文章目录
前言
编译环境:window10/pycharm
超级鹰打码的注册及导入pycharm请参考其他博主,此博客只是提供如何在爬虫代码中引用超级鹰的方法
项目代码(已测试运行无误)
#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
@author:${柒}
@file:验证码.py
@time:2022/03/27
"""
import requests
from lxml import etree
from hashlib import md5 #这个库是超级鹰要用到的所以需要导入
if __name__ == '__main__':
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36 Edg/99.0.1150.46'
}
#定义一个构造函数用于传参,用户名,密码,软件id可以固定为自己在平台申请的,传两个参数:验证码图片路径和验证码格式
def transform_image(img_path,img_type):
chaojiying = Chaojiying_Client('用户名', '密码', '软件id')
im = open(img_path, 'rb').read()
print("此刻验证码为:" + chaojiying.PostPic(im, img_type)['pic_str']) #输出此刻验证码
return chaojiying.PostPic(im,img_type)
#超级鹰平台的代码
class Chaojiying_Client(object):
def __init__(self, username, password, soft_id):
self.username = username
password = password.encode('utf8')
self.password = md5(password).hexdigest()
self.soft_id = soft_id
self.base_params = {
'user': self.username,
'pass2': self.password,
'softid': self.soft_id,
}
self.headers = {
'Connection': 'Keep-Alive',
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
}
def PostPic(self, im, codetype):
"""
im: 图片字节
codetype: 题目类型 参考 http://www.chaojiying.com/price.html
"""
params = {
'codetype': codetype,
}
params.update(self.base_params)
files = {'userfile': ('ccc.jpg', im)}
r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files,
headers=self.headers)
return r.json()
def ReportError(self, im_id):
"""
im_id:报错题目的图片ID
"""
params = {
'id': im_id,
}
params.update(self.base_params)
r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
return r.json()
#超级鹰平台的代码结束
#古诗文网登录界面验证码保存至本地的代码
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 #.encode('iso-8859-1')
tree = etree.HTML(page_text)
img_src='https://so.gushiwen.cn'+tree.xpath('//*[@id="imgCode"]/@src')[0]
img_data=requests.get(url=img_src,headers=headers).content
with open('验证码/code.jpg','wb') as fp:
fp.write(img_data) #保存验证码图片至本地
code_text=transform_image("验证码/code.jpg", '1902') #调用文首构造函数,进行传参,用户名,密码,软件id已固定,括号内是验证码图片路径和验证码格式自己修改
# print("此刻验证码为:"+code_text['pic_str']) #也可以在这里输出此刻验证码,不过我习惯在前面构造函数内已经加入了输出功能所以此处省略