python动态网页批量爬取

准考证号：

 
请输入15位准考证号

姓名：

 
姓名超过3个字，可只输入前3个


 
 

 

姓名：
XXXX

学校：
XXXXXX

考试类别：
英语四级

准考证号：
120135151100101

考试时间：
2015年06月总分：403 
听力： 132 
阅读： 147 
写作与翻译： 124 

from selenium import webdriver

driver = webdriver.PhantomJS(executable_path='D:\phantomjs-2.1.1-windows\phantomjs.exe')
driver.get(url)
driver.find_element_by_id('zkzh').send_keys(i)
driver.find_element_by_id('xm').send_keys(xm)
driver.find_elements_by_tag_name('form')[1].submit()

print driver.find_element_by_xpath("//tr[3]/td[1]").text
print driver.find_element_by_xpath("//tr[6]/td[1]").text

姓名
听力
阅读
写作

 import re
m = re.findall(r'(\w*[0-9]+)\w*', chuli2)

import MySQLdb

conn = MySQLdb.Connect(host='localhost', user='root', passwd='root', db='cet', port=3306, charset='utf8')
cur = conn.cursor()
curr = conn.cursor()
cur.execute("select name from cet.cet where zkzh=(%s)" % i)
xm = cur.fetchone()[0]
print "Name is " + xm
sqltxt = "update cet.cet set leibie=(%s),zongfen=(%s),tingli=(%s),yuedu=(%s),xiezuo=(%s) WHERE zkzh=(%s)" % (
  ss, m[0], m[1], m[2], m[3], i)
cur.execute(sqltxt)
conn.commit()
cur.close()
conn.close()

# encoding=utf8

import MySQLdb
import re
import time

from selenium import webdriver

# connect mysql,get zkxh and xm
conn = MySQLdb.Connect(host='localhost', user='root', passwd='root', db='cet', port=3306, charset='utf8')
cur = conn.cursor()
curr = conn.cursor()
url = 'http://www.chsi.com.cn/cet/query'


def kaishi(i):
 print i,
 print " start"
 try:
 cur.execute("select name from cet.cet where zkzh=(%s)" % i)
 xm = cur.fetchone()[0]
 print "Name is " + xm
 driver = webdriver.PhantomJS(executable_path='D:\phantomjs-2.1.1-windows\phantomjs.exe')
 driver.get(url)
 driver.find_element_by_id('zkzh').send_keys(i)
 driver.find_element_by_id('xm').send_keys(xm)
 driver.find_elements_by_tag_name('form')[1].submit()
 driver.set_page_load_timeout(10)
 leibie = driver.find_element_by_xpath("//tr[3]/td[1]").text
 leibie2 = str(leibie.encode("utf-8"))
 ss = ""
 if leibie2.decode("utf-8") == '英语四级'.decode("utf-8"):
  ss = 4
 else:
  ss = 6
 # zongfen = driver.find_element_by_xpath("//tr[6]/th[1]").text
 # print zongfen
 # print "===="
 chuli = driver.find_element_by_xpath("//tr[6]/td[1]").text
 print chuli
 chuli2 = str(chuli.encode("utf-8"))
 m = re.findall(r'(\w*[0-9]+)\w*', chuli2)
 sqltxt = "update cet.cet set leibie=(%s),zongfen=(%s),tingli=(%s),yuedu=(%s),xiezuo=(%s) WHERE zkzh=(%s)" % (
  ss, m[0], m[1], m[2], m[3], i)
 cur.execute(sqltxt)
 conn.commit()
 print str(i) + " finish"
 except Exception, e:
 print e
 driver.close()
 time.sleep(10)
 kaishi(i)


# for j1 in range(1201351511001, 1201351512154):
for j1 in range(1201351511007, 1201351512154):
 for j2 in range(0, 3):
 for j3 in range(0, 10):
  j = str(j1) + str(j2) + str(j3)
  if str(j2) + str(j3) == "00":
  print "0.0"
  elif str(j2) + str(j3) == "29":
  kaishi(str(j1) + str(j2) + str(j3))
  j4 = str(j1) + "30"
  kaishi(j4)
  else:
  kaishi(j)
print "END!!!"
cur.close()
conn.close()