def index_page(self, response):
cookie = response.cookies
sf = re.compile(r'value="(.\d*?)"/>').findall(response.text)[0]
print('sf等于{}'.format(sf))
url1 = 'http://credit.customs.gov.cn/ccppCopAction/createImage.action'
username = '******'
password = '******'
appid = '4934'
appkey = 'b7132447f5d2b263a61cd4252fd01d6a'
resp1 = requests.get(url1, headers=self.headers, cookies=cookie)
yundama = YDMHttp(username, password, appid, appkey)
cid, vcode = yundama.decode_mem(resp1.content, '5006', 10)
print('vcode:{}'.format(vcode))
image = Image.open(io.BytesIO(resp1.content))
#image.show()
#post链接
url2 = 'http://credit.customs.gov.cn/ccppCopAction/queryCopIn.action'
#企业名，轮询，先用佛山市顺德区蓝基恩塑料有限公司代替
data = 'copName=%E5%BF%AB%E9%92%B1%E6%94%AF%E4%BB%98%E6%B8%85%E7%AE%97%E4%BF%A1%E6%81%AF%E6%9C%89%E9%99%90%E5%85%AC%E5%8F%B8&sf={}&x=46&y=20&randomCode={}'.format(
sf, vcode)
html2 = requests.post(url2,
data=data,
headers=self.headers,
cookies=cookie).text
print(len(html2))
def __init__(self):
self.url = 'http://readfree.me/accounts/login/?next=/'
self.headers = {
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Encoding":
"gzip, deflate",
"Accept-Language":
"zh-CN,zh;q=0.9,en-GB;q=0.8,en;q=0.7,ja;q=0.6",
"Cache-Control":
"max-age=0",
"Connection":
"keep-alive",
"Host":
"readfree.me",
"Upgrade-Insecure-Requests":
"1",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
}
self.s = requests.Session()
self.yundama = YDMHttp()
self.verify_code_url = ''
self.verify_code_id = ''
self.captcha_id = ''
self.result = ''
def __init__(self, browser):
super(yanzhengma, self).__init__()
# self.arg = arg
self.browser = browser
# 用户名
username = '******'
# 密码
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 = 3035
# 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 = '0856355e1dd686e7819093bcd2843176'
# 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
self.codetype = 5000
# 超时时间，秒
self.timeout = 60
# 初始化
self.yundama = YDMHttp(username, password, appid, appkey)
# 登陆云打码
uid = self.yundama.login()
print 'uid: %s' % uid
# 查询余额
balance = self.yundama.balance()
print 'balance: %s' % balance
class yanzhengma(object):
"""docstring for yanzhengma"""
def __init__(self, browser):
super(yanzhengma, self).__init__()
# self.arg = arg
self.browser = browser
# 用户名
username = '******'
# 密码
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 = 3035
# 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 = '0856355e1dd686e7819093bcd2843176'
# 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
self.codetype = 5000
# 超时时间，秒
self.timeout = 60
# 初始化
self.yundama = YDMHttp(username, password, appid, appkey)
# 登陆云打码
uid = self.yundama.login()
print 'uid: %s' % uid
# 查询余额
balance = self.yundama.balance()
print 'balance: %s' % balance
def recognise(self, imgfilename):
# 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 = self.yundama.decode(imgfilename, self.codetype,
self.timeout)
print 'cid: %s, result: %s' % (cid, result)
result = str(result)
# print result
result = result.replace('c_char_p', '')
result = result.replace('(', '')
result = result.replace(')', '')
result = result.replace('\'', '')
img_to_text = result
#得到的是原始对象,使用原始的send_keys方法发送消息
self.browser.getelementbycss('#ccode').send_keys(img_to_text.decode())
time.sleep(0.3)
self.browser.getelementbycss('#Button1').send_keys(Keys.ENTER)
time.sleep(0.3)
def index_page(self, response):
cookie = response.cookies
sf = re.compile(r'value="(.\d*?)"/>').findall(response.text)[0]
print('sf等于{}'.format(sf))
url1 = 'http://credit.customs.gov.cn/ccppCopAction/createImage.action'
username = '******'
password = '******'
appid = '4934'
appkey = 'b7132447f5d2b263a61cd4252fd01d6a'
resp1 = requests.get(url1, headers=self.headers1, cookies=cookie)
yundama = YDMHttp(username, password, appid, appkey)
cid, vcode = yundama.decode_mem(resp1.content, '5006', 10)
print('vcode:{}'.format(vcode))
image = Image.open(io.BytesIO(resp1.content))
image.show()
# post链接
url2 = 'http://credit.customs.gov.cn/ccppCopAction/queryCopIn.action'
# 企业名，轮询，先用佛山市顺德区蓝基恩塑料有限公司代替
key_word = ['佛山市顺德区蓝基恩塑料有限公司', '快钱支付清算信息有限公司', '中国银联股份有限公司']
for k in range(len(key_word)):
key = urllib.parse.quote(key_word[k])
data = 'copName={}&sf={}&x=46&y=20&randomCode={}'.format(
key, sf, vcode)
html2 = requests.post(url2,
data=data,
headers=self.headers2,
cookies=cookie).text
# print(html2)
detail = re.compile("getDetail(.*?);", re.S).findall(html2)
for i in detail:
if len(detail) > 20:
print("你检索的信息超过20条，请精确您的查询条件")
break
i = eval(i)
seqNo = i[0]
saicSysNo = i[1]
data2 = {'seqNo': i[0], 'saicSysNo': i[1]}
print(data2)
self.crawl(
'http://credit.customs.gov.cn/ccppCopAction/getDetail.action',
headers=self.headers2,
cookies=cookie,
data=data2,
callback=self.detail_page)
print(k)
userInput = inputs[0]
passwordInput = inputs[1]
captchaInput = inputs[2]
onceInput = inputs[3]
userName = userInput.get('name')
passwordName = passwordInput.get('name')
captchaName = captchaInput.get('name')
onceValue = onceInput.get('value')
data = {
userName: '******',
passwordName: 'abcabc',
"once": onceValue,
'next': '/'
}
captcha_url = "https://www.v2ex.com/_captcha?once="+onceValue
imgResp = session.get(captcha_url,headers=headers)
with open("captcha.png",'wb') as fp:
fp.write(imgResp.content)
ydm = YDMHttp("zhiliao","abcabc")
_,result = ydm.recognize_captcha('captcha.png','3000')
print(result)
from yundama import YDMHttp
ydm = YDMHttp(username='******', password='******')
uid = ydm.login()
if not uid:
print("登录失败！")
balance = ydm.balance()
if balance < 10:
print("余额不足！")
_, result = ydm.decode(filename='image.jpg', codetype="3004")
print(result)
data = {
userName: '******',
passwordName: 'abcabc',
"once": onceValue,
'next': '/'
}
while True:
captcha_url = "https://www.v2ex.com/_captcha?once=" + onceValue
imgResp = session.get(captcha_url, headers=headers)
# 使用urlretrieve无法指定headers，导致不能下载
with open("captcha.png", 'wb') as fp:
fp.write(imgResp.content)
# captchaValue = input("请输入验证码：")
ydm = YDMHttp(username="******", password='******')
_, captchaValue = ydm.recognize_captcha("captcha.png", "3007")
data[captchaName] = captchaValue
loginResp = session.post(login_url, headers=headers, data=data)
if loginResp.status_code == 302:
break
settingsResp = session.get(settings_url, headers=headers)
print(settingsResp.text)
# 1. 云打码背后是人手工识别的，有可能识别失败，所以需要做多次的登录，直到登录成功。
# 2. v2ex一天之内只能登录10次（有待确定），如果超过了个这个次数，那么想再登录就只能更换ip地址或者等到24小时以后。
class ReadFree(object):
def __init__(self):
self.url = 'http://readfree.me/accounts/login/?next=/'
self.headers = {
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Encoding":
"gzip, deflate",
"Accept-Language":
"zh-CN,zh;q=0.9,en-GB;q=0.8,en;q=0.7,ja;q=0.6",
"Cache-Control":
"max-age=0",
"Connection":
"keep-alive",
"Host":
"readfree.me",
"Upgrade-Insecure-Requests":
"1",
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
}
self.s = requests.Session()
self.yundama = YDMHttp()
self.verify_code_url = ''
self.verify_code_id = ''
self.captcha_id = ''
self.result = ''
def to_douban(self):
t = self.s.get(self.url, headers=self.headers)
selector = etree.HTML(t.text)
douban_url = urljoin(self.url,
selector.xpath(".//*/a[text()='豆瓣登录']/@href")[0])
douban_response = self.s.get(douban_url)
douban_selector = etree.HTML(douban_response.text)
self.verify_code_url = douban_selector.xpath(
".//*/img[@id='captcha_image']/@src")
self.verify_code_id = douban_selector.xpath(
".//*/input[@name='captcha-id']/@value")
if self.verify_code_url and self.verify_code_id:
verify_code_res = requests.get(self.verify_code_url[0])
self.captcha_id = self.verify_code_id[0]
with open('douban.png', 'wb') as f:
f.write(verify_code_res.content)
try:
self.yundama.login()
self.result = self.yundama.decode('douban.png')
except Exception as e:
logger.error('云打码出错, 不能登录或者识别验证码失败', exc_info=True)
douban_form_state = douban_selector.xpath(
"substring-before(substring-after(.//*/form[@id='refuse_form']/@action, '?state='), '&')"
)
if douban_form_state:
douban_state = douban_form_state
to_readfree_url = 'https://www.douban.com/service/auth2/auth?state=' + douban_state + '&redirect_uri=http://readfree.me/auth/douban/login/callback/&scope=&client_id=018746ee51b1a6ad0495d4caf514f407&response_type=code'
else:
to_readfree_url = None
return to_readfree_url
def to_readfree(self):
to_readfree_url = self.to_douban()
if self.verify_code_id:
data = {
"user_alias": "*****",
"user_passwd": "***",
"captcha-id": self.captcha_id,
"captcha-solution": self.result[1],
"confirm": "授权"
}
else:
data = {
"user_alias": "****",
"user_passwd": "****",
"confirm": "授权"
}
if to_readfree_url:
response = self.s.post(to_readfree_url, data=data)
if '亚马逊' in response.url:
response = self.s.get('http://readfree.me/')
elif 'readfree' in response.url:
logger.info('没有跳转到亚马逊')
readfree_selector = etree.HTML(response.text)
user_url = readfree_selector.xpath(".//*/a[text()='个人中心']/@href")
return user_url
def get_score(self):
user_url = self.to_readfree()
if user_url:
url = urljoin('http://readfree.me', user_url[0])
user_page_res = self.s.get(url, headers=self.headers)
score_selector = etree.HTML(user_page_res.text)
score = score_selector.xpath(
"substring-before(substring-after(.//*/div[@class='clearfix']/following-sibling::p[1]/text(), '剩余额度:'), ',')"
)
return str(score).strip() if score else None
def mail_run(self):
email = EMAIL()
score = self.get_score()
balance = self.yundama.balance()
time = datetime.now() + timedelta(days=-1)
if balance < 10 and score:
contents = '{0} 云打码余额为: {1}, 余额已经不足请尽快充值。'.format(
time.strftime('%Y-%m-%d %H:%M'), balance)
elif balance <= 0 and score:
contents = '{0} 云打码余额为: {1}, 余额已经不足，无法用于下次验证。\n现在积分为{2}。'.format(
time.strftime('%Y-%m-%d %H:%M'), balance, score)
elif balance >= 10 and score:
contents = '{0} 云打码余额为: {1}, 余额较为充裕。\n现在ReadFree额度为{2}。'.format(
time.strftime('%Y-%m-%d %H:%M'), balance, score)
else:
contents = '{0} 没有获取到ReadFree额度。'.format(
time.strftime('%Y-%m-%d %H:%M'))
try:
email.send(contents, config['email_subject1'])
except Exception as e:
logger.error('邮件模块出现问题，不能正常发送邮件', exc_info=True)
else:
logger.info('邮件发送成功\n')
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Cookie': 'aisino-wsbs-session=de016770-5a45-406e-a5c5-53c74f6503a2',
'Host': 'etax.ah-n-tax.gov.cn',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36',
}
#主页url
url = 'http://etax.ah-n-tax.gov.cn/nsr/wzdk/checkybnsrrd'
#验证码url
url2 = 'http://etax.ah-n-tax.gov.cn/nsr/validate?randomNum=654.2100508709448'
imag = requests.get(url2,headers=headers).content
yundama = YDMHttp(username, password, appid, appkey)
cid, vcode = yundama.decode_mem(imag, '5006', 10)
print(vcode)
image = Image.open(io.BytesIO(imag))
image.show()
#查询post
url3 = 'http://etax.ah-n-tax.gov.cn/nsr/wzdk/checkybnsrrd'
data = {
'nsrsbh':'9134030078306486X3', #信用代码
'vcode':vcode,#验证码
}
result = requests.post(url3,headers=headers,data=data).text
print(result)
ydmUsername = '******' # 用户名
ydmPassword = '******' # 密码
appid = 1 # 开发者相关 功能使用和用户无关
appkey = '22cc5376925e9387a23cf797cb9ba745' # 开发者相关 功能使用和用户无关
filename = 'cache.png' # 验证码截图
# 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 (ydmUsername == ''):
print('请设置好相关参数再测试')
else:
# 初始化
yundama = YDMHttp(ydmUsername, ydmPassword, appid, appkey)
# 登陆云打码
uid = yundama.login()
print('云打码登录成功 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))
### yundama -------------------------------------
def get_snap(driver): # 对目标网页进行截屏。这里截的是全屏
base_url = 'http://credit.customs.gov.cn/'
resp = requests.get(base_url, headers=headers1)
cookie = resp.cookies.get_dict()
print(cookie)
sf = re.findall(r'type="hidden" value="(.*?)"', resp.text)[0]
print(sf)
url1 = 'http://credit.customs.gov.cn/ccppCopAction/createImage.action'
resp1 = requests.get(url1, headers=headers1, cookies=cookie)
# dma =DamaAPI(vctype='cpws_num')
# vcode = dma.yundamaByCode(resp1.content,codetype='5006')
yundama = YDMHttp(username, password, appid, appkey)
cid, vcode = yundama.decode_mem(resp1.content, '5006', 10)
print(vcode)
image = Image.open(io.BytesIO(resp1.content))
image.show()
headers2 = {
'Accept':
'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding':
'gzip, deflate',
'Accept-Language':
'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
'Content-Type':
'application/x-www-form-urlencoded',
'Origin':