代理ip

• 获取代理ip的网站：
  • 快代理
  • 西祠代理
  • www.goubanjia.com

#代理ip
import requests
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36',
}

url = 'https://www.baidu.com/s?wd=ip'
page_text = requests.get(url=url,headers=headers,proxies={'https':'134.209.13.16:8080'}).text
with open('./ip.html','w',encoding='utf-8') as fp:fp.write(page_text)

https_proxies = [{'https':'134.209.13.16:8080'},{'https':'134.209.13.14:8080'},{'https':'134.209.13.19:8080'}
]
http_proxies = [{'http':'134.209.13.16:8080'},{'http':'134.209.13.14:8080'},{'http':'134.209.13.19:8080'}
]

#获取请求的url
url = 'https://www.baidu.com/s?wd=ip'
response = requests.get(url=url,headers=headers)
response.url.split(':')[0]

云打码平台的使用

• 官网url：http://www.yundama.com/demo.html
• 注册：
  • 1.普通用户
  • 2.开发者用户
• 登录平台：
  • 1.普通用户：
    • 1.查询余额（题分）
  • 2.开发者用户：
    • 1.创建一个软件：软件的id和通讯秘钥后期在编码时会被用到
    • 2.下载示例代码：PythonHTTP
      • 开发文档-》下载最新的DLL文档-》PythonHTTP
• 编码：

import requests
import json
import time

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 = passwordself.appid = str(appid)self.appkey = appkeydef request(self, fields, files=[]):response = self.post_url(self.apiurl, fields, files)response = json.loads(response)return responsedef 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 -9001def 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 -9001def 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 -9001def 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, resultelse: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 -9001def 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

# 普通用户用户名
username    = 'bobo328410948'# 密码
password    = 'bobo328410948'                            # 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       = 6003                                     # 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      = '1f4b564483ae5c907a1d34f8e2f2776c'    # 图片文件
filename    = 'getimage.jpg'                        # 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    = 1004# 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))

#将验证码识别的操作封装成一个函数
def getCodeText(userName,passWord,imgPath,codeType):result = None# 普通用户用户名username    = userName# 密码password    = passWord                            # 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       = 6003                                     # 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      = '1f4b564483ae5c907a1d34f8e2f2776c'    # 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.htmlcodetype    = 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

from lxml import etree
from urllib import request
url = 'http://www.renren.com/'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.121 Safari/537.36'
}
page_text = requests.get(url=url,headers=headers).text
#解析验证码图片
tree = etree.HTML(page_text)
code_img_url = tree.xpath('//*[@id="verifyPic_login"]/@src')[0]
request.urlretrieve(code_img_url,'./code.jpg')code_text = getCodeText('账号','密码','./code.jpg',2004)
print(code_text)