网络爬虫之验证码识别
-
验证码识别
- 验证码和爬虫之间的爱恨情仇
- 反爬机制
- 云达码的使用方法
import http.client, mimetypes, urllib, json, time, requests
######################################################################
class YDMHttp:
apiurl = 'http://api.yundama.com/api.php'
username = '' #用户名
password = '' #用户密码
appid = '' #填写开发者软件代码
appkey = '' #填写开发者通讯密钥
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
######################################################################
# 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 = 1
# 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 = '22cc5376925e9387a23cf797cb9ba745'
# 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 = 60
# 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))
######################################################################
验证码识别接口
#!/usr/bin/env python
# coding:utf-8
import requests
from hashlib import md5
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 PostPic_base64(self, base64_str, codetype):
"""
im: 图片字节
codetype: 题目类型 参考 http://www.chaojiying.com/price.html
"""
params = {
'codetype': codetype,
'file_base64':base64_str
}
params.update(self.base_params)
r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, 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()
接口用法
import requests
from lxml import etree
from chaoying import Chaojiying_Client
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
}
url ='https://i.hongshu.com/login.html'
page_text = requests.post(url=url,headers=headers).text
tree = etree.HTML(page_text)
yzm_href = tree.xpath('//*[@id="imgValidCode"]/@src')[0]
yzm_data = requests.get(url=yzm_href,headers=headers).content
with open('./yzm.jpg','wb') as fp:
fp.write(yzm_data)
#验证码识别接口
chaojiying = Chaojiying_Client('账号', '密码', '软件id') #用户中心>>软件ID 生成一个替换 96001
im = open('yzm.jpg', 'rb').read() #本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
print (chaojiying.PostPic(im, 验证码类型)['pic_str']) #1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加()
#print chaojiying.PostPic(base64_str, 1902) #此处为传入 base64代码