  '124.240.187.80:83',  '110.153.9.250:80',  '202.202.1.189:80',  '58.67.147.205:8080',  '111.161.30.228:80',  '122.72.76.130:80',  '122.72.2.180:80',  '202.112.113.7:80',  '218.108.85.59:81',  '211.144.72.154:80',  '119.254.88.53:8080',  '121.14.145.132:82',  '114.80.149.183:80',  '111.161.30.239:80',  '182.48.107.219:9000',  '122.72.0.28:80',  '125.39.68.131:80',  '118.244.190.6:80',  '120.132.132.119:88',  '211.167.112.15:82',  '221.2.80.126:8888',  '219.137.229.214:3128',  '125.39.66.131:80',  '61.181.22.157:80',  '115.25.216.6:80',  '119.7.221.137:82',  '221.195.42.195:8080',  '119.254.88.53:8080',  '219.150.254.158:8080',  '113.9.163.101:8080',  '222.89.154.14:9000',  '114.141.162.53:8080',  '218.5.74.199:3128',  '61.152.108.187:80',  '218.76.159.133:80',  '59.34.57.88:8080',  '118.244.190.34:80',  '59.172.208.189:8080',  '116.236.216.116:8080',  '111.161.30.233:80',  '220.248.237.234:8080',  '121.14.145.132:82',  '202.114.205.125:8080'  )

#用time.sleep()
import urllib 
import time
def url_proxies():  
proxylist = (  '211.167.112.14:80',  '210.32.34.115:8080',  '115.47.8.39:80',  '211.151.181.41:80',  '219.239.26.23:80',  )  
for proxy in proxylist:  
# time.sleep(5)
proxies = {'': proxy}  
opener = urllib.FancyURLopener(proxies)  
f = opener.open("")  
print f.read()
i =0
while i < 100:
time.sleep(5)
url_proxies()