from analyzer import KNNAnalyzer
import random
import urllib
def getImage(url, file_path):
u = urllib.urlopen(url)
data = u.read()
f = open(file_path, 'wb')
f.write(data)
f.close()
segmenter = NormalSegmenter()
extractor = SimpleFeatureExtractor( feature_size=20, stretch=False )
analyzer = KNNAnalyzer( segmenter, extractor)
analyzer.train('../data/features.jpg')
for i in range(4):
rand = random.random()
url = "http://202.119.113.135/validateCodeAction.do?random=" + str(rand);
print url
file_path = "../train/crawler.jpg"
getImage(url,file_path)
result = analyzer.analyze('../train/crawler.jpg')
print result
analyzer.display()
analyzer.display_binary()
from analyzer import KNNAnalyzer
import random
import urllib
def getImage(url, file_path):
u = urllib.urlopen(url)
data = u.read()
f = open(file_path, 'wb')
f.write(data)
f.close()
segmenter = NormalSegmenter()
extractor = SimpleFeatureExtractor( feature_size=20, stretch=False )
analyzer = KNNAnalyzer( segmenter, extractor)
analyzer.train('../data/features.jpg')
for i in range(1):
rand = random.random()
url = "http://202.119.113.135/validateCodeAction.do?random=" + str(rand);
#print url
file_path = "../train/crawler.jpg"
getImage(url,file_path)
result = analyzer.analyze('../train/crawler.jpg')
print result
#analyzer.display()
#analyzer.display_binary()
def getSource(uid,pwd):
# print "初始化分类器..."
segmenter = NormalSegmenter()
extractor = SimpleFeatureExtractor( feature_size=20, stretch=False )
analyzer = KNNAnalyzer( segmenter, extractor)
analyzer.train('../data/features.jpg')
# print "开始模拟登录..."
login_url = "http://202.119.113.135/loginAction.do"
vcode_url = 'http://202.119.113.135/validateCodeAction.do?random=0.2583906068466604'
all_url = "http://202.119.113.135/gradeLnAllAction.do?type=ln&oper=sxinfo&lnsxdm=001"
now_url = "http://202.119.113.135/bxqcjcxAction.do"
#post请求头部
global headers
global postData
headers = {
'x-requestted-with': 'XMLHttpRequest',
'Accept-Language': 'zh-cn',
'Accept-Encoding': 'gzip, deflate',
'ContentType': 'application/x-www-form-urlencoded; chartset=UTF-8',
'Host': 'login.taobao.com',
'DNT': 1,
'Cache-Control': 'no-cache',
'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:14.0) Gecko/20100101 Firefox/14.0.1',
'Referer' : 'https://login.taobao.com/member/login.jhtml?redirectURL=http%3A%2F%2Fwww.taobao.com%2F',
'Connection' : 'Keep-Alive'
}
#用户名，密码
username = uid
password = pwd
#请求数据包
postData = {
'zjh':username,
'mm':password,
}
test_number = 10
while login(login_url,vcode_url,postData,headers,analyzer) == False:
test_number -= 1
if(test_number == 0):
print "please check out your uid and password!!"
break;
if test_number > 0:
page = getHtml(all_url)
print test_number
page = page.encode('utf-8')
soup = BeautifulSoup(page)
trs = soup.findAll('tr',{'class':'odd'})
lists = []
for tr in trs:
ll = []
tds = tr.findAll('td')
for td in tds:
tmp = ''
if(td.p):
tmp = td.p.string.strip().encode('utf-8')
else:
tmp = td.string.strip().encode('utf-8')
# print tmp
ll.append(tmp)
lists.append(ll)
return lists
cookieSupport= urllib2.HTTPCookieProcessor(cookiejar)
opener = urllib2.build_opener(cookieSupport, urllib2.HTTPHandler)
urllib2.install_opener(opener)
#打开登陆页面
urllib2.urlopen(login_url)
#此时直接发送post数据包登录
getCheckCode(vcode_url)
success_test, failed_test = 0, 0
return sendPostData(login_url, postData, headers)
if __name__ == "__main__":
print "初始化分类器..."
segmenter = NormalSegmenter()
extractor = SimpleFeatureExtractor( feature_size=20, stretch=False )
analyzer = KNNAnalyzer( segmenter, extractor)
analyzer.train('../data/features.jpg')
print "开始模拟登录..."
login_url = "http://202.119.113.135/loginAction.do"
vcode_url = 'http://202.119.113.135/validateCodeAction.do?random=0.2583906068466604'
#post请求头部
headers = {
'x-requestted-with': 'XMLHttpRequest',
'Accept-Language': 'zh-cn',
'Accept-Encoding': 'gzip, deflate',
'ContentType': 'application/x-www-form-urlencoded; chartset=UTF-8',
'Host': 'login.taobao.com',
'DNT': 1,
'Cache-Control': 'no-cache',