使用Python程序抓取新浪在国内的所有IP的教程

import re

 
def ipv3_to_int(s):
  l = [int(i) for i in s.split('.')]
  return (l[0] << 16) | (l[1] << 8) | l[2]

 
def int_to_ipv3(s):
  ip1 = s >> 16 & 0xFF
  ip2 = s >> 8 & 0xFF
  ip3 = s & 0xFF
  return "%d.%d.%d" % (ip1, ip2, ip3)

 
i = open('ChinaIPAddress.csv', 'r')
list = i.readlines()
for iplist in list:
  pattern = re.compile('(\d{1,3}\.\d{1,3}\.\d{1,3})\.\d{1,3}')
  ips = pattern.findall(iplist)
  x = ips[0]
  y = ips[1]
  for ip in range (ipv3_to_int(x),ipv3_to_int(y)):
    ipadress=str(ip)
    #ip_address = int_to_ipv3(ip)
    o = open('ChinaIPAddress.txt','a')
    o.writelines(ipadress)
    o.writelines('\n')
  o.close()
i.close()

#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib,urllib2, simplejson, sqlite3, time

 
def ipv3_to_int(s):
  l = [int(i) for i in s.split('.')]
  return (l[0] << 16) | (l[1] << 8) | l[2]

 
def int_to_ipv4(s):
  ip1 = s >> 16 & 0xFF
  ip2 = s >> 8 & 0xFF
  ip3 = s & 0xFF
  return "%d.%d.%d.0" % (ip1, ip2, ip3)

 
def fetch(ipv4, **kwargs):
  kwargs.update({
    'ip': ipv4,
    'format': 'json',
  })
  DATA_BASE = "http://int.dpool.sina.com.cn/iplookup/iplookup.php"
  url = DATA_BASE + '?' + urllib.urlencode(kwargs)
  print url
  fails = 0
  try:
    result = simplejson.load(urllib2.urlopen(url,timeout=20))
  except (urllib2.URLError,IOError):
    fails += 1
    if fails < 10:
      result = fetch(ipv4)
    else:
      sleep_download_time = 60*10
      time.sleep(sleep_download_time)
      result = fetch(ipv4)
  return result

 
def dbcreate():
  c = conn.cursor()
  c.execute('''create table ipdata(
    ip integer primary key,
    ret integer,
    start text,
    end text,
    country text,
    province text,
    city text,
    district text,
    isp text,
    type text,
    desc text
  )''')
  conn.commit()
  c.close()

 
def dbinsert(ip,address):
  c = conn.cursor()
  c.execute('insert into ipdata values(?,?,?,?,?,?,?,?,?,?,?)',(ip,address['ret'],address['start'],address['end'],address['country'],address['province'],address['city'],address['district'],address['isp'],address['type'],address['desc']))
  conn.commit()
  c.close()

 
conn = sqlite3.connect('ipaddress.sqlite3.db')
dbcreate()

 
i = open('ChinaIPAddress.txt','r')
list = [s.strip() for s in i.readlines()]
end = 0
for ip in list:
  ip = int(ip)
  if ip > end :
    ipaddress = int_to_ipv4(ip)
    info = fetch(ipaddress)
    if info['ret'] == -1:
      pass
    else:
      dbinsert(ip,info)
      end = ipv3_to_int(info['end'])
      print ip,end
  else :
    pass
i.close()