杭州市机动车驾驶人考试互联网预约平台预约考试人员统计脚本

hzti.com.9004.py

#coding: utf-8

import requests,re

headers = {'User-Agent': 'Mozilla/4.0', 
'Accept-Language':'en-US,en;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Cache-Control': 'max-age=0',
'Accept': 'text/html;q=0.9,*/*;q=0.8'
}

result = dict()
pageindex, totalpage = 1, 0
while(True):
    # print 'page {}'.format(pageindex)
    data = {'currentPage':pageindex,'kskm':2,'pageSize':20,'ykrq':'2016-03-20'}
    r = requests.post("http://www.hzti.com:9004/drv_web/queryKsmd.do", data=data, headers=headers)
    html = re.sub('\r|\n', '', r.text)
    html = re.sub('\s{2,}', ' ', html)
    html = re.sub('>\s+<', '><', html)
    html = re.sub('\s*>', '>', html)
    html = re.sub('&nbsp;', '', html)
    r.close()
    s = re.findall('<tr onMouseOver="mouseover\(this\);" onMouseOut="mouseout\(this\);"><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td></tr>', html)
    if len(s) < 1:
        print 'redo', pageindex
        time.sleep(2)
        continue
    for x in s:
        #print x[0].strip(),x[1].strip(),x[2].strip()
        m = x[2].strip()
        n = x[3].strip()
        if not result.has_key(m):
            result[m] = dict()
        if not result[m].has_key(n):
            result[m][n] = 0
        result[m][n] = result[m][n]+1

    if totalpage < 1:
        s = re.findall(u'共(\d+)页', html)
        totalpage = int(s[0])

    if pageindex+1>totalpage:
        break
    pageindex = pageindex + 1
    time.sleep(0.8) 

print u'科目二 2016-03-20 统计结果：'
total = 0
for m in result:
    for n in result[m]:
        total = total + result[m][n]
        print "{:<20}{:<16}{}".format(m.encode('gbk'), n.encode('gbk'), result[m][n]), u'人'
print u'总共{}人'.format(total)