时间:2020-07-27 python教程 查看: 1051
需求分析
项目上需要用到手机号前7位,判断号码是否合法,还有归属地查询。旧的数据是几年前了太久了,打算用python爬虫重新爬一份
单线程版本
# coding:utf-8
import requests
from datetime import datetime
class PhoneInfoSpider:
def __init__(self, phoneSections):
self.phoneSections = phoneSections
def phoneInfoHandler(self, textData):
text = textData.splitlines(True)
# print("text length:" + str(len(text)))
if len(text) >= 9:
number = text[1].split('\'')[1]
province = text[2].split('\'')[1]
mobile_area = text[3].split('\'')[1]
postcode = text[5].split('\'')[1]
line = "number:" + number + ",province:" + province + ",mobile_area:" + mobile_area + ",postcode:" + postcode
line_text = number + "," + province + "," + mobile_area + "," + postcode
print(line_text)
# print("province:" + province)
try:
f = open('./result.txt', 'a')
f.write(str(line_text) + '\n')
except Exception as e:
print(Exception, ":", e)
def requestPhoneInfo(self, phoneNum):
try:
url = 'https://tcc.taobao.com/cc/json/mobile_tel_segment.htm?tel=' + phoneNum
response = requests.get(url)
self.phoneInfoHandler(response.text)
except Exception as e:
print(Exception, ":", e)
def requestAllSections(self):
# last用于接上次异常退出前的号码
last = 0
# last = 4
# 自动生成手机号码,后四位补0
for head in self.phoneSections:
head_begin = datetime.now()
print(head + " begin time:" + str(head_begin))
# for i in range(last, 10000):
for i in range(last, 10):
middle = str(i).zfill(4)
phoneNum = head + middle + "0000"
self.requestPhoneInfo(phoneNum)
last = 0
head_end = datetime.now()
print(head + " end time:" + str(head_end))
if __name__ == '__main__':
task_begin = datetime.now()
print("phone check begin time:" + str(task_begin))
# 电信,联通,移动,虚拟运营商
dx = ['133', '149', '153', '173', '177', '180', '181', '189', '199']
lt = ['130', '131', '132', '145', '146', '155', '156', '166', '171', '175', '176', '185', '186', '166']
yd = ['134', '135', '136', '137', '138', '139', '147', '148', '150', '151', '152', '157', '158', '159', '172',
'178', '182', '183', '184', '187', '188', '198']
add = ['170']
all_num = dx + lt + yd + add
# print(all_num)
print(len(all_num))
# 要爬的号码段
spider = PhoneInfoSpider(all_num)
spider.requestAllSections()
task_end = datetime.now()
print("phone check end time:" + str(task_end))
发现爬取一个号段,共10000次查询,单线程版大概要多1个半小时,太慢了。
多线程版本
# coding:utf-8
import requests
from datetime import datetime
import queue
import threading
threadNum = 32
class MyThread(threading.Thread):
def __init__(self, func):
threading.Thread.__init__(self)
self.func = func
def run(self):
self.func()
def requestPhoneInfo():
global lock
while True:
lock.acquire()
if q.qsize() != 0:
print("queue size:" + str(q.qsize()))
p = q.get() # 获得任务
lock.release()
middle = str(9999 - q.qsize()).zfill(4)
phoneNum = phone_head + middle + "0000"
print("phoneNum:" + phoneNum)
try:
url = 'https://tcc.taobao.com/cc/json/mobile_tel_segment.htm?tel=' + phoneNum
# print(url)
response = requests.get(url)
# print(response.text)
phoneInfoHandler(response.text)
except Exception as e:
print(Exception, ":", e)
else:
lock.release()
break
def phoneInfoHandler(textData):
text = textData.splitlines(True)
if len(text) >= 9:
number = text[1].split('\'')[1]
province = text[2].split('\'')[1]
mobile_area = text[3].split('\'')[1]
postcode = text[5].split('\'')[1]
line = "number:" + number + ",province:" + province + ",mobile_area:" + mobile_area + ",postcode:" + postcode
line_text = number + "," + province + "," + mobile_area + "," + postcode
print(line_text)
# print("province:" + province)
try:
f = open('./result.txt', 'a')
f.write(str(line_text) + '\n')
except Exception as e:
print(Exception, ":", e)
if __name__ == '__main__':
task_begin = datetime.now()
print("phone check begin time:" + str(task_begin))
dx = ['133', '149', '153', '173', '177', '180', '181', '189', '199']
lt = ['130', '131', '132', '145', '155', '156', '166', '171', '175', '176', '185', '186', '166']
yd = ['134', '135', '136', '137', '138', '139', '147', '150', '151', '152', '157', '158', '159', '172', '178',
'182', '183', '184', '187', '188', '198']
all_num = dx + lt + yd
print(len(all_num))
for head in all_num:
head_begin = datetime.now()
print(head + " begin time:" + str(head_begin))
q = queue.Queue()
threads = []
lock = threading.Lock()
for p in range(10000):
q.put(p + 1)
print(q.qsize())
for i in range(threadNum):
middle = str(i).zfill(4)
global phone_head
phone_head = head
thread = MyThread(requestPhoneInfo)
thread.start()
threads.append(thread)
for thread in threads:
thread.join()
head_end = datetime.now()
print(head + " end time:" + str(head_end))
task_end = datetime.now()
print("phone check end time:" + str(task_end))
多线程版的1个号码段1000条数据,大概2,3min就好,cpu使用飙升,大概维持在70%左右。
总共40多个号段,爬完大概1,2个小时,总数据41w左右
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持python博客。