爬虫之解决验证码和cook问题

1.先写函数

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

def get_code_text(codeType,imgPath):
    # 用户名:普通用户
    username    = 'dongdong'

    # 密码
    password    = 'weidong123'                            

    # 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       = 6612                                    

    # 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      = 'fe5dfbc42f64af2d6e1c361bd094ea22'    

    # 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                                   

    # 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

#爬取古诗文网

import requests
from lxml import etree
import os
from urllib import request
headers={
    'User-Agent':"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36",
    
}
url = 'https://so.gushiwen.org/user/login.aspx'
session = requests.Session()

url_text = session.get(url=url,headers=headers).text
tree = etree.HTML(url_text)
img_url = 'https://so.gushiwen.org' +tree.xpath('//*[@id="imgCode"]/@src')[0]

# request.urlretrieve(url=img_url,filename='./code.jpg'
img_data = session.get(url=img_url,headers=headers).content
with open('./code.jpg','wb') as f:
    f.write(img_data)


code = get_code_text(1004,'./code.jpg')
#模拟登陆
login_url = 'https://so.gushiwen.org/user/login.aspx'
__VIEWSTATE = tree.xpath('//*[@id="__VIEWSTATE"]/@value')
__VIEWSTATEGENERATOR = tree.xpath('//*[@id="__VIEWSTATEGENERATOR"]/@value')
data = {
    "__VIEWSTATE": __VIEWSTATE,
    "__VIEWSTATEGENERATOR": __VIEWSTATEGENERATOR,
    "from": "http://so.gushiwen.org/user/collect.aspx",
    "email": "632806735@qq.com",
    "pwd": "weidong123",
    "code": code,
    "denglu": "登录"
}
page_text = session.post(url=login_url,headers=headers,data=data).text
with open('./gushi.html','w',encoding='utf-8') as f:
    f.write(page_text)