def login(linkedin_username, linkedin_password):
cookie_filename = "cookies.txt"
cookiejar = http.cookiejar.MozillaCookieJar(cookie_filename)
opener = urllib.request.build_opener(
urllib.request.HTTPRedirectHandler(),
urllib.request.HTTPHandler(debuglevel=0),
urllib.request.HTTPSHandler(debuglevel=0),
urllib.request.HTTPCookieProcessor(cookiejar))
page = load_page(opener, "https://www.linkedin.com/uas/login")
parse = BeautifulSoup(page, "html.parser")
csrf = ""
for link in parse.find_all('input'):
name = link.get('name')
if name == 'loginCsrfParam':
csrf = link.get('value')
login_data = urllib.parse.urlencode({
'session_key': linkedin_username,
'session_password': linkedin_password,
'loginCsrfParam': csrf
})
page = load_page(opener,
"https://www.linkedin.com/checkpoint/lg/login-submit",
login_data)
parse = BeautifulSoup(page, "html.parser")
cookie = ""
try:
cookie = cookiejar._cookies['.www.linkedin.com']['/']['li_at'].value
except:
print("[DEBUG] Cookie Value: ", cookie)
return
cookiejar.save()
os.remove(cookie_filename)
return cookie
def login(postdata):
result = get_servertime()
servertime = result[0]
nonce = result[1]
postdata['su'] = get_su()
postdata['sp'] = get_sp(servertime, nonce)
postdata['servertime'] = servertime
postdata['nonce'] = nonce
postdata = urllib.parse.urlencode(postdata)
url = 'http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.94 Safari/537.36 OPR/27.0.1689.66 (Edition Baidu)',
}
req = urllib.request.Request(url, postdata.encode(), headers)
text = urllib.request.urlopen(req)
text = text.read()
text = text.decode('gbk')
result = match_login_url(text)
opener.open(result)
cookiejar.save()
def _store_cookies(self):
"""Store the session's cookiejar in a cookies.txt file"""
if self._cookiefile and self.config("cookies-update", True):
cookiejar = http.cookiejar.MozillaCookieJar()
for cookie in self._cookiejar:
cookiejar.set_cookie(cookie)
try:
cookiejar.save(self._cookiefile)
except OSError as exc:
self.log.warning("cookies: %s", exc)
def save_cookies(cookies, filename):
cookiejar = http.cookiejar.MozillaCookieJar(filename)
for c in cookies:
args = dict(vars(c).items())
args['rest'] = args['_rest']
del args['_rest']
c = http.cookiejar.Cookie(**args)
cookiejar.set_cookie(c)
cookiejar.save(filename)
def startCourseImporter(): downloadDirectory = MediaManager(mw.col, None).dir() cookiefilename = os.path.join(mw.pm.profileFolder(), 'memrise.cookies') cookiejar = http.cookiejar.MozillaCookieJar(cookiefilename) if os.path.isfile(cookiefilename): cookiejar.load() memriseService = memrise.Service(downloadDirectory, cookiejar) if memriseService.isLoggedIn() or MemriseLoginDialog.login(memriseService): cookiejar.save() memriseCourseImporter = MemriseImportDialog(memriseService) memriseCourseImporter.exec_()
def startCourseImporter(): downloadDirectory = MediaManager(mw.col, None).dir() cookiefilename = os.path.join(mw.pm.profileFolder(), 'memrise.cookies') cookiejar = http.cookiejar.MozillaCookieJar(cookiefilename) if os.path.isfile(cookiefilename): cookiejar.load() memriseService = memrise.Service(downloadDirectory, cookiejar) if memriseService.isLoggedIn() or MemriseLoginDialog.login(memriseService): cookiejar.save() memriseCourseImporter = MemriseImportDialog(memriseService) memriseCourseImporter.exec_()
def test3():
# 保存cookie的本地磁盘文件名
filename = 'cookie.txt'
cookiejar = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookiejar)
opener = urllib.request.build_opener(handler)
opener.open("http://www.baidu.com")
cookiejar.save()
def save_cookie():
file = 'cookie.txt'
cookiejar = http.cookiejar.LWPCookieJar(file)
cookie_processor = urllib.request.HTTPCookieProcessor(cookiejar)
opener = urllib.request.build_opener(cookie_processor)
opener.open('http://www.baidu.com')
cookiejar.save(filename=file, ignore_discard=True, ignore_expires=True)
return opener
def SaveCookieToFileDemo():
#创建保存cookie的文件名
filename = 'cookie.txt'
#创建MozillaCookirJar，这个类是可以将cookie写到文件的
cookiejar = http.cookiejar.MozillaCookieJar()
#创建handler
handler = urllib.request.HTTPCookieProcessor(cookiejar)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookiejar.save(filename)
def login():
if not os.path.exists(r"cookie.txt"):
PixivID = input("ID:")
password = input("Password:"******"pixiv_id"] = PixivID
post_data["pass"] = password
request = urllib.request.Request('http://www.pixiv.net/login.php',
urllib.parse.urlencode(post_data).encode(encoding='utf_8'))
urlOpener.open(request)
cookiejar.save("cookie.txt")
else:
cookiejar.load("cookie.txt")
def login():
cookie_filename = "cookies.txt"
cookiejar = http.cookiejar.MozillaCookieJar(cookie_filename)
opener = urllib.request.build_opener(
urllib.request.HTTPRedirectHandler(),
urllib.request.HTTPHandler(debuglevel=0),
urllib.request.HTTPSHandler(debuglevel=0),
urllib.request.HTTPCookieProcessor(cookiejar))
page = loadPage(opener,
"https://www.linkedin.com/uas/login").decode('utf-8')
parse = BeautifulSoup(page, "html.parser")
csrf = ""
for link in parse.find_all('input'):
name = link.get('name')
if name == 'loginCsrfParam':
csrf = link.get('value')
login_data = urllib.parse.urlencode({
'session_key': linkedin_username,
'session_password': linkedin_password,
'loginCsrfParam': csrf
})
page = loadPage(opener,
"https://www.linkedin.com/checkpoint/lg/login-submit",
login_data).decode('utf-8')
parse = BeautifulSoup(page, "html.parser")
cookie = ""
try:
cookie = cookiejar._cookies['.www.linkedin.com']['/']['li_at'].value
except:
print(
"Error logging in! Try changing language on social networks or verifying login data."
)
print(
"If a capcha is required to login (due to excessive attempts) it will keep failing, try using a VPN or running with the -s flag to show the browser, where you can manually solve the capcha."
)
sys.exit(0)
cookiejar.save()
os.remove(cookie_filename)
return cookie
def login(postdata):
result=get_servertime()
servertime=result[0]
nonce=result[1]
postdata['su']=get_su()
postdata['sp']=get_sp(servertime,nonce)
postdata['servertime']=servertime
postdata['nonce']=nonce
postdata=urllib.parse.urlencode(postdata)
url='http://login.sina.com.cn/sso/login.php?client=ssologin.js(v1.4.18)'
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.94 Safari/537.36 OPR/27.0.1689.66 (Edition Baidu)',
}
req=urllib.request.Request(url,postdata.encode(),headers)
text=urllib.request.urlopen(req)
text=text.read()
text=text.decode('gbk')
result=match_login_url(text)
opener.open(result)
cookiejar.save()
## 为opener注册handler; 十分类似node/express的中间件 body-parser cookie-parser
opener = urllib.request.build_opener(proxy_handler, cookie_handler)
## 为opener添加请求的头部
opener.addheaders = headers_list_tuple ## opener.addheaders = [(key,value), (key1, value1)]
## opener.addheaders.append(('Cookie', 'cookiename=cookievalue'))
## Request.add_header(key, val)
request = urllib.request.Request(url2) ## 添加method
## Request(url, data, headers=headers, method=method)
## request.get_method = lambda: 'PUT'
reponse = opener.open(request)
# print(file.read(80).decode())
for item in cookiejar:
print(
item.name, item.value
) # <Cookie __cfduid=dd6bc42941031a7a945a804e2aca9be0f1541861819 for .realpython.com/>
# cookiejar里面保存了cookie对象
# cookie里面可以有很多的 field,每个field都有自己的policy
# Set-Cookie: name=wangzhen; path=/ domian=.wangzhen.com; max-age=300
# Set-Cookie :age=26; expires=Sun, 10-Nov-19 15:04:49 GMT; path=/; domain=.realpython.com; HttpOnly
cookiejar.save(ignore_discard=True, ignore_expires=True) ##初次获取cookie后保存在本地
'''
print( reponse.read().decode() )
#UnicodeEncodeError: 'gbk' codec can't encode character '\U0001f430' in position 366917: illegal multibyte sequence
but:
print( reponse.read(800).decode() ) #ok 不出错！！！ 为什么
'''
import urllib.request,http.cookiejar
# 保存cookie的本地磁盘文件名
filename = "cookie.txt"
# 声明一个MozillaCookieJar(有save实现)对象实例来保存cookie，之后写入文件
cookiejar = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookiejar)
opener = urllib.request.build_opener(handler)
response = opener.open("http://www.baidu.com")
cookiejar.save()
# print(cookieStr[:-1])
''' ''
'''''
#------->>>>>> 访问网站获得cookie，并把获得的cookie保存在cookie文件中
# 保存cookie的本地磁盘文件名
filename = 'cookie.txt'
# 声明一个MozillaCookieJar(有save实现)对象实例来保存cookie，之后写入文件
cookiejar = http.cookiejar.MozillaCookieJar(filename)
# 使用HTTPCookieProcessor()来创建cookie处理器对象，参数为CookieJar()对象
handler = urt.HTTPCookieProcessor(cookiejar)
# 通过 build_opener() 来构建opener
opener = urt.build_opener(handler)
# 创建一个请求，原理同urllib2的urlopen
response = opener.open('http://www.baidu.com')
# 保存cookie到本地文件
cookiejar.save(ignore_discard=True,ignore_expires=True)
''' ''
'''''
def login(cookiepath):
"""
The login function prompts for an authorized KOA user ID and password,
then sets up a workspace (or connects to an existing workspace) on
the PRV pipeline server for that user.
Args:
cookiepath (string): a file path provided by the user to save
returned cookie which is needed for the
subsequent PRV operations.
Example:
>>> import hiresprv.auth
>>> hiresprv.auth.login(cookiepath)
# program will prompt for userid and password
"""
# TODO: Many of these variables are not used
userid = ''
password = ''
url = ''
response = ''
jsondata = ''
status = ''
msg = ''
debug = 0
debugfile = ''
if len(debugfile) > 0:
debug = 1
logging.basicConfig(filename=debugfile, level=logging.DEBUG)
# TODO: Do we need this?
with open(debugfile, 'w') as fdebug:
pass
if debug:
logging.debug('')
logging.debug('Enter Login.init:')
logging.debug('cookiepath= %s' % cookiepath)
#
# get userid and password via keyboard input
#
userid = input("KOA userid: ")
if debug:
logging.debug('')
logging.debug('userid= %s' % userid)
password = getpass.getpass("KOA Password: "******"utf-8")
jsondata = json.loads(sdata)
if debug:
logging.debug('here2: data= ')
logging.debug(data)
logging.debug('sdata= %s' % sdata)
logging.debug('jsondata= ')
logging.debug(jsondata)
for key, val in jsondata.items():
if debug:
logging.debug('key= %s val= %s' % (key, val))
if key == 'status':
status = val
if key == 'msg':
msg = val
if debug:
logging.debug('status= %s msg= %s' % (status, msg))
if status == 'ok':
cookiejar.save(cookiepath, ignore_discard=True)
if debug:
logging.debug('cookiejar saved to hirescookietxt')
msg = 'Successful login as %s' % userid
else:
msg = 'Failed to login: %s' % msg
if debug:
logging.debug('')
logging.debug('status= %s' % status)
logging.debug('msg= %s' % msg)
print(msg)
return
'src': None
}
form_login = urlencode(dic_login).encode(encoding='UTF8')
#构造csrf验证表单
dic_csrf = {'csrfmiddlewaretoken': csrfmiddlewaretoken}
form_csrf = urlencode(dic_csrf).encode(encoding='UTF8')
#post登陆页面
login_html = maxcrawler.get_webtext(opener, max_login, header_login,
form_login)
if not 'pkey' in [cookie.name for cookie in cookiejar]:
print("We are not logged in !")
else:
print("We are logged in !")
cookiejar.save(ignore_discard=True, ignore_expires=True)
for ele in cookiejar:
print('Name=' + ele.name)
print('Value' + ele.value)
#request 胜率数据页面
data_html = maxcrawler.get_webtext(opener, max_data, header_data, form_csrf)
#############################
name_pattern = re.compile('<span class="hero-name-list">(.*?)</span>')
hero_list = re.findall(name_pattern, data_html)
print(hero_list)
rate_pattern = re.compile(
'([\d|\.]*)%</div><div class="segment segment-green"')
rate_list = re.findall(rate_pattern, data_html)
