古诗文网验证码识别

Posted 2020-12-18 gerenboke

#!/usr/bin/python

import requests 
from lxml import etree 
from codeClass import YDMHTTP

#封装识别验证码图片的函数
def getCodeText(imgPath,codeType):
    pass


#将验证码下载到本地

    headers = {
        ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (Khtml, like Gecko) Chrome/47.0.2626.106 Safari/537.36‘
    }
    url = ‘https://so.gushiwen.cn/user/login.aspx?from=http://so.gushiwen.cn/user/collect.aspx‘
    page_text = requests.get(url=url,headers=headers).text
    #解析验证码图片img中的src属性
    page_text = etree.HTML(page_text)
    code_img_src = ‘https://so.gushiwen.org‘+tree.xpath(‘//*[@id="imgCode"]/@src‘)[0]
    img_data = requests.get(url=code_img_src,headers=headers).content
    #将验证码图片保存到了本地

    with open(‘./code.jpg‘,‘wb‘) as fp:
        fp.write(img_data)

    #调用打码平台对应程序进行识别
    code_text = getCodeText(‘code.jpg‘,1004)
    print(‘识别结果为：‘,code_text)