def urllib2_yzm_cookie():
url = 'http://202.119.81.112:8080/Logon.do?method=logon'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'
}
data = {'USERNAME': '******', 'PASSWORD': '******', 'RANDOMCODE': ''}
postdata = urllib.urlencode(data)
# cookie
cookie = cookielib.CookieJar()
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
# 第一次请求网页得到cookie
request = urllib2.Request(url, postdata, headers=headers)
response = opener.open(request)
# 由于验证码识别的误差，不停地获取验证码登陆，直到正确为止
while True:
# 获取验证码
yzm = opener.open('http://202.119.81.112:8080/verifycode.servlet')
yzmfile = open('yzm.jpg', 'wb')
yzmfile.write(yzm.read())
yzmfile.close()
# 识别验证码
image = Image.open('yzm.jpg')
yzmtext = pytesser.image_to_string(image)
tmp = list(yzmtext)
while ' ' in tmp:
tmp.remove(' ')
while '\n' in tmp:
tmp.remove('\n')
yzmtext = ''.join(tmp)[:4]
print yzmtext
# return
# 模拟登陆
# data['RANDOMCODE'] = raw_input()
data['RANDOMCODE'] = yzmtext
postdata = urllib.urlencode(data)
request = urllib2.Request(url, postdata, headers=headers)
response = opener.open(request)
# print response.read().decode('utf-8')
# 爬取成绩
grade_url = 'http://202.119.81.112:9080/njlgdx/kscj/cjcx_list'
response = opener.open(grade_url)
html = response.read()
f = open('1.txt', 'w')
f.write(html)
f.close()
# print html
if re.search('RANDOMCODE', html) == None:
break
def get_webtoken():
CaptchaUrl = "http://e.oppo.cn/loginCaptcha"
LoginUrl = "http://e.oppo.cn/login"
# 验证码地址和post地址
while True:
cookie = cookielib.CookieJar()
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
# urllib2.install_opener(opener)
# 将cookies绑定到一个opener cookie由cookielib自动管理
while True:
picture = opener.open(CaptchaUrl) # 用openr访问验证码地址,获取cookie
local = open('/data/rx/image/image.jpg', 'wb')
local.write(picture.read())
local.close()
im = Image.open('/data/rx/image/image.jpg')
text = pytesser.image_to_string(im).strip()
# text = pytesser.image_file_to_string(im,graceful_errors=True).strip()
flag = len(text)
# print 'authCode=%s,lens=%s' % (text, flag)
# print len(text)
if flag == 4:
break
boby = {'name': '扣费', 'passwd': '123456', 'captcha': text}
data = urllib.urlencode(boby)
request = urllib2.Request(url=LoginUrl, data=data)
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
opener.open(request) #response
cookies = cookie.__str__().split(' ')[1]
# print 'cookies=%s' % cookies
if cookies.find('WEBTOKEN') == 0:
break
return cookies
def recognize(pic_name):
im = pre_operation(pic_name)
text = pytesser.image_to_string(im).strip()
if(len(text) == 4 and isalpha(text)):
print(text)
return text.upper()
return None
def __ImagePriceExtract(self, file):
try:
img = Image.open(file)
r,g,b,a = img.split()
img = Image.merge('RGB',(r,g,b))
text = image_to_string(img)
text = text.replace(" ",'').replace('\n','').replace('\r','')
return float(text)
except Exception,e:
raise DropItem("item price can't not extracted successfully: %s" % e)
def captchaRecognize(captchaImg):
#识别修改后的图片
text = pytesser.image_to_string(captchaImg)
#使用正则表达式过滤除数字以外的识别数据
captcha = re.findall('[0-9]',text)
captcha = ''.join(captcha)
if len(captcha)!=4:
return 0
else:
return captcha
def solve_captcha(self, img):
imagename = img.split("/")[-1]
req = urllib2.Request(img)
img_file = Image.open(StringIO(urllib2.urlopen(req).read()))
img_file.resize((116, 56), Image.NEAREST)
if self.tmp:
with tmanage() as t:
n = ''.join([t, "/code.tif"])
img_file.save(n)
img_file = Image.open(n)
s = image_to_string(img_file)
img_file.close()
else:
output = StringIO()
img_file.save(output, format="TIFF")
s = image_to_string(Image.open(StringIO(output.getvalue())))
output.close()
s = s.replace(' ', '')
s = s.replace('.', '')
return s[:4]
def solve_captcha(self,img):
imagename = img.split("/")[-1]
req = urllib2.Request(img)
img_file = Image.open(StringIO(urllib2.urlopen(req).read()))
img_file.resize((116, 56), Image.NEAREST)
if self.tmp:
with tmanage() as t:
n = ''.join([t, "/code.tif"])
img_file.save(n)
img_file = Image.open(n)
s = image_to_string(img_file)
img_file.close()
else:
output = StringIO()
img_file.save(output,format="TIFF")
s = image_to_string(Image.open(StringIO(output.getvalue())))
output.close()
s = s.replace(' ','')
s = s.replace('.','')
return s[:4]
def access_company_url(self,company_url):
base_url ='http://bj.597rcw.com'
page = urllib2.urlopen(base_url+company_url).read().decode("gbk")
number_urls=re.findall('/AspNet/StrToImg.ashx.+?/>', page, re.S)
if len(number_urls)!=0:
#'<td><b>北京中泰安瑞科技发展有限公司</b></td>"' 截取
commpany_name=re.findall('<td><b>.+?</b></td>', page, re.S)[0][7:-9]
#<td height="25" width="85%">饶经理</td>
contacts_name=re.findall('<td height="25" width="85%">.+?</td>', page, re.S)[0][28:-5]
#<img src="/AspNet/StrToImg.ashx?type=code&email=p7JDp9Jzqo3AaSHCR4ySUg%3D%3D">
number_url=number_urls[0][:-4]
#把号码图片转换为文本
img = Image.open(cStringIO.StringIO(urllib2.urlopen(base_url+number_url).read()))
number = image_to_string(img)
return commpany_name+","+contacts_name+","+number
else:
return ''
# -*- coding: utf-8 -*- from pytesser.pytesser import image_to_string from PIL import * import Image import ImageEnhance image = Image.open(r"TB2965Lb46I8KJjSszfXXaZVXXa_!!646445699.jpg.jpg") enhancer = ImageEnhance.Contrast(image) image_enhancer = enhancer.enhance(4) print(image_to_string(image_enhancer))
def ocr(image):
return pytesser.image_to_string(image.convert('RGB'))
def ocr_cropped(image, box):
region = image.crop(box)
region = region.convert('RGB')
return pytesser.image_to_string(region)
def ocr(image):
return pytesser.image_to_string(image.convert('RGB'))
'referer': 'http://hub.hust.edu.cn/index.jsp'
}).content
global k1, k2
k1, k2 = eval(content)
verify_image_url = 'http://hub.hust.edu.cn/randomImage.action?k1=%s&k2=%s&uno=%s&time=%d' % (
k1, k2, username, TIME)
content = s.get(verify_image_url).content
global vimg
vimg = Image.open(StringIO(content))
get_rand_key()
try:
from pytesser.pytesser import image_to_string
vcode = image_to_string(vimg).strip()
vimg.save('vcode.jpg')
print vcode
except:
import traceback, sys
traceback.print_exc(file=sys.stdout)
vimg.show()
vcode = raw_input('verify code:')
data = {
'usertype': 'xs',
'username': username,
'password': password,
'rand': '',
'ln': server,
'random_key1': '',
def resolver(path):
result = pytesser.image_to_string(path)
return result
def extractText(left, top, right, bottom, scale = 2):
im = capture(left, top, right, bottom)
im = im.resize([scale * i for i in im.size])
return tesser.image_to_string(im)
# print headers['Cookie']
# 输入用户名和密码
login_info['USERNAME'] = raw_input('Username: '******'PASSWORD'] = raw_input('Password: '******'yzm.jpg', 'wb')
yzmfile.write(yzm_response.content)
yzmfile.close()
# 识别验证码
image = Image.open('yzm.jpg')
yzmtext = pytesser.image_to_string(image)
tmp = list(yzmtext)
while ' ' in tmp:
tmp.remove(' ')
while '\n' in tmp:
tmp.remove('\n')
yzmtext = ''.join(tmp)[:4]
# print yzmtext
login_info['RANDOMCODE'] = yzmtext
# 重新登陆，若验证码正确则登陆成功
# should_success_response = requests.get(login_url, params=urllib.urlencode(login_info), headers=headers)
should_success_response = requests.post(login_url,
data=login_info,
headers=headers)
html = should_success_response.content
def ocr_cropped(image, box):
region = image.crop(box)
region = region.convert('RGB')
return pytesser.image_to_string(region)
run_from_console = __name__ == '__main__'
img = Image.open('code.png')
imgry = img.convert('L')
table = []
threshold = 150
for i in range(256):
if i < threshold:
table.append(0)
else:
table.append(1)
out = imgry.point(table, '1')
fname = 'test.tiff'
out.save(fname, dpi=(72, 72))
tiff = Image.open(fname)
code = pytesser.image_to_string(tiff)
clean_code = re.sub(r'[^0-9a-zA-Z]', '', code)
print clean_code
os.remove(fname)
def extractText(left, top, right, bottom, scale=2):
im = capture(left, top, right, bottom)
im = im.resize([scale * i for i in im.size])
return tesser.image_to_string(im)
image_to_string = None
def get_rand_key():
verify_url = 'http://hub.hust.edu.cn/randomKey.action?username=%s&time=%d' % (username, TIME)
content = s.get(verify_url, headers={'referer': 'http://hub.hust.edu.cn/index.jsp'}).content
global k1, k2
k1, k2 = eval(content)
verify_image_url = 'http://hub.hust.edu.cn/randomImage.action?k1=%s&k2=%s&uno=%s&time=%d' % (k1, k2, username, TIME)
content = s.get(verify_image_url).content
global vimg
vimg = Image.open(StringIO(content))
get_rand_key()
try:
from pytesser.pytesser import image_to_string
vcode = image_to_string(vimg).strip()
vimg.save('vcode.jpg')
print vcode
except:
import traceback, sys
traceback.print_exc(file=sys.stdout)
vimg.show()
vcode = raw_input('verify code:')
data = {
'usertype': 'xs',
'username': username,
'password': password,
'rand': '',
'ln': server,
'random_key1' : '',
