def save_cookie(self, text, cookie_file=CONF.cookie_file):
cookie_jar2 = cookielib.LWPCookieJar()
cookie_support2 = urllib2.HTTPCookieProcessor(cookie_jar2)
opener2 = urllib2.build_opener(cookie_support2, urllib2.HTTPHandler)
urllib2.install_opener(opener2)
if six.PY3:
text = text.decode('gbk')
p = re.compile('location\.replace\(\'(.*?)\'\)')
# ???httpfox??????????????
# location.replace('http://weibo.com ?????????
# ?????????????# ????login_url?? ??????re?????
# p = re.compile('location\.replace\(\B'(.*?)'\B\)')
# ??? ??????? re?????\'???????
try:
# Search login redirection URL
login_url = p.search(text).group(1)
data = urllib2.urlopen(login_url).read()
# Verify login feedback, check whether result is TRUE
patt_feedback = 'feedBackUrlCallBack\((.*)\)'
p = re.compile(patt_feedback, re.MULTILINE)
feedback = p.search(data).group(1)
feedback_json = json.loads(feedback)
if feedback_json['result']:
cookie_jar2.save(cookie_file,
ignore_discard=True,
ignore_expires=True)
return 1
else:
return 0
except:
return 0
python类HTTPCookieProcessor()的实例源码
def login(self, username, pwd, cookie_file):
""""
Login with use name, password and cookies.
(1) If cookie file exists then try to load cookies;
(2) If no cookies found then do login
"""
#If cookie file exists then try to load cookies
if os.path.exists(cookie_file):
try:
cookie_jar = cookielib.LWPCookieJar(cookie_file)
cookie_jar.load(ignore_discard=True, ignore_expires=True)
loaded = 1
except cookielib.LoadError:
loaded = 0
print 'Loading cookies error'
#install loaded cookies for urllib2
if loaded:
cookie_support = urllib2.HTTPCookieProcessor(cookie_jar)
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
print 'Loading cookies success'
return 1
else:
return self.do_login(username, pwd, cookie_file)
else: #If no cookies found
return self.do_login(username, pwd, cookie_file)
def login(self, username, pwd, cookie_file):
""""
Login with use name, password and cookies.
(1) If cookie file exists then try to load cookies;
(2) If no cookies found then do login
"""
# If cookie file exists then try to load cookies
if os.path.exists(cookie_file):
try:
cookie_jar = cookielib.LWPCookieJar(cookie_file)
cookie_jar.load(ignore_discard=True, ignore_expires=True)
loaded = 1
except cookielib.LoadError:
loaded = 0
print('Loading cookies error')
#install loaded cookies for urllib2
if loaded:
cookie_support = urllib2.HTTPCookieProcessor(cookie_jar)
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
print('Loading cookies success')
return 1
else:
return self.do_login(username, pwd, cookie_file)
else: #If no cookies found
return self.do_login(username, pwd, cookie_file)
weibologin.py 文件源码
项目：SinaMicroblog_Creeper-Spider_VerificationCode
作者: somethingx64
项目源码
文件源码
阅读 33
收藏 0
点赞 0
评论 0
def EnableCookie(self, enableProxy):
#"Enable cookie & proxy (if needed)."
cookiejar = cookielib.LWPCookieJar()#construct cookie
cookie_support = urllib2.HTTPCookieProcessor(cookiejar)
if enableProxy:
proxy_support = urllib2.ProxyHandler({'http':'http://xxxxx.pac'})#use proxy
opener = urllib2.build_opener(proxy_support, cookie_support, urllib2.HTTPHandler)
print ("Proxy enabled")
else:
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)#construct cookie's opener
def login(form_data):
url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)'
headers = ('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0')
cookie = cookielib.MozillaCookieJar(cookie_file)
handler = urllib2.HTTPCookieProcessor(cookie)
opener = urllib2.build_opener(handler)
opener.addheaders.append(headers)
req = opener.open(url, form_data)
redirect_result = req.read()
login_pattern = r'location.replace\(\'(.*?)\'\)'
login_url = re.search(login_pattern, redirect_result).group(1)
opener.open(login_url).read()
cookie.save(cookie_file, ignore_discard=True, ignore_expires=True)
def request_image_url(image_path):
cookie = cookielib.MozillaCookieJar()
cookie.load(cookie_file, ignore_expires=False, ignore_discard=True)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
image_url = 'http://picupload.service.weibo.com/interface/pic_upload.php?mime=image%2Fjpeg&data=base64&url=0&markpos=1&logo=&nick=0&marks=1&app=miniblog'
b = base64.b64encode(file(image_path).read())
data = urllib.urlencode({'b64_data': b})
result = opener.open(image_url, data).read()
result = re.sub(r"<meta.*</script>", "", result, flags=re.S)
image_result = json.loads(result)
image_id = image_result.get('data').get('pics').get('pic_1').get('pid')
return 'https://ws3.sinaimg.cn/large/%s.jpg' % image_id
def __init__(self, cookie_filename=None, timeout=None, **kwargs):
self.cj = cookielib.LWPCookieJar()
if cookie_filename is not None:
self.cj.load(cookie_filename)
self.cookie_processor = urllib2.HTTPCookieProcessor(self.cj)
self.__build_opener()
urllib2.install_opener(self.opener)
if timeout is None:
# self._default_timeout = socket._GLOBAL_DEFAULT_TIMEOUT
# Set default timeout
self._default_timeout = 5
else:
self._default_timeout = timeout
def getUrl(self,url, ischunkDownloading=False):
try:
post=None
print 'url',url
#openner = urllib2.build_opener(urllib2.HTTPHandler, urllib2.HTTPSHandler)
cookie_handler = urllib2.HTTPCookieProcessor(self.cookieJar)
openner = urllib2.build_opener(cookie_handler, urllib2.HTTPBasicAuthHandler(), urllib2.HTTPHandler())
if post:
req = urllib2.Request(url, post)
else:
req = urllib2.Request(url)
ua_header=False
if self.clientHeader:
for n,v in self.clientHeader:
req.add_header(n,v)
if n=='User-Agent':
ua_header=True
if not ua_header:
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64; Trident/7.0; rv:11.0) like Gecko')
#response = urllib2.urlopen(req)
if self.proxy and ( (not ischunkDownloading) or self.use_proxy_for_chunks ):
req.set_proxy(self.proxy, 'http')
response = openner.open(req)
data=response.read()
return data
except:
print 'Error in getUrl'
traceback.print_exc()
return None
def getUrl(self,url, ischunkDownloading=False):
try:
post=None
print 'url',url
#openner = urllib2.build_opener(urllib2.HTTPHandler, urllib2.HTTPSHandler)
cookie_handler = urllib2.HTTPCookieProcessor(self.cookieJar)
openner = urllib2.build_opener(cookie_handler, urllib2.HTTPBasicAuthHandler(), urllib2.HTTPHandler())
if post:
req = urllib2.Request(url, post)
else:
req = urllib2.Request(url)
ua_header=False
if self.clientHeader:
for n,v in self.clientHeader:
req.add_header(n,v)
if n=='User-Agent':
ua_header=True
if not ua_header:
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64; Trident/7.0; rv:11.0) like Gecko')
#response = urllib2.urlopen(req)
if self.proxy and ( (not ischunkDownloading) or self.use_proxy_for_chunks ):
req.set_proxy(self.proxy, 'http')
response = openner.open(req)
data=response.read()
return data
except:
print 'Error in getUrl'
traceback.print_exc()
return None
def init(self, proxy=None):
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
if proxy:
proxy_support = urllib2.ProxyHandler({'http': proxy})
opener = urllib2.build_opener(proxy_support, cookie_support, urllib2.HTTPHandler)
else:
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
#print 'seton'
def use_proxy(self, proxy):
"""
????????,??proxy?????????????:http://XX.XX.XX.XX:XXXX
"""
cj = cookielib.LWPCookieJar()
cookie_support = urllib2.HTTPCookieProcessor(cj)
if proxy:
proxy_support = urllib2.ProxyHandler({'http': proxy})
opener = urllib2.build_opener(proxy_support, cookie_support, urllib2.HTTPHandler)
else:
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)
def __init__(self,url):
cookie_jar = cookielib.LWPCookieJar()
cookie = urllib2.HTTPCookieProcessor(cookie_jar)
self.opener = urllib2.build_opener(cookie)
user_agent="Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.84 Safari/537.36"
self.url=url
self.send_headers={'User-Agent':user_agent}
def test_cookies(self):
cj = MockCookieJar()
h = urllib2.HTTPCookieProcessor(cj)
o = h.parent = MockOpener()
req = Request("http://example.com/")
r = MockResponse(200, "OK", {}, "")
newreq = h.http_request(req)
self.assertTrue(cj.ach_req is req is newreq)
self.assertEqual(req.get_origin_req_host(), "example.com")
self.assertTrue(not req.is_unverifiable())
newr = h.http_response(req, r)
self.assertTrue(cj.ec_req is req)
self.assertTrue(cj.ec_r is r is newr)
def test_cookie_redirect(self):
# cookies shouldn't leak into redirected requests
from cookielib import CookieJar
from test.test_cookielib import interact_netscape
cj = CookieJar()
interact_netscape(cj, "http://www.example.com/", "spam=eggs")
hh = MockHTTPHandler(302, "Location: http://www.cracker.com/\r\n\r\n")
hdeh = urllib2.HTTPDefaultErrorHandler()
hrh = urllib2.HTTPRedirectHandler()
cp = urllib2.HTTPCookieProcessor(cj)
o = build_test_opener(hh, hdeh, hrh, cp)
o.open("http://www.example.com/")
self.assertTrue(not hh.req.has_header("Cookie"))
def test_cookies(self):
cj = MockCookieJar()
h = urllib2.HTTPCookieProcessor(cj)
o = h.parent = MockOpener()
req = Request("http://example.com/")
r = MockResponse(200, "OK", {}, "")
newreq = h.http_request(req)
self.assertTrue(cj.ach_req is req is newreq)
self.assertEqual(req.get_origin_req_host(), "example.com")
self.assertTrue(not req.is_unverifiable())
newr = h.http_response(req, r)
self.assertTrue(cj.ec_req is req)
self.assertTrue(cj.ec_r is r is newr)
def test_cookie_redirect(self):
# cookies shouldn't leak into redirected requests
from cookielib import CookieJar
from test.test_cookielib import interact_netscape
cj = CookieJar()
interact_netscape(cj, "http://www.example.com/", "spam=eggs")
hh = MockHTTPHandler(302, "Location: http://www.cracker.com/\r\n\r\n")
hdeh = urllib2.HTTPDefaultErrorHandler()
hrh = urllib2.HTTPRedirectHandler()
cp = urllib2.HTTPCookieProcessor(cj)
o = build_test_opener(hh, hdeh, hrh, cp)
o.open("http://www.example.com/")
self.assertTrue(not hh.req.has_header("Cookie"))
def __init__(self, username, password=None):
# Get password if necessary
if password is None:
password = getpass()
# Get URL for the database
self.db_url = "http://galaxy-catalogue.dur.ac.uk:8080/Eagle"
# Set up authentication and cookies
self.password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
self.password_mgr.add_password(None, self.db_url, username, password)
self.opener = urllib2.OpenerDirector()
self.auth_handler = urllib2.HTTPBasicAuthHandler(self.password_mgr)
self.cookie_handler = urllib2.HTTPCookieProcessor(cookie_jar)
## This functions executes an SQL query on the database and returns the result as a record array.
def __init__(self, username, password=None):
# Get password if necessary
if password is None:
password = getpass()
# Get URL for the database
self.db_url = "http://galaxy-catalogue.dur.ac.uk:8080/Eagle"
# Set up authentication and cookies
self.password_mgr = urllib2.HTTPPasswordMgrWithDefaultRealm()
self.password_mgr.add_password(None, self.db_url, username, password)
self.opener = urllib2.OpenerDirector()
self.auth_handler = urllib2.HTTPBasicAuthHandler(self.password_mgr)
self.cookie_handler = urllib2.HTTPCookieProcessor(cookie_jar)
## This functions executes an SQL query on the database and returns the result as a record array.
def __init__(self):
import cookielib
self.cookiejar = cookielib.CookieJar()
self._cookie_processor = urllib2.HTTPCookieProcessor(self.cookiejar)
self.form = None
self.url = "http://0.0.0.0:8080/"
self.path = "/"
self.status = None
self.data = None
self._response = None
self._forms = None
def __init__(self, headers = {},debug = True, p = ''):
#timeout
self.timeout = 10
#cookie handler
self.cookie_processor = urllib2.HTTPCookieProcessor(cookielib.LWPCookieJar())
#debug handler
self.debug = debug
if self.debug:
self.httpHandler = urllib2.HTTPHandler(debuglevel=1)
self.httpsHandler = urllib2.HTTPSHandler(debuglevel=1)
else:
self.httpHandler = urllib2.HTTPHandler(debuglevel=0)
self.httpsHandler = urllib2.HTTPSHandler(debuglevel=0)
#proxy handler (http)
if p != '' and p != 'None' and p != None and p != 'NULL':
self.proxy_handler = urllib2.ProxyHandler({'http': p})
else:
self.proxy_handler = urllib2.ProxyHandler({})
#opener
self.opener = urllib2.build_opener( self.cookie_processor,self.proxy_handler, self.httpHandler, self.httpsHandler)
self.opener.addheaders = [('User-Agent', 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'),]
#header
for key in headers.keys():
cur=self._replace(key)
if cur!=-1:
self.opener.addheaders.pop(cur)
self.opener.addheaders += [(key, headers[key]), ]
