python爬虫学习(十六)古诗文网验证码识别

先注册云打码,再去开发者模式下载pythonhttp示例代码

# -*- coding: utf-8 -*-
import requests
from lxml import etree
import os
from codeClass import YDMHttp
#封装打码平台代码
def getCodeText(imgPath,codeType):
    # 用户名
    username = '用户名'

    # 密码
    password = ‘密码'

    # 软件ID,开发者分成必要参数。登录开发者后台【我的软件】获得!
    appid = 9000

    # 软件密钥,开发者分成必要参数。登录开发者后台【我的软件】获得!
    appkey = '3dfbf9060d982ffb1c93'

    # 图片文件
    filename = imgPath

    # 验证码类型,# 例:1004表示4位字母数字,不同类型收费不同。请准确填写,否则影响识别率。在此查询所有类型 http://www.yundama.com/price.html
    codetype = codeType

    # 超时时间,秒
    timeout = 20
    result = None
    # 检查
    if (username == 'username'):
        print('请设置好相关参数再测试')
    else:
        # 初始化
        yundama = YDMHttp(username, password, appid, appkey)

        # 登陆云打码
        uid = yundama.login();
        print('uid: %s' % uid)

        # 查询余额
        balance = yundama.balance();
        print('balance: %s' % balance)

        # 开始识别,图片路径,验证码类型ID,超时时间(秒),识别结果
        cid, result = yundama.decode(filename, codetype, timeout);
        print('cid: %s, result: %s' % (cid, result))
    return result


headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36'
    }
url='https://so.gushiwen.org/user/login.aspx?from=http://so.gushiwen.org/user/collect.aspx'
page_text= requests.get(url=url,headers=headers).text
#解析验证码图片
tree = 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
#将验证码保存到本地
with open ('./code.jpg','wb')as fp:
    fp.write(img_data)
    print("保存成功")
#调用打码平台代码

code_text=getCodeText('code.jpg',1004)
print("识别结果:",code_text)

云打码的类

import http.client, mimetypes, urllib, json, time, requests


class YDMHttp:
    apiurl = 'http://api.yundama.com/api.php'
    username = ''
    password = ''
    appid = ''
    appkey = ''

    def __init__(self, username, password, appid, appkey):
        self.username = username
        self.password = password
        self.appid = str(appid)
        self.appkey = appkey

    def request(self, fields, files=[]):
        response = self.post_url(self.apiurl, fields, files)
        response = json.loads(response)
        return response

    def balance(self):
        data = {'method': 'balance', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['balance']
        else:
            return -9001

    def login(self):
        data = {'method': 'login', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey}
        response = self.request(data)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['uid']
        else:
            return -9001

    def upload(self, filename, codetype, timeout):
        data = {'method': 'upload', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'codetype': str(codetype), 'timeout': str(timeout)}
        file = {'file': filename}
        response = self.request(data, file)
        if (response):
            if (response['ret'] and response['ret'] < 0):
                return response['ret']
            else:
                return response['cid']
        else:
            return -9001

    def result(self, cid):
        data = {'method': 'result', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid)}
        response = self.request(data)
        return response and response['text'] or ''

    def decode(self, filename, codetype, timeout):
        cid = self.upload(filename, codetype, timeout)
        if (cid > 0):
            for i in range(0, timeout):
                result = self.result(cid)
                if (result != ''):
                    return cid, result
                else:
                    time.sleep(1)
            return -3003, ''
        else:
            return cid, ''

    def report(self, cid):
        data = {'method': 'report', 'username': self.username, 'password': self.password, 'appid': self.appid,
                'appkey': self.appkey, 'cid': str(cid), 'flag': '0'}
        response = self.request(data)
        if (response):
            return response['ret']
        else:
            return -9001

    def post_url(self, url, fields, files=[]):
        for key in files:
            files[key] = open(files[key], 'rb');
        res = requests.post(url, files=files, data=fields)
        return res.text

发布了23 篇原创文章 · 获赞 0 · 访问量 664

猜你喜欢

转载自blog.csdn.net/haimian_baba/article/details/103822117