def set_cookie(self, name, value):
"""
Sets a cookie to be passed through with requests.
"""
cookie_domain = self.extra_environ.get('HTTP_HOST', '.localhost')
cookie_domain = cookie_domain.split(':', 1)[0]
if '.' not in cookie_domain:
cookie_domain = "%s.local" % cookie_domain
value = escape_cookie_value(value)
cookie = http_cookiejar.Cookie(
version=0,
name=name,
value=value,
port=None,
port_specified=False,
domain=cookie_domain,
domain_specified=True,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=False,
comment=None,
comment_url=None,
rest=None
)
self.cookiejar.set_cookie(cookie)
def validate_session(self):
"""Validate an API session."""
# We need to store our access token as the openx3_access_token cookie.
# This cookie will be passed to all future API requests.
cookie = cookielib.Cookie(version=0,
name='openx3_access_token',
value=self._token,
port=None,
port_specified=False,
domain=self.domain,
domain_specified=True,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=False,
comment=None,
comment_url=None,
rest={})
self._session.cookies.set_cookie(cookie)
# v2 doesn't need this extra step, just the cookie:
if self.api_path == API_PATH_V1:
response = self._session.put(
url=self._resolve_url('/a/session/validate'),
timeout=self.timeout)
self.log_request(response)
return response.text
def get_cookie_opener(gs_username, gs_token, gs_toolname=None):
""" Create a GenomeSpace cookie opener """
cj = http_cookiejar.CookieJar()
for cookie_name, cookie_value in [('gs-token', gs_token),
('gs-username', gs_username)]:
# create a super-cookie, valid for all domains
cookie = http_cookiejar.Cookie(version=0,
name=cookie_name,
value=cookie_value,
port=None,
port_specified=False,
domain='',
domain_specified=False,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=True,
comment=None,
comment_url=None,
rest={'HttpOnly': None},
rfc2109=False)
cj.set_cookie(cookie)
cookie_opener = build_opener(HTTPCookieProcessor(cj))
cookie_opener.addheaders.append(('gs-toolname', gs_toolname
or DEFAULT_GENOMESPACE_TOOLNAME))
return cookie_opener
def set_cookie(self, name, value):
"""
Sets a cookie to be passed through with requests.
"""
value = escape_cookie_value(value)
cookie = http_cookiejar.Cookie(
version=0,
name=name,
value=value,
port=None,
port_specified=False,
domain='.localhost',
domain_specified=True,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=False,
comment=None,
comment_url=None,
rest=None
)
self.cookiejar.set_cookie(cookie)
def cookie(
url,
name,
value,
expires=None):
'''Return a new Cookie using a slightly more
friendly API than that provided by six.moves.http_cookiejar
@param name The cookie name {str}
@param value The cookie value {str}
@param url The URL path of the cookie {str}
@param expires The expiry time of the cookie {datetime}. If provided,
it must be a naive timestamp in UTC.
'''
u = urlparse(url)
domain = u.hostname or u.netloc
port = str(u.port) if u.port is not None else None
secure = u.scheme == 'https'
if expires is not None:
if expires.tzinfo is not None:
raise ValueError('Cookie expiration must be a naive datetime')
expires = (expires - datetime(1970, 1, 1)).total_seconds()
return http_cookiejar.Cookie(
version=0,
name=name,
value=value,
port=port,
port_specified=port is not None,
domain=domain,
domain_specified=True,
domain_initial_dot=False,
path=u.path,
path_specified=True,
secure=secure,
expires=expires,
discard=False,
comment=None,
comment_url=None,
rest=None,
rfc2109=False,
)
def _make_cookies(base_url, cookies, cj):
domain = urllib_parse.urlsplit(base_url).hostname
for key in cookies:
c = http_cookiejar.Cookie(0,
key,
str(cookies[key].split(';')[0]),
port=None,
port_specified=False,
domain=domain,
domain_specified=True,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=False,
comment=None,
comment_url=None,
rest={})
cj.set_cookie(c)
return cj
def cookie(
url,
name,
value,
expires=None):
'''Return a new Cookie using a slightly more
friendly API than that provided by six.moves.http_cookiejar
@param name The cookie name {str}
@param value The cookie value {str}
@param url The URL path of the cookie {str}
@param expires The expiry time of the cookie {datetime}
'''
u = urlparse(url)
domain = u.hostname or u.netloc
port = str(u.port) if u.port is not None else None
secure = u.scheme == 'https'
if expires is not None:
expires = expires.strftime("%s")
return http_cookiejar.Cookie(
version=0,
name=name,
value=value,
port=port,
port_specified=port is not None,
domain=domain,
domain_specified=True,
domain_initial_dot=False,
path=u.path,
path_specified=True,
secure=secure,
expires=expires,
discard=False,
comment=None,
comment_url=None,
rest=None,
rfc2109=False,
)
def _add_cookie(self, cookie_dict):
# We don't use self.app.set_cookie since it has undesirable behaviour
# with domain and value fields that causes issues.
value = cookie_dict['value']
if six.PY2:
value = value.encode('utf-8')
cookie = http_cookiejar.Cookie(version=0,
name=cookie_dict['name'],
value=value,
port=None,
port_specified=False,
domain='localhost.local',
domain_specified=True,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=False,
comment=None,
comment_url=None,
rest=None)
self.app.cookiejar.set_cookie(cookie)
def set_cookie(cookiejar, kaka):
"""PLaces a cookie (a cookielib.Cookie based on a set-cookie header
line) in the cookie jar.
Always chose the shortest expires time.
:param cookiejar:
:param kaka: Cookie
"""
# default rfc2109=False
# max-age, httponly
for cookie_name, morsel in kaka.items():
std_attr = ATTRS.copy()
std_attr["name"] = cookie_name
_tmp = morsel.coded_value
if _tmp.startswith('"') and _tmp.endswith('"'):
std_attr["value"] = _tmp[1:-1]
else:
std_attr["value"] = _tmp
std_attr["version"] = 0
attr = ""
# copy attributes that have values
try:
for attr in morsel.keys():
if attr in ATTRS:
if morsel[attr]:
if attr == "expires":
std_attr[attr] = http2time(morsel[attr])
else:
std_attr[attr] = morsel[attr]
elif attr == "max-age":
if morsel[attr]:
std_attr["expires"] = http2time(morsel[attr])
except TimeFormatError:
# Ignore cookie
logger.info(
"Time format error on %s parameter in received cookie" %
(attr, ))
continue
for att, spec in PAIRS.items():
if std_attr[att]:
std_attr[spec] = True
if std_attr["domain"] and std_attr["domain"].startswith("."):
std_attr["domain_initial_dot"] = True
if morsel["max-age"] is 0:
try:
cookiejar.clear(domain=std_attr["domain"],
path=std_attr["path"],
name=std_attr["name"])
except ValueError:
pass
else:
# Fix for Microsoft cookie error
if "version" in std_attr:
try:
std_attr["version"] = std_attr["version"].split(",")[0]
except (TypeError, AttributeError):
pass
new_cookie = cookielib.Cookie(**std_attr)
cookiejar.set_cookie(new_cookie)
def set_cookie(self, kaka, request):
"""Returns a http_cookiejar.Cookie based on a set-cookie header line"""
if not kaka:
return
part = urlparse(request.url)
_domain = part.hostname
logger.debug("%s: '%s'", _domain, kaka)
for cookie_name, morsel in kaka.items():
std_attr = ATTRS.copy()
std_attr["name"] = cookie_name
_tmp = morsel.coded_value
if _tmp.startswith('"') and _tmp.endswith('"'):
std_attr["value"] = _tmp[1:-1]
else:
std_attr["value"] = _tmp
std_attr["version"] = 0
# copy attributes that have values
for attr in morsel.keys():
if attr in ATTRS:
if morsel[attr]:
if attr == "expires":
std_attr[attr] = _since_epoch(morsel[attr])
elif attr == "path":
if morsel[attr].endswith(","):
std_attr[attr] = morsel[attr][:-1]
else:
std_attr[attr] = morsel[attr]
else:
std_attr[attr] = morsel[attr]
elif attr == "max-age":
if morsel["max-age"]:
std_attr["expires"] = time.time() + int(morsel["max-age"])
for att, item in PAIRS.items():
if std_attr[att]:
std_attr[item] = True
if std_attr["domain"]:
if std_attr["domain"].startswith("."):
std_attr["domain_initial_dot"] = True
else:
std_attr["domain"] = _domain
std_attr["domain_specified"] = True
if morsel["max-age"] == 0:
try:
self.cookiejar.clear(domain=std_attr["domain"],
path=std_attr["path"],
name=std_attr["name"])
except ValueError:
pass
elif std_attr["expires"] and std_attr["expires"] < utc_now():
try:
self.cookiejar.clear(domain=std_attr["domain"],
path=std_attr["path"],
name=std_attr["name"])
except ValueError:
pass
else:
new_cookie = http_cookiejar.Cookie(**std_attr)
self.cookiejar.set_cookie(new_cookie)
def getRegexParsed(
regexs,
url,
cookieJar=None,
forCookieJarOnly=False,
recursiveCall=False,
cachedPages={},
rawPost=False,
cookie_jar_file=None): #0,1,2 = URL, regexOnly, CookieJarOnly
#cachedPages = {}
#print 'url',url
doRegexs = re.compile('\$doregex\[([^\]]*)\]').findall(url)
# print 'doRegexs',doRegexs,regexs
setresolved = True
for k in doRegexs:
if k in regexs:
#print 'processing ' ,k
m = regexs[k]
#print m
cookieJarParam = False
if 'cookiejar' in m: # so either create or reuse existing jar
#print 'cookiejar exists',m['cookiejar']
cookieJarParam = m['cookiejar']
if '$doregex' in cookieJarParam:
cookieJar = getRegexParsed(regexs, m['cookiejar'],
cookieJar, True, True,
cachedPages)
cookieJarParam = True
else:
cookieJarParam = True
#print 'm[cookiejar]',m['cookiejar'],cookieJar
if cookieJarParam:
if cookieJar == None:
#print 'create cookie jar'
cookie_jar_file = None
if 'open[' in m['cookiejar']:
cookie_jar_file = m['cookiejar'].split(
'open[')[1].split(']')[0]
# print 'cookieJar from file name',cookie_jar_file
cookieJar = getCookieJar(cookie_jar_file)
# print 'cookieJar from file',cookieJar
if cookie_jar_file:
saveCookieJar(cookieJar, cookie_jar_file)
#cookieJar = http_cookiejar.LWPCookieJar()
#print 'cookieJar new',cookieJar
elif 'save[' in m['cookiejar']:
cookie_jar_file = m['cookiejar'].split('save[')[1].split(
']')[0]
complete_path = os.path.join(profile, cookie_jar_file)
# print 'complete_path',complete_path
saveCookieJar(cookieJar, cookie_jar_file)
if m['page'] and '$doregex' in m['page']:
pg = getRegexParsed(regexs,
m['page'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if len(pg) == 0:
pg = 'http://regexfailed'
m['page'] = pg
if 'setcookie' in m and m['setcookie'] and '$doregex' in m[
'setcookie']:
m['setcookie'] = getRegexParsed(regexs,
m['setcookie'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if 'appendcookie' in m and m['appendcookie'] and '$doregex' in m[
'appendcookie']:
m['appendcookie'] = getRegexParsed(regexs,
m['appendcookie'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if 'post' in m and '$doregex' in m['post']:
m['post'] = getRegexParsed(regexs,
m['post'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
# print 'post is now',m['post']
if 'rawpost' in m and '$doregex' in m['rawpost']:
m['rawpost'] = getRegexParsed(regexs,
m['rawpost'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages,
rawPost=True)
#print 'rawpost is now',m['rawpost']
if 'rawpost' in m and '$epoctime$' in m['rawpost']:
m['rawpost'] = m['rawpost'].replace('$epoctime$',
getEpocTime())
if 'rawpost' in m and '$epoctime2$' in m['rawpost']:
m['rawpost'] = m['rawpost'].replace('$epoctime2$',
getEpocTime2())
link = ''
if m['page'] and m[
'page'] in cachedPages and not 'ignorecache' in m and forCookieJarOnly == False:
#print 'using cache page',m['page']
link = cachedPages[m['page']]
else:
if m['page'] and not m['page'] == '' and m['page'].startswith(
'http'):
if '$epoctime$' in m['page']:
m['page'] = m['page'].replace('$epoctime$',
getEpocTime())
if '$epoctime2$' in m['page']:
m['page'] = m['page'].replace('$epoctime2$',
getEpocTime2())
#print 'Ingoring Cache',m['page']
page_split = m['page'].split('|')
pageUrl = page_split[0]
header_in_page = None
if len(page_split) > 1:
header_in_page = page_split[1]
# if
# proxy = urllib_request.ProxyHandler({ ('https' ? proxytouse[:5]=="https":"http") : proxytouse})
# opener = urllib_request.build_opener(proxy)
# urllib_request.install_opener(opener)
# print 'urllib_request.getproxies',urllib_request.getproxies()
current_proxies = urllib_request.ProxyHandler(
urllib_request.getproxies())
#print 'getting pageUrl',pageUrl
req = urllib_request.Request(pageUrl)
if 'proxy' in m:
proxytouse = m['proxy']
# print 'proxytouse',proxytouse
# urllib_request.getproxies= lambda: {}
if pageUrl[:5] == "https":
proxy = urllib_request.ProxyHandler(
{'https': proxytouse})
#req.set_proxy(proxytouse, 'https')
else:
proxy = urllib_request.ProxyHandler(
{'http': proxytouse})
#req.set_proxy(proxytouse, 'http')
opener = urllib_request.build_opener(proxy)
urllib_request.install_opener(opener)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; rv:14.0) Gecko/20100101 Firefox/14.0.1'
)
proxytouse = None
if 'referer' in m:
req.add_header('Referer', m['referer'])
if 'accept' in m:
req.add_header('Accept', m['accept'])
if 'agent' in m:
req.add_header('User-agent', m['agent'])
if 'x-req' in m:
req.add_header('X-Requested-With', m['x-req'])
if 'x-addr' in m:
req.add_header('x-addr', m['x-addr'])
if 'x-forward' in m:
req.add_header('X-Forwarded-For', m['x-forward'])
if 'setcookie' in m:
# print 'adding cookie',m['setcookie']
req.add_header('Cookie', m['setcookie'])
if 'appendcookie' in m:
# print 'appending cookie to cookiejar',m['appendcookie']
cookiestoApend = m['appendcookie']
cookiestoApend = cookiestoApend.split(';')
for h in cookiestoApend:
n, v = h.split('=')
w, n = n.split(':')
ck = http_cookiejar.Cookie(
version=0,
name=n,
value=v,
port=None,
port_specified=False,
domain=w,
domain_specified=False,
domain_initial_dot=False,
path='/',
path_specified=True,
secure=False,
expires=None,
discard=True,
comment=None,
comment_url=None,
rest={'HttpOnly': None},
rfc2109=False)
cookieJar.set_cookie(ck)
if 'origin' in m:
req.add_header('Origin', m['origin'])
if header_in_page:
header_in_page = header_in_page.split('&')
for h in header_in_page:
n, v = h.split('=')
req.add_header(n, v)
if not cookieJar == None:
# print 'cookieJarVal',cookieJar
cookie_handler = urllib_request.HTTPCookieProcessor(
cookieJar)
opener = urllib_request.build_opener(
cookie_handler,
urllib_request.HTTPBasicAuthHandler(),
urllib_request.HTTPHandler())
opener = urllib_request.install_opener(opener)
# print 'noredirect','noredirect' in m
if 'noredirect' in m:
opener = urllib_request.build_opener(
cookie_handler, NoRedirection,
urllib_request.HTTPBasicAuthHandler(),
urllib_request.HTTPHandler())
opener = urllib_request.install_opener(opener)
elif 'noredirect' in m:
opener = urllib_request.build_opener(
NoRedirection,
urllib_request.HTTPBasicAuthHandler(),
urllib_request.HTTPHandler())
opener = urllib_request.install_opener(opener)
if 'connection' in m:
# print '..........................connection//////.',m['connection']
from keepalive import HTTPHandler
keepalive_handler = HTTPHandler()
opener = urllib_request.build_opener(keepalive_handler)
urllib_request.install_opener(opener)
#print 'after cookie jar'
post = None
if 'post' in m:
postData = m['post']
#if '$LiveStreamRecaptcha' in postData:
# (captcha_challenge,catpcha_word,idfield)=processRecaptcha(m['page'],cookieJar)
# if captcha_challenge:
# postData=postData.replace('$LiveStreamRecaptcha','manual_recaptcha_challenge_field:'+captcha_challenge+',recaptcha_response_field:'+catpcha_word+',id:'+idfield)
splitpost = postData.split(',')
post = {}
for p in splitpost:
n = p.split(':')[0]
v = p.split(':')[1]
post[n] = v
post = urllib_parse.urlencode(post)
if 'rawpost' in m:
post = m['rawpost']
#if '$LiveStreamRecaptcha' in post:
# (captcha_challenge,catpcha_word,idfield)=processRecaptcha(m['page'],cookieJar)
# if captcha_challenge:
# post=post.replace('$LiveStreamRecaptcha','&manual_recaptcha_challenge_field='+captcha_challenge+'&recaptcha_response_field='+catpcha_word+'&id='+idfield)
link = ''
try:
if post:
response = urllib_request.urlopen(req, post)
else:
response = urllib_request.urlopen(req)
if response.info().get('Content-Encoding') == 'gzip':
import gzip
buf = six.BytesIO(response.read())
f = gzip.GzipFile(fileobj=buf)
link = f.read()
else:
link = response.read()
if 'proxy' in m and not current_proxies is None:
urllib_request.install_opener(
urllib_request.build_opener(current_proxies))
link = javascriptUnEscape(link)
#print repr(link)
#print link This just print whole webpage in LOG
if 'includeheaders' in m:
#link+=str(response.headers.get('Set-Cookie'))
link += '$$HEADERS_START$$:'
for b in response.headers:
link += b + ':' + response.headers.get(
b) + '\n'
link += '$$HEADERS_END$$:'
# print link
response.close()
except:
pass
cachedPages[m['page']] = link
#print link
#print 'store link for',m['page'],forCookieJarOnly
if forCookieJarOnly:
return cookieJar # do nothing
elif m['page'] and not m['page'].startswith('http'):
if m['page'].startswith('$pyFunction:'):
val = doEval(m['page'].split('$pyFunction:')[1], '',
cookieJar, m)
if forCookieJarOnly:
return cookieJar # do nothing
link = val
link = javascriptUnEscape(link)
else:
link = m['page']
if '$doregex' in m['expres']:
m['expres'] = getRegexParsed(regexs,
m['expres'],
cookieJar,
recursiveCall=True,
cachedPages=cachedPages)
if not m['expres'] == '':
#print 'doing it ',m['expres']
if '$LiveStreamCaptcha' in m['expres']:
val = askCaptcha(m, link, cookieJar)
#print 'url and val',url,val
url = url.replace("$doregex[" + k + "]", val)
elif m['expres'].startswith(
'$pyFunction:') or '#$pyFunction' in m['expres']:
#print 'expeeeeeeeeeeeeeeeeeee',m['expres']
val = ''
if m['expres'].startswith('$pyFunction:'):
val = doEval(m['expres'].split('$pyFunction:')[1],
link, cookieJar, m)
else:
val = doEvalFunction(m['expres'], link, cookieJar, m)
if 'ActivateWindow' in m['expres']: return
if forCookieJarOnly:
return cookieJar # do nothing
if 'listrepeat' in m:
listrepeat = m['listrepeat']
return listrepeat, eval(val), m, regexs, cookieJar
try:
url = url.replace(u"$doregex[" + k + "]", val)
except:
url = url.replace("$doregex[" + k + "]",
six.ensure_text(val))
else:
if 'listrepeat' in m:
listrepeat = m['listrepeat']
ret = re.findall(m['expres'], link)
return listrepeat, ret, m, regexs
val = ''
if not link == '':
#print 'link',link
reg = re.compile(m['expres']).search(link)
try:
val = reg.group(1).strip()
except:
traceback.print_exc()
elif m['page'] == '' or m['page'] == None:
val = m['expres']
if rawPost:
# print 'rawpost'
val = urllib_parse.quote_plus(val)
if 'htmlunescape' in m:
#val=urllib_parse.unquote_plus(val)
import HTMLParser
val = HTMLParser.HTMLParser().unescape(val)
try:
url = url.replace("$doregex[" + k + "]", val)
except:
url = url.replace("$doregex[" + k + "]",
six.ensure_text(val))
#print 'ur',url
#return val
else:
url = url.replace("$doregex[" + k + "]", '')
if '$epoctime$' in url:
url = url.replace('$epoctime$', getEpocTime())
if '$epoctime2$' in url:
url = url.replace('$epoctime2$', getEpocTime2())
if '$GUID$' in url:
import uuid
url = url.replace('$GUID$', str(uuid.uuid1()).upper())
if '$get_cookies$' in url:
url = url.replace('$get_cookies$', getCookiesString(cookieJar))
if recursiveCall: return url
#print 'final url',repr(url)
if url == "":
return
else:
return url, setresolved
