IP+IDC-chinaz抓取

#-*-coding:gbk-*-
#code by anyun.org
import urllib
import re
import time


def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    html = html.replace('
', '')
    html = html.replace('       ', ' ')
    html = html.replace('   ', '')
    html = html.replace('   ', '')
    # html = html.replace(' ','')
    return html


def getcontext(html):
    reg = (r'<span class="Whwtdhalf w15-0">(.*?)</span>')
    listre = re.compile(reg)
    mylist = re.findall(listre, html)
    return mylist

def getadd(html):
    reg = (r'<span class="Whwtdhalf w50-0">(.*?)</span>')
    listre = re.compile(reg)
    mylist = re.findall(listre, html)
    return mylist

def geterr(html):
    reg = (r'<div class="col-red lh30 fz14 jspu">(.*?)</div>')
    listre = re.compile(reg)
    mylist = re.findall(listre, html)
    return mylist

if __name__ == '__main__':
	f =open('list.txt','r')
	for i in f.readlines():
		i=i.strip()
		
		try:
			Url='http://ip.chinaz.com/?ip=http://'+i
		except:
			print 'error'
		Html = getHtml(Url)
	#	print (getcontext(Html))
		
		if len(geterr(Html))==0:
			print getcontext(Html)[0],getcontext(Html)[3] 
			,getcontext(Html)[1],getcontext(Html)[4] 
			,getcontext(Html)[2],getcontext(Html)[5] 
			,getadd(Html)[0],getadd(Html)[1]
			
			f1 = open('ok.txt','a')
			print >>f1,getcontext(Html)[0],getcontext(Html)[3] 
			,getcontext(Html)[1],getcontext(Html)[4] 
			,getcontext(Html)[2],getcontext(Html)[5] 
			,getadd(Html)[0],getadd(Html)[1]
			f1.close()
			
		else:
			print i,'解析失败'
			f2=open('err.txt','a')
			print >>f2,i,'解析失败'
			f2.close()
		time.sleep(0.5)
	print 'over'