深圳小汽车摇号结果采集

最新推荐文章于 2025-08-09 10:17:13 发布

转载最新推荐文章于 2025-08-09 10:17:13 发布 · 261 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/fer-team/p/10037422.html

文章标签：

#python

每月26号，是深圳小汽车增量摇号开始的日子，等摇号结束后，都要去看看自己有没有中签。以前微信没推出城市
服务的时候，都要自己去网站查询，又要输入自己的申请号，估计也没多少人知道。嫌麻烦，就开始写了一个采集
程序。很简单的功能。用了很久，现在不想维护了，先放在博客做个备忘。

#!/usr/bin/python  
# -*-coding:utf-8 -*-  
import urllib
import urllib2
import re

  
def main():
    url='http://apply.sztb.gov.cn/apply/app/status/norm/person'
    current_range='201801'
    total_pageNo=612
    values = {'pageNo': '1', 'issueNumber': current_range,'applyCode': ''}
    f = open('f'+current_range+'.txt', 'a')
    for num in range(1,total_pageNo):
        values["pageNo"]=num
        data = urllib.urlencode(values)
        req = urllib2.Request(url, data)
        response = urllib2.urlopen(req)
        content = response.read()
        r_Table = r'<table\s*class="ge2_content".*?</table>'
        id_re = re.compile(r_Table,re.S)
        tablecontent = id_re.search(content)
        tablecontent=tablecontent.group()
        print tablecontent

        r_id = r'<tr\s*class="content_data">.*?<td >(\d+)</td>.*?<td >(.*?)</td>.*?</tr>'
        id_re = re.compile(r_id,re.S)
        id_regx = id_re.findall(tablecontent)
        print  id_regx
        for tx in id_regx:
            v1=tx[0]
            v2=tx[1]
            f.write(v1+"  "+v2)
            f.write('\n')
    f.close()

if __name__ == "__main__":  
    main()

　　添加python3 的代码如下：

#!/usr/bin/python  
# -*-coding:utf-8 -*-  
import urllib
import urllib.request
import re

  
def main():
    url='http://apply.sztb.gov.cn/apply/app/status/norm/person'
    current_range='201812'
    total_pageNo=705
    values = {'pageNo': '1', 'issueNumber': current_range,'applyCode': ''}
    f = open('f'+current_range+'.txt', 'a')
    for num in range(1,total_pageNo):
        values["pageNo"]=num
        data =urllib.parse.urlencode(values).encode('utf-8')
        response = urllib.request.urlopen(url,data)
        content = response.read().decode("utf-8")
        r_Table = r'<table\s*class="ge2_content".*?</table>'
        id_re = re.compile(r_Table,re.S)
        tablecontent = id_re.search(content)
        tablecontent=tablecontent.group()
        print(tablecontent)

        r_id = r'<tr\s*class="content_data">.*?<td >(\d+)</td>.*?<td >(.*?)</td>.*?</tr>'
        id_re = re.compile(r_id,re.S)
        id_regx = id_re.findall(tablecontent)
        print(id_regx)
        for tx in id_regx:
            v1=tx[0]
            v2=tx[1]
            f.write(v1+"  "+v2)
            f.write('\n')
    f.close()

if __name__ == "__main__":  
    main()

转载于:https://www.cnblogs.com/fer-team/p/10037422.html