Python爬虫爬验证码实现功能详解

<code class="hljs python">from selenium.webdriver.support.ui import Select, WebDriverWait
from selenium import webdriver
from selenium import common
from PIL import Image
import pytesser
import sys
reload(sys)
sys.setdefaultencoding('utf8')
broswer = webdriver.Chrome()
broswer.maximize_window()
username = 'test'
password = 'test'
url = 'http://graduate.buct.edu.cn'
broswer.get(url)</code>

<code class="hljs livecodeserver">url = 'http://graduate.buct.edu.cn'
broswer.get(url)
wait = WebDriverWait(webdriver,5) #设置超时时间5s
# 在这里输入表单填写并加载的代码
elm = wait.until(lambda webdriver: broswer.find_element_by_xpath(xpathMenuCheck))</code>

<code class="hljs sql">select = Select(broswer.find_element_by_id('UserRole'))
select.select_by_value('2')
name = broswer.find_element_by_id('username')
name.send_keys(username)
pswd = broswer.find_element_by_id('password')
pswd.send_keys(password)
btnlg = broswer.find_element_by_id('btnLogin')
btnlg.click()</code>

<code class="hljs perl">//*[@id="dgData00"]/tbody/tr/td[2] （前面是xpath）</code>

<code class="hljs axapta"># 寻找有效报告
flag = 1
count = 2
count_valid = 0
while flag:
  try:
    category = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(count) + ']/td[1]').text
    count += 1
  except common.exceptions.NoSuchElementException:
    break
# 获取报告信息
flag = 1
for currentLecture in range(2, count):
  # 类别
  category = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(currentLecture) + ']/td[1]').text
  # 名称
  name = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(currentLecture) + ']/td[2]').text
  # 单位
  unitsPublish = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(currentLecture) + ']/td[3]').text
  # 开始时间
  startTime = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(currentLecture) + ']/td[4]').text
  # 截止时间
  endTime = broswer.find_element_by_xpath('//*[@id="dgData00"]/tbody/tr[' + str(currentLecture) + ']/td[5]').text</code>

<code class="hljs livecodeserver"># 获取验证码并验证（仅仅一幅）
authCodeURL = broswer.find_element_by_xpath('//*[@id="Table2"]/tbody/tr[2]/td/p/img').get_attribute('src') # 获取验证码地址
broswer.get(authCodeURL)
broswer.save_screenshot('text.png')
rangle = (0, 0, 64, 28)
i = Image.open('text.png')
frame4 = i.crop(rangle)
frame4.save('authcode.png')
qq = Image.open('authcode.png')
text = pytesser.image_to_string(qq).strip()</code>
<code class="hljs axapta"># 批量获取验证码
authCodeURL = broswer.find_element_by_xpath('//*[@id="Table2"]/tbody/tr[2]/td/p/img').get_attribute('src') # 获取验证码地址
# 获取学习样本
for count in range(10):
  broswer.get(authCodeURL)
  broswer.save_screenshot('text.png')
  rangle = (1, 1, 62, 27)
  i = Image.open('text.png')
  frame4 = i.crop(rangle)
  frame4.save('authcode' + str(count) + '.png')
  print 'count:' + str(count)
  broswer.refresh()
broswer.quit()</code>