获取阿里通信170和171电话号码库(选号大数据)

获取阿里通信的号码库,一次执行下来获取7万多条可用的电话号码备选,从中选出优质的电话号码,选号必学...

# -*- coding:utf-8 -*-

import json

import pymysql

import requests

from bs4 import BeautifulSoup

import time

import HTMLParser

# import sys

# reload(sys)

# sys.setdefaultencoding('utf-8')

引入所需要的软件包

class aliqin:

def __init__(self):

pass

self.conn = pymysql.connect(host='localhost', port=3306, user='root', passwd='root', db='aliqin',

charset='utf8')

self.cur = self.conn.cursor()

def __del__(self):

pass

self.cur.close()

self.conn.close()

def fun_main(self):

for i in range(10, 99):

for n in range(1,9):

ty = ["TD-SCDMA","WCDMA"]

for t1 in ty:

provId = "%s0000" % i

cityId = "%s0%s00" % (i,n)

url = "http://wt.tmall.com/trade/detail/itemOp.do?itemId=39990583842&skuId=0&provId=%s&cityId=%s&planId=22317&network=%s&m=SelectNum" % (provId,cityId,t1)

print url

self.get_page_url(url,t1,provId,cityId)

# exit()

# exit()

使用面向对象的方法,

def __init__(self): 构造方法连接数据库

def __del__(self): 析构方法断开数据库

def fun_main(self): 设置入口函数,循环执行查询

url = "http://wt.tmall.com/trade/detail/itemOp.do?itemId=39990583842&skuId=0&provId=%s&cityId=%s&planId=22317&network=%s&m=SelectNum" % (provId,cityId,t1) 是天猫的选号地址

def get_page_url(self,url,t1,provId,cityId): 获取页面源码,解析数据,让可用的数据导入数据库

执行程序

# -*- coding:utf-8 -*-

import json

import pymysql

import requests

from bs4 import BeautifulSoup

import time

import HTMLParser

# import sys

# reload(sys)

# sys.setdefaultencoding('utf-8')

class aliqin:

def __init__(self):

pass

self.conn = pymysql.connect(host='localhost', port=3306, user='root', passwd='root', db='aliqin',

charset='utf8')

self.cur = self.conn.cursor()

def __del__(self):

pass

self.cur.close()

self.conn.close()

def fun_main(self):

for i in range(10, 99):

for n in range(1,9):

ty = ["TD-SCDMA","WCDMA"]

for t1 in ty:

provId = "%s0000" % i

cityId = "%s0%s00" % (i,n)

url = "http://wt.tmall.com/trade/detail/itemOp.do?itemId=39990583842&skuId=0&provId=%s&cityId=%s&planId=22317&network=%s&m=SelectNum" % (provId,cityId,t1)

print url

self.get_page_url(url,t1,provId,cityId)

# exit()

# exit()

# 获取页面源码

def get_page_url(self,url,t1,provId,cityId):

try:

# url = "http://wt.tmall.com/trade/detail/itemOp.do?itemId=39990583842&skuId=0&provId=140000&cityId=140100&planId=22317&network=WCDMA&m=SelectNum"

headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:22.0) Gecko/20100101 Firefox/22.0'}

res = requests.get(url, params=headers)

print res.encoding

json_res = json.loads(res.text)

for i in json_res:

print i,json_res[i]

if json_res['code'] == "0000":

print True

for i2 in json_res['data']:

print i2['phoneNum'],t1,provId,cityId

try:

sql = "INSERT INTO `aliqin` SET `telNum`='%s',`network`='%s',`provId`='%s',`cityId`='%s';" % (i2['phoneNum'],t1,provId,cityId)

self.cur.execute(sql)

self.conn.commit()

except BaseException as e:

print e

except BaseException as e:

print e

if __name__ == '__main__':

obj = aliqin()

obj.fun_main()

复制保存,就可用执行