def get_360_captcha(count=1000):
url = r'http://captcha.360.cn/image.php?app=i360&r=0.874529683496803'
site = '360cn'
if not os.access(site, os.F_OK):
os.mkdir(site)
for i in range(count):
r = urllib4.urlopen(url)
content = r.read()
fname = os.path.join(site, "_".join([site, str(i)]) + ".jpg")
with open(fname, 'wb') as f:
f.write(content)
print i
def get_icbc_captcha(count=1000):
"""https://passport.baidu.com/?verifypic"""
url_base = 'https://vip.icbc.com.cn/servlet/com.icbc.inbs.person.servlet.Verifyimage2?disFlag=2&randomKey=132098559975661896'
site = 'icbc'
if not os.access(site, os.F_OK):
os.mkdir(site)
start_time = time.time()*100
for i in range(count):
url = url_base
r = urllib4.urlopen(url, headers=header)
content = r.read()
fname = os.path.join(site, "_".join([site, str(i)]) + ".jpg")
with open(fname, 'wb') as f:
f.write(content)
print i
def get_baidu_captcha(count=1000):
"""https://passport.baidu.com/?verifypic"""
baidu_captcha_url = 'https://passport.baidu.com/?verifypic&t=%s'
site = 'baidu'
if not os.access(site, os.F_OK):
os.mkdir(site)
start_time = time.time()*100
for i in range(count):
url = baidu_captcha_url % str(start_time+i)
r = urllib4.urlopen(url, headers=header)
content = r.read()
fname = os.path.join(site, "_".join([site, str(i)]) + ".jpg")
with open(fname, 'wb') as f:
f.write(content)
print i
def __iter__(self):
while self.params['start'] < self.count:
url = self.SEARCH_PATH + '?' + urlencode(self.params)
response = json.loads(urlopen(url, user_agent=CHROME_USER_AGENT).read())
if response['responseStatus'] == 200:
results = response['responseData']['results']
for result in results:
self.params['start'] += 1
if self.params['start'] >= self.count:
break
yield GoogleQueryResult(result)
def get_taobao_pay_captcha(count=1000):
"""
nwe: http://checkcode.taobao.com/auction/checkcode?sessionID=4b9b83e4f8e6821c2e2929089f7b09bd&t=1323411260198&t=1323411260862&t=1323411261318&t=1323411261798&t=1323411262046&t=1323411262246&t=1323411262430&t=1323411262614&t=1323411262806&t=1323411262974&t=1323411263151&t=1323411263334&t=1323411263519&t=1323411263702&t=1323411263895&t=1323411264070&t=1323411264255&t=1323411264439&t=1323411264624&t=1323411264814&t=1323411265015&t=1323411265198&t=1323411265390&t=1323411265574&t=1323411265766&t=1323411265950&t=1323411266126&t=1323411266318&t=1323411266494&t=1323411266686&t=1323411266870&t=1323411267054&t=1323411267214&t=1323411267398&t=1323411277182
"""
url_base = 'http://checkcode.taobao.com/auction/checkcode?sessionID=b5b6083c712d5a524d046e3324b3cec9&t=1321946037628'
site = 'taobao'
if not os.access(site, os.F_OK):
os.mkdir(site)
start_time = time.time()*100
url = url_base
for i in range(count):
r = urllib4.urlopen(url, headers=header)
content = r.read()
fname = os.path.join(site, "_".join([site, str(i)]) + ".jpg")
with open(fname, 'wb') as f:
f.write(content)
print i
def search(self, ip, top=50, _format='json'):
url = str(gurl.Url(URL % (ip, _format, top)))
req = self.request(url)
fo = urllib4.urlopen(req)
result = fo.read()
return json.loads(result)
