根据指定的手机号码，查询其归属地等相关信息，python实现：
手机号文件：phone.txt
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
|
18815484184
18818701639
18818773287
18818791154
18819026693
18820160604
18823376260
18823669247
18823834556
18824635390
18824722564
18824724252
18824728654
18824731004
18824734215
18824766242
18824932474
18825243001
18825255219
18825269277
18825276414
18825287578
18826014855
18826017814
18826532860
18826573310
18833526414
18837925448
18846911049
18875909323
18876361443
|
python实现：
# coding=UTF-8
# get provider information by phoneNumber
from urllib import urlopen
import re
# get html source code for url
def getPageCode(url):
file = urlopen(url)
text = file.read()
file.close()
# text = text.decode("utf-8") # depending on coding of source code responded
return text
# parse html source code to get provider information
def parseString(src, result):
pat = []
pat.append('(?<=归属地：</span>).+(?=<br />)')
pat.append('(?<=卡类型：</span>).+(?=<br />)')
pat.append('(?<=运营商：</span>).+(?=<br />)')
pat.append('(?<=区号：</span>)\d+(?=<br />)')
pat.append('(?<=邮编：</span>)\d+(?=<br />)')
item = []
for i in range(len(pat)):
m = re.search(pat[i], src)
if m:
v = m.group(0)
item.append(v)
return item
# get provider by phoneNum
def getProvider(phoneNum, result):
url = "http://www.sjgsd.com/n/?q=%s" %phoneNum
text = getPageCode(url)
item = parseString(text, result)
result.append((phoneNum, item))
# write result to file
def writeResult(result):
f = open("result.log", "w")
for num, item in result:
f.write("%s:\t" %num)
for i in item:
f.write("%s,\t" %i)
f.write("\n")
f.close()
if __name__ == "__main__":
result = []
for line in open("test.txt", "r"):
phoneNum = line.strip(" \t\r\n")
getProvider(phoneNum, result)
print("%s is finished" %phoneNum)
writeResult(result)
本文转自027ryan 51CTO博客，原文链接：http://blog.51cto.com/ucode/1735183，如需转载请自行联系原作者
