def getUrl(url,
cookieJar=None,
post=None,
timeout=20,
headers=None,
noredir=False):
cookie_handler = urllib_request.HTTPCookieProcessor(cookieJar)
if noredir:
opener = urllib_request.build_opener(
NoRedirection,
cookie_handler, urllib_request.HTTPBasicAuthHandler(),
urllib_request.HTTPHandler())
else:
opener = urllib_request.build_opener(
cookie_handler, urllib_request.HTTPBasicAuthHandler(),
urllib_request.HTTPHandler())
#opener = urllib_request.install_opener(opener)
req = urllib_request.Request(url)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.154 Safari/537.36'
)
if headers:
for h, hv in headers:
req.add_header(h, hv)
response = opener.open(req, post, timeout=timeout)
link = response.read()
response.close()
return link
def get(url, cookiepath=None, cookie=None, user_agent=None, referer=None):
# use cookies if cookiepath is set and if the cookiepath exists.
if cookiepath is not None:
# check if user has supplied only a folder path, or a full path
if not os.path.isfile(cookiepath):
# if the user supplied only a folder path, append on to the end
# of the path a common filename.
cookiepath = os.path.join(cookiepath, 'cookies.lwp')
# check that the cookie exists
if not os.path.exists(cookiepath):
with open(cookiepath, 'w') as f:
f.write('#LWP-Cookies-2.0\n')
cj = http_cookiejar.LWPCookieJar()
cj.load(cookiepath)
req = urllib_request.Request(url)
if user_agent:
req.add_header('User-Agent', user_agent)
else:
req.add_header('User-Agent', USER_AGENT_STRING)
if referer:
req.add_header('Referer', referer)
if cookie:
req.add_header('Cookie', cookie)
opener = urllib_request.build_opener(urllib_request.HTTPCookieProcessor(cj))
try:
response = opener.open(req)
except urllib_error.URLError as e:
xbmc.log('%s Error opening %s' % (e, url))
sys.exit(1)
link = response.read()
response.close()
return link
else:
return _loadwithoutcookies(url, user_agent)
def _update_opener(self, drop_tls_level=False):
"""
Builds and installs a new opener to be used by all future calls to
:func:`urllib2.urlopen`.
"""
handlers = [
urllib_request.HTTPCookieProcessor(self._cj),
urllib_request.HTTPBasicAuthHandler()
]
if self._http_debug:
handlers += [urllib_request.HTTPHandler(debuglevel=1)]
else:
handlers += [urllib_request.HTTPHandler()]
if self._proxy:
handlers += [urllib_request.ProxyHandler({'http': self._proxy})]
try:
import platform
node = platform.node().lower()
except:
node = ''
if not self._ssl_verify or node == 'xboxone':
try:
import ssl
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE
if self._http_debug:
handlers += [
urllib_request.HTTPSHandler(context=ctx, debuglevel=1)
]
else:
handlers += [urllib_request.HTTPSHandler(context=ctx)]
except:
pass
else:
try:
import ssl
import certifi
ctx = ssl.create_default_context(cafile=certifi.where())
if drop_tls_level:
ctx.protocol = ssl.PROTOCOL_TLSv1_1
if self._http_debug:
handlers += [
urllib_request.HTTPSHandler(context=ctx, debuglevel=1)
]
else:
handlers += [urllib_request.HTTPSHandler(context=ctx)]
except:
pass
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
def _update_opener(self):
'''
Builds and installs a new opener to be used by all future calls to
:func:`urllib2.urlopen`.
'''
if self._http_debug:
http = urllib_request.HTTPHandler(debuglevel=1)
else:
http = urllib_request.HTTPHandler()
if self._proxy:
opener = urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(self._cj),
urllib_request.ProxyHandler({'http': self._proxy}),
urllib_request.HTTPBasicAuthHandler(), http)
else:
opener = urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(self._cj),
urllib_request.HTTPBasicAuthHandler(), http)
urllib_request.install_opener(opener)
def getUrl(url, proxy={}, timeout=TIMEOUT, cookies=True):
global cs
cookie = []
if proxy:
urllib_request.install_opener(
urllib_request.build_opener(urllib_request.ProxyHandler(proxy)))
elif cookies:
cookie = http_cookiejar.LWPCookieJar()
opener = urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(cookie))
urllib_request.install_opener(opener)
req = urllib_request.Request(url)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36'
)
try:
response = urllib_request.urlopen(req, timeout=timeout)
linkSRC = response.read()
response.close()
except:
linkSRC = ''
cs = ''.join(['%s=%s;' % (c.name, c.value) for c in cookie])
return linkSRC
def request(url,
close=True,
redirect=True,
error=False,
proxy=None,
post=None,
headers=None,
mobile=False,
limit=None,
referer=None,
cookie=None,
output='',
timeout='30'):
handlers = []
if proxy is not None:
handlers += [
ProxyHandler({'http': '{0}'.format(proxy)}),
urllib_request.HTTPHandler
]
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
if output == 'cookie' or output == 'extended' or close is not True:
cookies = cookielib.LWPCookieJar()
handlers += [
urllib_request.HTTPHandler(),
urllib_request.HTTPSHandler(),
urllib_request.HTTPCookieProcessor(cookies)
]
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
try:
if sys.version_info < (2, 7, 9):
raise Exception()
import ssl
ssl_context = ssl.create_default_context()
ssl_context.check_hostname = False
ssl_context.verify_mode = ssl.CERT_NONE
handlers += [urllib_request.HTTPSHandler(context=ssl_context)]
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
except:
pass
try:
headers.update(headers)
except:
headers = {}
if 'User-Agent' in headers:
pass
elif not mobile is True:
# headers['User-Agent'] = agent()
headers['User-Agent'] = cache.get(randomagent, 1)
else:
headers['User-Agent'] = 'Apple-iPhone/701.341'
if 'Referer' in headers:
pass
elif referer is None:
headers['Referer'] = '%s://%s/' % (urlparse(url).scheme,
urlparse(url).netloc)
else:
headers['Referer'] = referer
if not 'Accept-Language' in headers:
headers['Accept-Language'] = 'en-US'
if 'Cookie' in headers:
pass
elif cookie is not None:
headers['Cookie'] = cookie
if redirect is False:
class NoRedirection(urllib_error.HTTPError):
def http_response(self, request, response):
return response
opener = urllib_request.build_opener(NoRedirection)
urllib_request.install_opener(opener)
try:
del headers['Referer']
except:
pass
req = urllib_request.Request(url, data=post, headers=headers)
try:
response = urllib_request.urlopen(req, timeout=int(timeout))
except urllib_error.HTTPError as response:
if response.code == 503:
if 'cf-browser-verification' in response.read(5242880):
netloc = '%s://%s' % (urlparse(url).scheme,
urlparse(url).netloc)
cf = cache.get(cfcookie, 168, netloc, headers['User-Agent'],
timeout)
headers['Cookie'] = cf
request = urllib_request.Request(url,
data=post,
headers=headers)
response = urllib_request.urlopen(request,
timeout=int(timeout))
elif error is False:
return
elif error is False:
return
if output == 'cookie':
try:
result = '; '.join(['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
result = cf
except:
pass
elif output == 'response':
if limit == '0':
result = (str(response.code), response.read(224 * 1024))
elif limit is not None:
result = (str(response.code), response.read(int(limit) * 1024))
else:
result = (str(response.code), response.read(5242880))
elif output == 'chunk':
try:
content = int(response.headers['Content-Length'])
except:
content = (2049 * 1024)
if content < (2048 * 1024):
return
result = response.read(16 * 1024)
elif output == 'extended':
try:
cookie = '; '.join(['%s=%s' % (i.name, i.value) for i in cookies])
except:
pass
try:
cookie = cf
except:
pass
content = response.headers
result = response.read(5242880)
return result, headers, content, cookie
elif output == 'geturl':
result = response.geturl()
elif output == 'headers':
content = response.headers
return content
else:
if limit == '0':
result = response.read(224 * 1024)
elif limit is not None:
result = response.read(int(limit) * 1024)
else:
result = response.read(5242880)
if close is True:
response.close()
return result
def cfcookie(netloc, ua, timeout):
try:
headers = {'User-Agent': ua}
req = urllib_request.Request(netloc, headers=headers)
try:
urllib_request.urlopen(req, timeout=int(timeout))
except urllib_request.HTTPError as response:
result = response.read(5242880)
jschl = re.findall('name="jschl_vc" value="(.+?)"/>', result)[0]
init = re.findall('setTimeout\(function\(\){\s*.*?.*:(.*?)};',
result)[-1]
builder = re.findall(r"challenge-form\'\);\s*(.*)a.v", result)[0]
decryptVal = parseJSString(init)
lines = builder.split(';')
for line in lines:
if len(line) > 0 and '=' in line:
sections = line.split('=')
line_val = parseJSString(sections[1])
decryptVal = int(
eval(str(decryptVal) + sections[0][-1] + str(line_val)))
answer = decryptVal + len(urlparse.urlparse(netloc).netloc)
query = '%s/cdn-cgi/l/chk_jschl?jschl_vc=%s&jschl_answer=%s' % (
netloc, jschl, answer)
if 'type="hidden" name="pass"' in result:
passval = re.findall('name="pass" value="(.*?)"', result)[0]
query = '%s/cdn-cgi/l/chk_jschl?pass=%s&jschl_vc=%s&jschl_answer=%s' % (
netloc, quote_plus(passval), jschl, answer)
time.sleep(5)
cookies = cookielib.LWPCookieJar()
handlers = [
urllib_request.HTTPHandler(),
urllib_request.HTTPSHandler(),
urllib_request.HTTPCookieProcessor(cookies)
]
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
try:
request = urllib_request.Request(query, headers=headers)
urllib_request.urlopen(request, timeout=int(timeout))
except:
pass
cookie = '; '.join(['%s=%s' % (i.name, i.value) for i in cookies])
return cookie
except:
pass
def solve(url, cj, user_agent=None, wait=True):
if user_agent is None:
user_agent = USER_AGENT
headers = {'User-Agent': user_agent, 'Referer': url}
if cj is not None:
try:
cj.load(ignore_discard=True)
except:
pass
opener = urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(cj))
urllib_request.install_opener(opener)
request = urllib_request.Request(url)
for key in headers:
request.add_header(key, headers[key])
try:
response = urllib_request.urlopen(request)
html = response.read()
except urllib_error.HTTPError as e:
html = e.read()
tries = 0
while tries < MAX_TRIES:
solver_pattern = r'var (?:s,t,o,p,b,r,e,a,k,i,n,g|t,r,a),f,\s*([^=]+)={"([^"]+)":([^}]+)};.+challenge-form\'\);.*?\n.*?;(.*?);a\.value'
vc_pattern = 'input type="hidden" name="jschl_vc" value="([^"]+)'
pass_pattern = 'input type="hidden" name="pass" value="([^"]+)'
init_match = re.search(solver_pattern, html, re.DOTALL)
vc_match = re.search(vc_pattern, html)
pass_match = re.search(pass_pattern, html)
if not init_match or not vc_match or not pass_match:
xbmc.log(
"Couldn't find attribute: init: |%s| vc: |%s| pass: |%s| No cloudflare check?"
% (init_match, vc_match, pass_match))
return False
init_dict, init_var, init_equation, equations = init_match.groups()
vc = vc_match.group(1)
password = pass_match.group(1)
# log_utils.log("VC is: %s" % (vc), xbmc.LOGDEBUG, COMPONENT)
varname = (init_dict, init_var)
result = int(solve_equation(init_equation.rstrip()))
xbmc.log('Initial value: |%s| Result: |%s|' % (init_equation, result))
for equation in equations.split(';'):
equation = equation.rstrip()
if equation[:len('.'.join(varname))] != '.'.join(varname):
xbmc.log('Equation does not start with varname |%s|' %
(equation))
else:
equation = equation[len('.'.join(varname)):]
expression = equation[2:]
operator = equation[0]
if operator not in ['+', '-', '*', '/']:
# log_utils.log('Unknown operator: |%s|' % (equation), log_utils.LOGWARNING, COMPONENT)
continue
result = int(
str(
eval(
str(result) + operator +
str(solve_equation(expression)))))
# log_utils.log('intermediate: %s = %s' % (equation, result), log_utils.LOGDEBUG, COMPONENT)
scheme = urllib_parse.urlparse(url).scheme
domain = urllib_parse.urlparse(url).hostname
result += len(domain)
# log_utils.log('Final Result: |%s|' % (result), log_utils.LOGDEBUG, COMPONENT)
if wait:
# log_utils.log('Sleeping for 5 Seconds', log_utils.LOGDEBUG, COMPONENT)
xbmc.sleep(5000)
url = '%s://%s/cdn-cgi/l/chk_jschl?jschl_vc=%s&jschl_answer=%s&pass=%s' % (
scheme, domain, vc, result, urllib_parse.quote(password))
# log_utils.log('url: %s' % (url), log_utils.LOGDEBUG, COMPONENT)
request = urllib_request.Request(url)
for key in headers:
request.add_header(key, headers[key])
try:
opener = urllib_request.build_opener(NoRedirection)
urllib_request.install_opener(opener)
response = urllib_request.urlopen(request)
while response.getcode() in [301, 302, 303, 307]:
if cj is not None:
cj.extract_cookies(response, request)
redir_url = response.info().getheader('location')
if not redir_url.startswith('http'):
base_url = '%s://%s' % (scheme, domain)
redir_url = urllib_parse.urljoin(base_url, redir_url)
request = urllib_request.Request(redir_url)
for key in headers:
request.add_header(key, headers[key])
if cj is not None:
cj.add_cookie_header(request)
response = urllib_request.urlopen(request)
final = response.read()
if 'cf-browser-verification' in final:
# log_utils.log('CF Failure: html: %s url: %s' % (html, url), log_utils.LOGWARNING, COMPONENT)
tries += 1
html = final
else:
break
except urllib_error.HTTPError as e:
# log_utils.log('CloudFlare HTTP Error: %s on url: %s' % (e.code, url), log_utils.LOGWARNING, COMPONENT)
return False
except urllib_error.URLError as e:
# log_utils.log('CloudFlare URLError Error: %s on url: %s' % (e, url), log_utils.LOGWARNING, COMPONENT)
return False
if cj is not None:
cj.save()
return final
def read_body_and_headers(url,
post=None,
headers=[],
follow_redirects=False,
timeout=None):
xbmc.log("read_body_and_headers " + url, 2)
if len(headers) == 0:
headers.append([
"User-Agent",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:18.0) Gecko/20100101 Firefox/18.0"
])
# Start cookie lib
ficherocookies = os.path.join(get_data_path(), 'cookies.dat')
_log("read_body_and_headers cookies_file=" + ficherocookies)
cj = None
ClientCookie = None
cookielib = None
# Let's see if cookielib is available
try:
_log("read_body_and_headers importing cookielib")
import cookielib
except ImportError:
_log("read_body_and_headers cookielib no disponible")
# If importing cookielib fails
# let's try ClientCookie
try:
_log("read_body_and_headers importing ClientCookie")
import ClientCookie
except ImportError:
_log("read_body_and_headers ClientCookie not available")
# ClientCookie isn't available either
urlopen = urllib_request.urlopen
Request = urllib_request.Request
else:
_log("read_body_and_headers ClientCookie available")
# imported ClientCookie
urlopen = ClientCookie.urlopen
Request = ClientCookie.Request
cj = ClientCookie.MozillaCookieJar()
else:
_log("read_body_and_headers cookielib available")
# importing cookielib worked
urlopen = urllib_request.urlopen
Request = urllib_request.Request
cj = cookielib.MozillaCookieJar()
# This is a subclass of FileCookieJar
# that has useful load and save methods
if cj is not None:
# we successfully imported
# one of the two cookie handling modules
_log("read_body_and_headers Cookies enabled")
if os.path.isfile(ficherocookies):
_log("read_body_and_headers Reading cookie file")
# if we have a cookie file already saved
# then load the cookies into the Cookie Jar
try:
cj.load(ficherocookies)
except:
_log("read_body_and_headers Wrong cookie file, deleting...")
os.remove(ficherocookies)
# Now we need to get our Cookie Jar
# installed in the opener;
# for fetching URLs
if cookielib is not None:
_log(
"read_body_and_headers opener using urllib_request (cookielib)"
)
# if we use cookielib
# then we get the HTTPCookieProcessor
# and install the opener in urllib_request
if not follow_redirects:
opener = urllib_request.build_opener(
urllib_request.HTTPHandler(
debuglevel=http_debug_log_enabled),
urllib_request.HTTPCookieProcessor(cj),
NoRedirectHandler())
else:
opener = urllib_request.build_opener(
urllib_request.HTTPHandler(
debuglevel=http_debug_log_enabled),
urllib_request.HTTPCookieProcessor(cj))
urllib_request.install_opener(opener)
else:
_log("read_body_and_headers opener using ClientCookie")
# if we use ClientCookie
# then we get the HTTPCookieProcessor
# and install the opener in ClientCookie
opener = ClientCookie.build_opener(
ClientCookie.HTTPCookieProcessor(cj))
ClientCookie.install_opener(opener)
# -------------------------------------------------
# Cookies instaladas, lanza la petición
# -------------------------------------------------
# Contador
inicio = time.time()
# Diccionario para las cabeceras
txheaders = {}
if type(post) == dict: post = urlencode(post)
if post:
if isinstance(post, unicode):
post = post.encode('utf-8', 'strict')
if post is None:
_log("read_body_and_headers GET request")
else:
_log("read_body_and_headers POST request")
# Añade las cabeceras
_log("read_body_and_headers ---------------------------")
for header in headers:
_log("read_body_and_headers header %s=%s" %
(str(header[0]), str(header[1])))
txheaders[header[0]] = header[1]
_log("read_body_and_headers ---------------------------")
if post and six.PY3:
post = six.ensure_binary(post)
req = Request(url, post, txheaders)
if timeout is None:
handle = urlopen(req)
else:
#Disponible en python 2.6 en adelante --> handle = urlopen(req, timeout=timeout)
#Para todas las versiones:
try:
import socket
deftimeout = socket.getdefaulttimeout()
socket.setdefaulttimeout(timeout)
handle = urlopen(req)
socket.setdefaulttimeout(deftimeout)
except:
import sys
for line in sys.exc_info():
_log("%s" % line)
# Actualiza el almacén de cookies
if cj: cj.save(ficherocookies)
# Lee los datos y cierra
if handle.info().get('Content-Encoding') == 'gzip':
buf = BytesIO(handle.read())
f = gzip.GzipFile(fileobj=buf)
data = f.read()
else:
data = handle.read()
info = handle.info()
_log("read_body_and_headers Response")
returnheaders = []
_log("read_body_and_headers ---------------------------")
for header in info:
_log("read_body_and_headers " + header + "=" + info[header])
returnheaders.append([header, info[header]])
handle.close()
_log("read_body_and_headers ---------------------------")
'''
# Lanza la petición
try:
response = urllib_request.urlopen(req)
# Si falla la repite sustituyendo caracteres especiales
except:
req = urllib_request.Request(url.replace(" ","%20"))
# Añade las cabeceras
for header in headers:
req.add_header(header[0],header[1])
response = urllib_request.urlopen(req)
'''
# Tiempo transcurrido
fin = time.time()
_log("read_body_and_headers Downloaded in %d seconds " %
(fin - inicio + 1))
if not isinstance(data, str):
try:
data = data.decode("utf-8", "strict")
except:
data = str(data)
return data, returnheaders
def doLogin(cookiepath, username, password):
#check if user has supplied only a folder path, or a full path
if not os.path.isfile(cookiepath):
# if the user supplied only a folder path, append on to the end of the
# path a filename.
cookiepath = os.path.join(cookiepath, 'cookies.lwp')
#delete any old version of the cookie file
try:
os.remove(cookiepath)
except:
pass
if username and password:
#the url you will request to.
login_url = 'https://fantasti.cc/signin.php'
#the header used to pretend you are a browser
header_string = 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-GB; rv:1.9.0.3) Gecko/2008092417 Firefox/3.0.3'
#build the form data necessary for the login
login_data = urllib_parse.urlencode({
'user': username,
'pass': password,
'memento': 1,
'x': 0,
'y': 0,
'do': 'login',
'SSO': ''
})
#build the request we will make
req = urllib_request.Request(login_url)
req.add_header('User-Agent', header_string)
#initiate the cookielib class
cj = http_cookiejar.LWPCookieJar()
# Setup no redirects
class NoRedirection(urllib_request.HTTPRedirectHandler):
def redirect_request(self, req, fp, code, msg, headers, newurl):
return None
#install cookielib into the url opener, so that cookies are handled
opener = urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(cj), NoRedirection())
urllib_request.install_opener(opener)
#do the login and get the response
try:
source = urllib_request.urlopen(req, login_data.encode()).read()
except urllib_error.HTTPError as e:
source = e.read()
#check the received html for a string that will tell us if the user is
# logged in
#pass the username, which can be used to do this.
login, avatar = check_login(source, username)
#if login suceeded, save the cookiejar to disk
if login:
cj.save(cookiepath)
#return whether we are logged in or not
return (login, avatar)
else:
return (False, False)
kodilog('Failed String Lookup: %s (%s)' % (string_id, e))
return string_id
if cj is not None:
if os.path.isfile(TRANSLATEPATH(cookiePath)):
try:
cj.load(ignore_discard=True)
except:
try:
xbmcvfs.delete(TRANSLATEPATH(cookiePath))
pass
except:
dialog.ok(i18n('oh_oh'), i18n('cookie_lock'))
pass
cookie_handler = urllib_request.HTTPCookieProcessor(cj)
handlers += [cookie_handler]
opener = urllib_request.build_opener(*handlers)
urllib_request.install_opener(opener)
class StopDownloading(Exception):
def __init__(self, value):
self.value = value
def __str__(self):
return repr(self.value)
def downloadVideo(url, name):
CODEC_UNKNOWN = 0
CODEC_XVID = 1
CODEC_H264 = 2
CODEC_H265 = 3
CODEC_MP3 = 4
CODEC_AAC = 5
CODEC_AC3 = 6
CODEC_DTS = 7
CODEC_DTSHD = 8
CODEC_DTSHDMA = 9
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.66 Safari/537.36"
COOKIE_JAR = CookieJar()
urllib_request.install_opener(urllib_request.build_opener(urllib_request.HTTPCookieProcessor(COOKIE_JAR)))
class closing(object):
def __init__(self, thing):
self.thing = thing
def __enter__(self):
return self.thing
def __exit__(self, *exc_info):
self.thing.close()
def parse_json(data):
try:
import simplejson as json
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
CODEC_XVID = 1
CODEC_H264 = 2
CODEC_H265 = 3
CODEC_MP3 = 4
CODEC_AAC = 5
CODEC_AC3 = 6
CODEC_DTS = 7
CODEC_DTSHD = 8
CODEC_DTSHDMA = 9
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.66 Safari/537.36"
COOKIE_JAR = CookieJar()
urllib_request.install_opener(
urllib_request.build_opener(
urllib_request.HTTPCookieProcessor(COOKIE_JAR)))
class closing(object):
def __init__(self, thing):
self.thing = thing
def __enter__(self):
return self.thing
def __exit__(self, *exc_info):
self.thing.close()
def parse_json(data):
try:
def downloadpage(url, post=None, headers=None, timeout=None, follow_redirects=True, cookies=True, replace_headers=False,
add_referer=False, only_headers=False, bypass_cloudflare=True, bypass_testcookie=True, no_decode=False,
method=None, cache=CACHE_ENABLED, cache_expiration=CACHE_EXPIRATION):
"""
Descarga una página web y devuelve los resultados
:type url: str
:type post: dict, str
:type headers: dict, list
:type timeout: int
:type follow_redirects: bool
:type cookies: bool, dict
:type replace_headers: bool
:type add_referer: bool
:type only_headers: bool
:type bypass_cloudflare: bool
:type cache: bool
:type cache_expiration: timedelta
:return: Resultado
"""
arguments = locals().copy()
if cache:
try:
cache_key = '|'.join(["%s:%s" %(k,v) for k,v in sorted(arguments.items(),key= lambda x: x[0]) if v]).encode()
cache_key = CACHE_PREFIX + hashlib.sha1(cache_key).hexdigest()
cacheado = CACHE.get(cache_key)
if cacheado:
return HTTPResponse(cacheado)
except:
pass
response = {}
# Post tipo dict
if type(post) == dict:
post = urllib_parse.urlencode(post)
# Url quote
url = urllib_parse.quote(url, safe="%/:=&?~#+!$,;'@()*[]")
# Headers por defecto, si no se especifica nada
request_headers = default_headers.copy()
# Headers pasados como parametros
if headers is not None:
if not replace_headers:
request_headers.update(dict(headers))
else:
request_headers = dict(headers)
# Referer
if add_referer:
request_headers["Referer"] = "/".join(url.split("/")[:3])
#logger("Headers:")
#logger(request_headers, 'info')
# Handlers
handlers = list()
handlers.append(HTTPHandler(debuglevel=False))
handlers.append(HTTPSHandler(debuglevel=False))
handlers.append(urllib_request.HTTPBasicAuthHandler())
# No redirects
if not follow_redirects:
handlers.append(NoRedirectHandler())
else:
handlers.append(HTTPRedirectHandler())
# Dict con cookies para la sesión
if type(cookies) == dict:
for name, value in cookies.items():
if not type(value) == dict:
value = {'value': value}
ck = Cookie(
version=0,
name=name,
value=value.get('value', ''),
port=None,
port_specified=False,
domain=value.get('domain', urllib_parse.urlparse(url)[1]),
domain_specified=False,
domain_initial_dot=False,
path=value.get('path', '/'),
path_specified=True,
secure=False,
expires=value.get('expires', time.time() + 3600 * 24),
discard=True,
comment=None,
comment_url=None,
rest={'HttpOnly': None},
rfc2109=False
)
cj.set_cookie(ck)
if cookies:
handlers.append(urllib_request.HTTPCookieProcessor(cj))
# Opener
opener = urllib_request.build_opener(*handlers)
# Contador
inicio = time.time()
# Request
req = Request(url, six.ensure_binary(post) if post else None, request_headers, method=method)
try:
#logger("Realizando Peticion")
handle = opener.open(req, timeout=timeout)
#logger('Peticion realizada')
except HTTPError as handle:
#logger('Peticion realizada con error')
response["sucess"] = False
response["code"] = handle.code
response["error"] = handle.__dict__.get("reason", str(handle))
response["headers"] = dict(handle.headers.items())
response['cookies'] = get_cookies(urllib_parse.urlparse(url)[1])
if not only_headers:
#logger('Descargando datos...')
response["data"] = handle.read()
else:
response["data"] = b""
response["time"] = time.time() - inicio
response["url"] = handle.geturl()
except Exception as e:
#logger('Peticion NO realizada')
response["sucess"] = False
response["code"] = e.__dict__.get("errno", e.__dict__.get("code", str(e)))
response["error"] = e.__dict__.get("reason", str(e))
response["headers"] = {}
response['cookies'] = get_cookies(urllib_parse.urlparse(url)[1])
response["data"] = b""
response["time"] = time.time() - inicio
response["url"] = url
else:
response["sucess"] = True
response["code"] = handle.code
response["error"] = None
response["headers"] = dict(handle.headers.items())
response['cookies'] = get_cookies(urllib_parse.urlparse(url)[1])
if not only_headers:
#logger('Descargando datos...')
response["data"] = handle.read()
else:
response["data"] = b""
response["time"] = time.time() - inicio
response["url"] = handle.geturl()
response['headers'] = dict([(k.lower(), v) for k, v in response['headers'].items()])
#logger("Terminado en %.2f segundos" % (response["time"]))
#logger("url: %s" % url)
#logger("Response sucess : %s" % (response["sucess"]))
#logger("Response code : %s" % (response["code"]))
#logger("Response error : %s" % (response["error"]))
#logger("Response cookies : %s" % (response["cookies"]))
#logger("Response data length: %s" % (len(response["data"])))
#logger("Response headers:")
#logger(response['headers'])
# Guardamos las cookies
if cookies:
save_cookies()
# Gzip
if response["headers"].get('content-encoding') == 'gzip':
response["data"] = gzip.GzipFile(fileobj=BytesIO(response["data"])).read()
# Binarios no se codifican ni se comprueba cloudflare, etc...
if not is_binary(response):
response['data'] = six.ensure_str(response['data'], errors='replace')
if not no_decode:
response["data"] = six.ensure_str(HTMLParser().unescape(
six.ensure_text(response['data'], errors='replace')
))
# Anti TestCookie
if bypass_testcookie:
if 'document.cookie="__test="+toHex(slowAES.decrypt(c,2,a,b))+"' in response['data']:
a = re.findall('a=toNumbers\("([^"]+)"\)', response['data'])[0].decode("HEX")
b = re.findall('b=toNumbers\("([^"]+)"\)', response['data'])[0].decode("HEX")
c = re.findall('c=toNumbers\("([^"]+)"\)', response['data'])[0].decode("HEX")
arguments['bypass_testcookie'] = False
if not type(arguments['cookies']) == dict:
arguments['cookies'] = {'__test': ii11.new(a, ii11.MODE_CBC, b).decrypt(c).encode("HEX")}
else:
arguments['cookies']['__test'] = ii11.new(a, ii11.MODE_CBC, b).decrypt(c).encode("HEX")
response = downloadpage(**arguments).__dict__
# Anti Cloudflare
if bypass_cloudflare:
response = retry_if_cloudflare(response, arguments)
if cache:
CACHE.set(cache_key, response, expiration=cache_expiration)
return HTTPResponse(response)
