summaryrefslogtreecommitdiffstats
path: root/module/plugins/internal
diff options
context:
space:
mode:
Diffstat (limited to 'module/plugins/internal')
-rw-r--r--module/plugins/internal/Account.py292
-rw-r--r--module/plugins/internal/AdYouLike.py91
-rw-r--r--module/plugins/internal/AdsCaptcha.py63
-rw-r--r--module/plugins/internal/Captcha.py56
-rw-r--r--module/plugins/internal/CaptchaService.py353
-rw-r--r--module/plugins/internal/Container.py75
-rw-r--r--module/plugins/internal/Crypter.py72
-rw-r--r--module/plugins/internal/DeadCrypter.py15
-rw-r--r--module/plugins/internal/DeadHoster.py15
-rw-r--r--module/plugins/internal/Extractor.py118
-rw-r--r--module/plugins/internal/Hook.py161
-rw-r--r--module/plugins/internal/Hoster.py33
-rw-r--r--module/plugins/internal/MultiHook.py158
-rw-r--r--module/plugins/internal/MultiHoster.py85
-rw-r--r--module/plugins/internal/Plugin.py598
-rw-r--r--module/plugins/internal/ReCaptcha.py195
-rw-r--r--module/plugins/internal/SevenZip.py153
-rw-r--r--module/plugins/internal/SimpleCrypter.py88
-rw-r--r--module/plugins/internal/SimpleDereferer.py99
-rw-r--r--module/plugins/internal/SimpleHoster.py583
-rw-r--r--module/plugins/internal/SolveMedia.py104
-rw-r--r--module/plugins/internal/UnRar.py258
-rw-r--r--module/plugins/internal/UnZip.py76
-rw-r--r--module/plugins/internal/XFSAccount.py61
-rw-r--r--module/plugins/internal/XFSCrypter.py27
-rw-r--r--module/plugins/internal/XFSHoster.py177
26 files changed, 2829 insertions, 1177 deletions
diff --git a/module/plugins/internal/Account.py b/module/plugins/internal/Account.py
new file mode 100644
index 000000000..7632d15c2
--- /dev/null
+++ b/module/plugins/internal/Account.py
@@ -0,0 +1,292 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: mkaay
+"""
+
+from random import choice
+from time import time
+from traceback import print_exc
+from threading import RLock
+
+from Plugin import Base
+from module.utils import compare_time, parseFileSize, lock
+
+class WrongPassword(Exception):
+ pass
+
+
+class Account(Base):
+ """
+ Base class for every Account plugin.
+ Just overwrite `login` and cookies will be stored and account becomes accessible in\
+ associated hoster plugin. Plugin should also provide `loadAccountInfo`
+ """
+ __name__ = "Account"
+ __version__ = "0.02"
+ __type__ = "account"
+ __description__ = """Account Plugin"""
+ __author_name__ = ("mkaay")
+ __author_mail__ = ("mkaay@mkaay.de")
+
+ #: after that time [in minutes] pyload will relogin the account
+ login_timeout = 600
+ #: account data will be reloaded after this time
+ info_threshold = 600
+
+
+ def __init__(self, manager, accounts):
+ Base.__init__(self, manager.core)
+
+ self.manager = manager
+ self.accounts = {}
+ self.infos = {} # cache for account information
+ self.lock = RLock()
+
+ self.timestamps = {}
+ self.setAccounts(accounts)
+ self.init()
+
+ def init(self):
+ pass
+
+ def login(self, user, data, req):
+ """login into account, the cookies will be saved so user can be recognized
+
+ :param user: loginname
+ :param data: data dictionary
+ :param req: `Request` instance
+ """
+ pass
+
+ @lock
+ def _login(self, user, data):
+ # set timestamp for login
+ self.timestamps[user] = time()
+
+ req = self.getAccountRequest(user)
+ try:
+ self.login(user, data, req)
+ except WrongPassword:
+ self.logWarning(
+ _("Could not login with account %(user)s | %(msg)s") % {"user": user
+ , "msg": _("Wrong Password")})
+ data["valid"] = False
+
+ except Exception, e:
+ self.logWarning(
+ _("Could not login with account %(user)s | %(msg)s") % {"user": user
+ , "msg": e})
+ data["valid"] = False
+ if self.core.debug:
+ print_exc()
+ finally:
+ if req: req.close()
+
+ def relogin(self, user):
+ req = self.getAccountRequest(user)
+ if req:
+ req.cj.clear()
+ req.close()
+ if user in self.infos:
+ del self.infos[user] #delete old information
+
+ self._login(user, self.accounts[user])
+
+ def setAccounts(self, accounts):
+ self.accounts = accounts
+ for user, data in self.accounts.iteritems():
+ self._login(user, data)
+ self.infos[user] = {}
+
+ def updateAccounts(self, user, password=None, options={}):
+ """ updates account and return true if anything changed """
+
+ if user in self.accounts:
+ self.accounts[user]["valid"] = True #do not remove or accounts will not login
+ if password:
+ self.accounts[user]["password"] = password
+ self.relogin(user)
+ return True
+ if options:
+ before = self.accounts[user]["options"]
+ self.accounts[user]["options"].update(options)
+ return self.accounts[user]["options"] != before
+ else:
+ self.accounts[user] = {"password": password, "options": options, "valid": True}
+ self._login(user, self.accounts[user])
+ return True
+
+ def removeAccount(self, user):
+ if user in self.accounts:
+ del self.accounts[user]
+ if user in self.infos:
+ del self.infos[user]
+ if user in self.timestamps:
+ del self.timestamps[user]
+
+ @lock
+ def getAccountInfo(self, name, force=False):
+ """retrieve account infos for an user, do **not** overwrite this method!\\
+ just use it to retrieve infos in hoster plugins. see `loadAccountInfo`
+
+ :param name: username
+ :param force: reloads cached account information
+ :return: dictionary with information
+ """
+ data = Account.loadAccountInfo(self, name)
+
+ if force or name not in self.infos:
+ self.logDebug("Get Account Info for %s" % name)
+ req = self.getAccountRequest(name)
+
+ try:
+ infos = self.loadAccountInfo(name, req)
+ if not type(infos) == dict:
+ raise Exception("Wrong return format")
+ except Exception, e:
+ infos = {"error": str(e)}
+
+ if req: req.close()
+
+ self.logDebug("Account Info: %s" % str(infos))
+
+ infos["timestamp"] = time()
+ self.infos[name] = infos
+ elif "timestamp" in self.infos[name] and self.infos[name][
+ "timestamp"] + self.info_threshold * 60 < time():
+ self.logDebug("Reached timeout for account data")
+ self.scheduleRefresh(name)
+
+ data.update(self.infos[name])
+ return data
+
+ def isPremium(self, user):
+ info = self.getAccountInfo(user)
+ return info["premium"]
+
+ def loadAccountInfo(self, name, req=None):
+ """this should be overwritten in account plugin,\
+ and retrieving account information for user
+
+ :param name:
+ :param req: `Request` instance
+ :return:
+ """
+ return {
+ "validuntil": None, # -1 for unlimited
+ "login": name,
+ #"password": self.accounts[name]["password"], #@XXX: security
+ "options": self.accounts[name]["options"],
+ "valid": self.accounts[name]["valid"],
+ "trafficleft": None, # in kb, -1 for unlimited
+ "maxtraffic": None,
+ "premium": True, #useful for free accounts
+ "timestamp": 0, #time this info was retrieved
+ "type": self.__name__,
+ }
+
+ def getAllAccounts(self, force=False):
+ return [self.getAccountInfo(user, force) for user, data in self.accounts.iteritems()]
+
+ def getAccountRequest(self, user=None):
+ if not user:
+ user, data = self.selectAccount()
+ if not user:
+ return None
+
+ req = self.core.requestFactory.getRequest(self.__name__, user)
+ return req
+
+ def getAccountCookies(self, user=None):
+ if not user:
+ user, data = self.selectAccount()
+ if not user:
+ return None
+
+ cj = self.core.requestFactory.getCookieJar(self.__name__, user)
+ return cj
+
+ def getAccountData(self, user):
+ return self.accounts[user]
+
+ def selectAccount(self):
+ """ returns an valid account name and data"""
+ usable = []
+ for user, data in self.accounts.iteritems():
+ if not data["valid"]: continue
+
+ if "time" in data["options"] and data["options"]["time"]:
+ time_data = ""
+ try:
+ time_data = data["options"]["time"][0]
+ start, end = time_data.split("-")
+ if not compare_time(start.split(":"), end.split(":")):
+ continue
+ except:
+ self.logWarning(_("Your Time %s has wrong format, use: 1:22-3:44") % time_data)
+
+ if user in self.infos:
+ if "validuntil" in self.infos[user]:
+ if self.infos[user]["validuntil"] > 0 and time() > self.infos[user]["validuntil"]:
+ continue
+ if "trafficleft" in self.infos[user]:
+ if self.infos[user]["trafficleft"] == 0:
+ continue
+
+ usable.append((user, data))
+
+ if not usable: return None, None
+ return choice(usable)
+
+ def canUse(self):
+ return False if self.selectAccount() == (None, None) else True
+
+ def parseTraffic(self, string): #returns kbyte
+ return parseFileSize(string) / 1024
+
+ def wrongPassword(self):
+ raise WrongPassword
+
+ def empty(self, user):
+ if user in self.infos:
+ self.logWarning(_("Account %s has not enough traffic, checking again in 30min") % user)
+
+ self.infos[user].update({"trafficleft": 0})
+ self.scheduleRefresh(user, 30 * 60)
+
+ def expired(self, user):
+ if user in self.infos:
+ self.logWarning(_("Account %s is expired, checking again in 1h") % user)
+
+ self.infos[user].update({"validuntil": time() - 1})
+ self.scheduleRefresh(user, 60 * 60)
+
+ def scheduleRefresh(self, user, time=0, force=True):
+ """ add task to refresh account info to sheduler """
+ self.logDebug("Scheduled Account refresh for %s in %s seconds." % (user, time))
+ self.core.scheduler.addJob(time, self.getAccountInfo, [user, force])
+
+ @lock
+ def checkLogin(self, user):
+ """ checks if user is still logged in """
+ if user in self.timestamps:
+ if self.timestamps[user] + self.login_timeout * 60 < time():
+ self.logDebug("Reached login timeout for %s" % user)
+ self.relogin(user)
+ return False
+
+ return True
diff --git a/module/plugins/internal/AdYouLike.py b/module/plugins/internal/AdYouLike.py
new file mode 100644
index 000000000..a9c194dda
--- /dev/null
+++ b/module/plugins/internal/AdYouLike.py
@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from module.common.json_layer import json_loads
+from module.plugins.internal.Captcha import Captcha
+
+
+class AdYouLike(Captcha):
+ __name__ = "AdYouLike"
+ __type__ = "captcha"
+ __version__ = "0.06"
+
+ __description__ = """AdYouLike captcha service plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
+
+
+ AYL_PATTERN = r'Adyoulike\.create\s*\((.+?)\)'
+ CALLBACK_PATTERN = r'(Adyoulike\.g\._jsonp_\d+)'
+
+
+ def detect_key(self, html=None):
+ html = html or self.retrieve_html()
+
+ m = re.search(self.AYL_PATTERN, html)
+ n = re.search(self.CALLBACK_PATTERN, html)
+ if m and n:
+ self.key = (m.group(1).strip(), n.group(1).strip())
+ self.logDebug("Ayl: %s | Callback: %s" % self.key)
+ return self.key #: key is the tuple(ayl, callback)
+ else:
+ self.logWarning("Ayl or callback pattern not found")
+ return None
+
+
+ def challenge(self, key=None, html=None):
+ ayl, callback = key or self.retrieve_key(html)
+
+ # {"adyoulike":{"key":"P~zQ~O0zV0WTiAzC-iw0navWQpCLoYEP"},
+ # "all":{"element_id":"ayl_private_cap_92300","lang":"fr","env":"prod"}}
+ ayl = json_loads(ayl)
+
+ html = self.plugin.req.load("http://api-ayl.appspot.com/challenge",
+ get={'key' : ayl['adyoulike']['key'],
+ 'env' : ayl['all']['env'],
+ 'callback': callback})
+ try:
+ challenge = json_loads(re.search(callback + r'\s*\((.+?)\)', html).group(1))
+
+ except AttributeError:
+ self.fail(_("AdYouLike challenge pattern not found"))
+
+ self.logDebug("Challenge: %s" % challenge)
+
+ return self.result(ayl, challenge), challenge
+
+
+ def result(self, server, challenge):
+ # Adyoulike.g._jsonp_5579316662423138
+ # ({"translations":{"fr":{"instructions_visual":"Recopiez « Soonnight » ci-dessous :"}},
+ # "site_under":true,"clickable":true,"pixels":{"VIDEO_050":[],"DISPLAY":[],"VIDEO_000":[],"VIDEO_100":[],
+ # "VIDEO_025":[],"VIDEO_075":[]},"medium_type":"image/adyoulike",
+ # "iframes":{"big":"<iframe src=\"http://www.soonnight.com/campagn.html\" scrolling=\"no\"
+ # height=\"250\" width=\"300\" frameborder=\"0\"></iframe>"},"shares":{},"id":256,
+ # "token":"e6QuI4aRSnbIZJg02IsV6cp4JQ9~MjA1","formats":{"small":{"y":300,"x":0,"w":300,"h":60},
+ # "big":{"y":0,"x":0,"w":300,"h":250},"hover":{"y":440,"x":0,"w":300,"h":60}},
+ # "tid":"SqwuAdxT1EZoi4B5q0T63LN2AkiCJBg5"})
+
+ if isinstance(server, basestring):
+ server = json_loads(server)
+
+ if isinstance(challenge, basestring):
+ challenge = json_loads(challenge)
+
+ try:
+ instructions_visual = challenge['translations'][server['all']['lang']]['instructions_visual']
+ result = re.search(u'«(.+?)»', instructions_visual).group(1).strip()
+
+ except AttributeError:
+ self.fail(_("AdYouLike result not found"))
+
+ result = {'_ayl_captcha_engine' : "adyoulike",
+ '_ayl_env' : server['all']['env'],
+ '_ayl_tid' : challenge['tid'],
+ '_ayl_token_challenge': challenge['token'],
+ '_ayl_response' : response}
+
+ self.logDebug("Result: %s" % result)
+
+ return result
diff --git a/module/plugins/internal/AdsCaptcha.py b/module/plugins/internal/AdsCaptcha.py
new file mode 100644
index 000000000..9cab99151
--- /dev/null
+++ b/module/plugins/internal/AdsCaptcha.py
@@ -0,0 +1,63 @@
+# -*- coding: utf-8 -*-
+
+import random
+import re
+
+from module.plugins.internal.Captcha import Captcha
+
+
+class AdsCaptcha(Captcha):
+ __name__ = "AdsCaptcha"
+ __type__ = "captcha"
+ __version__ = "0.09"
+
+ __description__ = """AdsCaptcha captcha service plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("pyLoad Team", "admin@pyload.org")]
+
+
+ CAPTCHAID_PATTERN = r'api\.adscaptcha\.com/Get\.aspx\?.*?CaptchaId=(\d+)'
+ PUBLICKEY_PATTERN = r'api\.adscaptcha\.com/Get\.aspx\?.*?PublicKey=([\w-]+)'
+
+
+ def detect_key(self, html=None):
+ html = html or self.retrieve_html()
+
+ m = re.search(self.PUBLICKEY_PATTERN, html)
+ n = re.search(self.CAPTCHAID_PATTERN, html)
+ if m and n:
+ self.key = (m.group(1).strip(), n.group(1).strip()) #: key is the tuple(PublicKey, CaptchaId)
+ self.logDebug("Key: %s | ID: %s" % self.key)
+ return self.key
+ else:
+ self.logWarning("Key or id pattern not found")
+ return None
+
+
+ def challenge(self, key=None, html=None):
+ PublicKey, CaptchaId = key or self.retrieve_key(html)
+
+ html = self.plugin.req.load("http://api.adscaptcha.com/Get.aspx",
+ get={'CaptchaId': CaptchaId,
+ 'PublicKey': PublicKey})
+ try:
+ challenge = re.search("challenge: '(.+?)',", html).group(1)
+ server = re.search("server: '(.+?)',", html).group(1)
+
+ except AttributeError:
+ self.fail(_("AdsCaptcha challenge pattern not found"))
+
+ self.logDebug("Challenge: %s" % challenge)
+
+ return self.result(server, challenge), challenge
+
+
+ def result(self, server, challenge):
+ result = self.plugin.decryptCaptcha("%sChallenge.aspx" % server,
+ get={'cid': challenge, 'dummy': random.random()},
+ cookies=True,
+ imgtype="jpg")
+
+ self.logDebug("Result: %s" % result)
+
+ return result
diff --git a/module/plugins/internal/Captcha.py b/module/plugins/internal/Captcha.py
new file mode 100644
index 000000000..e5a44d750
--- /dev/null
+++ b/module/plugins/internal/Captcha.py
@@ -0,0 +1,56 @@
+# -*- coding: utf-8 -*-
+
+from module.plugins.internal.Plugin import Base
+
+
+#@TODO: Extend (new) Plugin class; remove all `html` args
+class Captcha(Base):
+ __name__ = "Captcha"
+ __type__ = "captcha"
+ __version__ = "0.30"
+
+ __description__ = """Base captcha service plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("pyLoad Team", "admin@pyload.org")]
+
+
+ key = None #: last key detected
+
+
+ def __init__(self, plugin):
+ self.plugin = plugin
+ super(Captcha, self).__init__(plugin.core)
+
+
+ #@TODO: Recheck in 0.4.10
+ def fail(self, reason):
+ self.plugin.fail(reason)
+ raise AttributeError(reason)
+
+
+ #@TODO: Recheck in 0.4.10
+ def retrieve_key(self, html):
+ if self.detect_key(html):
+ return self.key
+ else:
+ self.fail(_("%s key not found") % self.__name__)
+
+
+ #@TODO: Recheck in 0.4.10
+ def retrieve_html(self):
+ if hasattr(self.plugin, "html") and self.plugin.html:
+ return self.plugin.html
+ else:
+ self.fail(_("%s html not found") % self.__name__)
+
+
+ def detect_key(self, html=None):
+ raise NotImplementedError
+
+
+ def challenge(self, key=None, html=None):
+ raise NotImplementedError
+
+
+ def result(self, server, challenge):
+ raise NotImplementedError
diff --git a/module/plugins/internal/CaptchaService.py b/module/plugins/internal/CaptchaService.py
deleted file mode 100644
index b429fd6e0..000000000
--- a/module/plugins/internal/CaptchaService.py
+++ /dev/null
@@ -1,353 +0,0 @@
-# -*- coding: utf-8 -*-
-
-import re
-
-from base64 import urlsafe_b64encode
-from random import random
-
-from module.common.json_layer import json_loads
-
-
-class CaptchaService:
- __name__ = "CaptchaService"
- __version__ = "0.16"
-
- __description__ = """Base captcha service plugin"""
- __license__ = "GPLv3"
- __authors__ = [("pyLoad Team", "admin@pyload.org")]
-
-
- KEY_PATTERN = None
-
- key = None #: last key detected
-
-
- def __init__(self, plugin):
- self.plugin = plugin
-
-
- def detect_key(self, html=None):
- if not html:
- if hasattr(self.plugin, "html") and self.plugin.html:
- html = self.plugin.html
- else:
- errmsg = _("%s html not found") % self.__name__
- self.plugin.fail(errmsg) #@TODO: replace all plugin.fail(errmsg) with plugin.error(errmsg) in 0.4.10
- raise TypeError(errmsg)
-
- m = re.search(self.KEY_PATTERN, html)
- if m:
- self.key = m.group(1).strip()
- self.plugin.logDebug("%s key: %s" % (self.__name__, self.key))
- return self.key
- else:
- self.plugin.logDebug("%s key not found" % self.__name__)
- return None
-
-
- def challenge(self, key=None):
- raise NotImplementedError
-
-
- def result(self, server, challenge):
- raise NotImplementedError
-
-
-class ReCaptcha(CaptchaService):
- __name__ = "ReCaptcha"
- __version__ = "0.09"
-
- __description__ = """ReCaptcha captcha service plugin"""
- __license__ = "GPLv3"
- __authors__ = [("pyLoad Team", "admin@pyload.org")]
-
-
- KEY_PATTERN = r'(?:class="g-recaptcha"\s+data-sitekey="|recaptcha(?:/api|\.net)/(?:challenge|noscript)\?k=)([\w-]+)'
- KEY_AJAX_PATTERN = r'Recaptcha\.create\s*\(\s*["\']([\w-]+)'
-
-
- def detect_key(self, html=None):
- if not html:
- if hasattr(self.plugin, "html") and self.plugin.html:
- html = self.plugin.html
- else:
- errmsg = _("ReCaptcha html not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- m = re.search(self.KEY_PATTERN, html) or re.search(self.KEY_AJAX_PATTERN, html)
- if m:
- self.key = m.group(1).strip()
- self.plugin.logDebug("ReCaptcha key: %s" % self.key)
- return self.key
- else:
- self.plugin.logDebug("ReCaptcha key not found")
- return None
-
-
- def challenge(self, key=None, userverify=False):
- if not key:
- if self.detect_key():
- key = self.key
- else:
- errmsg = _("ReCaptcha key not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- html = self.plugin.req.load("http://www.google.com/recaptcha/api/challenge", get={'k': key})
- try:
- challenge = re.search("challenge : '(.+?)',", html).group(1)
- server = re.search("server : '(.+?)',", html).group(1)
-
- except AttributeError:
- errmsg = _("ReCaptcha challenge pattern not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
- self.plugin.logDebug("ReCaptcha challenge: %s" % challenge)
-
- response = challenge, self.result(server, challenge)
-
- return self.userverify(*response) if userverify else response
-
-
- def userverify(self, challenge, result):
- response = self.plugin.req.load("https://www.google.com/recaptcha/api2/userverify",
- post={'c' : challenge,
- 'response': urlsafe_b64encode('{"response":"%s"}' % result)})
- try:
- return re.search(r'"uvresp","(.+?)"', response).group(1)
-
- except AttributeError:
- errmsg = _("ReCaptcha userverify response not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
-
- def result(self, server, challenge):
- result = self.plugin.decryptCaptcha("%simage" % server,
- get={'c': challenge},
- cookies=True,
- forceUser=True,
- imgtype="jpg")
-
- self.plugin.logDebug("ReCaptcha result: %s" % result)
-
- return result
-
-
-class AdsCaptcha(CaptchaService):
- __name__ = "AdsCaptcha"
- __version__ = "0.06"
-
- __description__ = """AdsCaptcha captcha service plugin"""
- __license__ = "GPLv3"
- __authors__ = [("pyLoad Team", "admin@pyload.org")]
-
-
- CAPTCHAID_PATTERN = r'api\.adscaptcha\.com/Get\.aspx\?[^"\']*CaptchaId=(\d+)'
- PUBLICKEY_PATTERN = r'api\.adscaptcha\.com/Get\.aspx\?[^"\']*PublicKey=([\w-]+)'
-
-
- def detect_key(self, html=None):
- if not html:
- if hasattr(self.plugin, "html") and self.plugin.html:
- html = self.plugin.html
- else:
- errmsg = _("AdsCaptcha html not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- m = re.search(self.PUBLICKEY_PATTERN, html)
- n = re.search(self.CAPTCHAID_PATTERN, html)
- if m and n:
- self.key = (m.group(1).strip(), n.group(1).strip()) #: key is the tuple(PublicKey, CaptchaId)
- self.plugin.logDebug("AdsCaptcha key|id: %s | %s" % self.key)
- return self.key
- else:
- self.plugin.logDebug("AdsCaptcha key or id not found")
- return None
-
-
- def challenge(self, key=None):
- if not key:
- if self.detect_key():
- key = self.key
- else:
- errmsg = _("AdsCaptcha key not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- PublicKey, CaptchaId = key
-
- html = self.plugin.req.load("http://api.adscaptcha.com/Get.aspx", get={'CaptchaId': CaptchaId, 'PublicKey': PublicKey})
- try:
- challenge = re.search("challenge: '(.+?)',", html).group(1)
- server = re.search("server: '(.+?)',", html).group(1)
-
- except AttributeError:
- errmsg = _("AdsCaptcha challenge pattern not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
- self.plugin.logDebug("AdsCaptcha challenge: %s" % challenge)
-
- return challenge, self.result(server, challenge)
-
-
- def result(self, server, challenge):
- result = self.plugin.decryptCaptcha("%sChallenge.aspx" % server,
- get={'cid': challenge, 'dummy': random()},
- cookies=True,
- imgtype="jpg")
-
- self.plugin.logDebug("AdsCaptcha result: %s" % result)
-
- return result
-
-
-class SolveMedia(CaptchaService):
- __name__ = "SolveMedia"
- __version__ = "0.06"
-
- __description__ = """SolveMedia captcha service plugin"""
- __license__ = "GPLv3"
- __authors__ = [("pyLoad Team", "admin@pyload.org")]
-
-
- KEY_PATTERN = r'api\.solvemedia\.com/papi/challenge\.(?:no)?script\?k=(.+?)["\']'
-
-
- def challenge(self, key=None):
- if not key:
- if self.detect_key():
- key = self.key
- else:
- errmsg = _("SolveMedia key not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- html = self.plugin.req.load("http://api.solvemedia.com/papi/challenge.noscript", get={'k': key})
- try:
- challenge = re.search(r'<input type=hidden name="adcopy_challenge" id="adcopy_challenge" value="([^"]+)">',
- html).group(1)
- server = "http://api.solvemedia.com/papi/media"
-
- except AttributeError:
- errmsg = _("SolveMedia challenge pattern not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
- self.plugin.logDebug("SolveMedia challenge: %s" % challenge)
-
- return challenge, self.result(server, challenge)
-
-
- def result(self, server, challenge):
- result = self.plugin.decryptCaptcha(server, get={'c': challenge}, imgtype="gif")
-
- self.plugin.logDebug("SolveMedia result: %s" % result)
-
- return result
-
-
-class AdYouLike(CaptchaService):
- __name__ = "AdYouLike"
- __version__ = "0.02"
-
- __description__ = """AdYouLike captcha service plugin"""
- __license__ = "GPLv3"
- __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
-
-
- AYL_PATTERN = r'Adyoulike\.create\s*\((.+?)\)'
- CALLBACK_PATTERN = r'(Adyoulike\.g\._jsonp_\d+)'
-
-
- def detect_key(self, html=None):
- if not html:
- if hasattr(self.plugin, "html") and self.plugin.html:
- html = self.plugin.html
- else:
- errmsg = _("AdYouLike html not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- m = re.search(self.AYL_PATTERN, html)
- n = re.search(self.CALLBACK_PATTERN, html)
- if m and n:
- self.key = (m.group(1).strip(), n.group(1).strip())
- self.plugin.logDebug("AdYouLike ayl|callback: %s | %s" % self.key)
- return self.key #: key is the tuple(ayl, callback)
- else:
- self.plugin.logDebug("AdYouLike ayl or callback not found")
- return None
-
-
- def challenge(self, key=None):
- if not key:
- if self.detect_key():
- key = self.key
- else:
- errmsg = _("AdYouLike key not found")
- self.plugin.fail(errmsg)
- raise TypeError(errmsg)
-
- ayl, callback = key
-
- # {"adyoulike":{"key":"P~zQ~O0zV0WTiAzC-iw0navWQpCLoYEP"},
- # "all":{"element_id":"ayl_private_cap_92300","lang":"fr","env":"prod"}}
- ayl = json_loads(ayl)
-
- html = self.plugin.req.load("http://api-ayl.appspot.com/challenge",
- get={'key' : ayl['adyoulike']['key'],
- 'env' : ayl['all']['env'],
- 'callback': callback})
- try:
- challenge = json_loads(re.search(callback + r'\s*\((.+?)\)', html).group(1))
-
- except AttributeError:
- errmsg = _("AdYouLike challenge pattern not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
- self.plugin.logDebug("AdYouLike challenge: %s" % challenge)
-
- return self.result(ayl, challenge)
-
-
- def result(self, server, challenge):
- # Adyoulike.g._jsonp_5579316662423138
- # ({"translations":{"fr":{"instructions_visual":"Recopiez « Soonnight » ci-dessous :"}},
- # "site_under":true,"clickable":true,"pixels":{"VIDEO_050":[],"DISPLAY":[],"VIDEO_000":[],"VIDEO_100":[],
- # "VIDEO_025":[],"VIDEO_075":[]},"medium_type":"image/adyoulike",
- # "iframes":{"big":"<iframe src=\"http://www.soonnight.com/campagn.html\" scrolling=\"no\"
- # height=\"250\" width=\"300\" frameborder=\"0\"></iframe>"},"shares":{},"id":256,
- # "token":"e6QuI4aRSnbIZJg02IsV6cp4JQ9~MjA1","formats":{"small":{"y":300,"x":0,"w":300,"h":60},
- # "big":{"y":0,"x":0,"w":300,"h":250},"hover":{"y":440,"x":0,"w":300,"h":60}},
- # "tid":"SqwuAdxT1EZoi4B5q0T63LN2AkiCJBg5"})
-
- if isinstance(server, basestring):
- server = json_loads(server)
-
- if isinstance(challenge, basestring):
- challenge = json_loads(challenge)
-
- try:
- instructions_visual = challenge['translations'][server['all']['lang']]['instructions_visual']
- result = re.search(u'«(.+?)»', instructions_visual).group(1).strip()
-
- except AttributeError:
- errmsg = _("AdYouLike result not found")
- self.plugin.fail(errmsg)
- raise AttributeError(errmsg)
-
- result = {'_ayl_captcha_engine' : "adyoulike",
- '_ayl_env' : server['all']['env'],
- '_ayl_tid' : challenge['tid'],
- '_ayl_token_challenge': challenge['token'],
- '_ayl_response' : response}
-
- self.plugin.logDebug("AdYouLike result: %s" % result)
-
- return result
diff --git a/module/plugins/internal/Container.py b/module/plugins/internal/Container.py
new file mode 100644
index 000000000..43ca95e77
--- /dev/null
+++ b/module/plugins/internal/Container.py
@@ -0,0 +1,75 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: mkaay
+"""
+
+from module.plugins.internal.Crypter import Crypter
+
+from os.path import join, exists, basename
+from os import remove
+import re
+
+class Container(Crypter):
+ __name__ = "Container"
+ __version__ = "0.02"
+ __pattern__ = None
+ __type__ = "container"
+ __description__ = """Base container plugin"""
+ __author_name__ = ("mkaay")
+ __author_mail__ = ("mkaay@mkaay.de")
+
+
+ def preprocessing(self, thread):
+ """prepare"""
+
+ self.setup()
+ self.thread = thread
+
+ self.loadToDisk()
+
+ self.decrypt(self.pyfile)
+ self.deleteTmp()
+
+ self.createPackages()
+
+
+ def loadToDisk(self):
+ """loads container to disk if its stored remotely and overwrite url,
+ or check existent on several places at disk"""
+
+ if self.pyfile.url.startswith("http"):
+ self.pyfile.name = re.findall("([^\/=]+)", self.pyfile.url)[-1]
+ content = self.load(self.pyfile.url)
+ self.pyfile.url = join(self.config["general"]["download_folder"], self.pyfile.name)
+ f = open(self.pyfile.url, "wb" )
+ f.write(content)
+ f.close()
+
+ else:
+ self.pyfile.name = basename(self.pyfile.url)
+ if not exists(self.pyfile.url):
+ if exists(join(pypath, self.pyfile.url)):
+ self.pyfile.url = join(pypath, self.pyfile.url)
+ else:
+ self.fail(_("File not exists."))
+
+
+ def deleteTmp(self):
+ if self.pyfile.name.startswith("tmp_"):
+ remove(self.pyfile.url)
+
+
diff --git a/module/plugins/internal/Crypter.py b/module/plugins/internal/Crypter.py
new file mode 100644
index 000000000..b87ed1882
--- /dev/null
+++ b/module/plugins/internal/Crypter.py
@@ -0,0 +1,72 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: mkaay
+"""
+
+from module.plugins.internal.Plugin import Plugin
+
+class Crypter(Plugin):
+ __name__ = "Crypter"
+ __version__ = "0.02"
+ __pattern__ = None
+ __type__ = "container"
+ __description__ = """Base crypter plugin"""
+ __author_name__ = ("mkaay")
+ __author_mail__ = ("mkaay@mkaay.de")
+
+ def __init__(self, pyfile):
+ Plugin.__init__(self, pyfile)
+
+ #: Put all packages here. It's a list of tuples like: ( name, [list of links], folder )
+ self.packages = []
+
+ #: List of urls, pyLoad will generate packagenames
+ self.urls = []
+
+ self.multiDL = True
+ self.limitDL = 0
+
+
+ def preprocessing(self, thread):
+ """prepare"""
+ self.setup()
+ self.thread = thread
+
+ self.decrypt(self.pyfile)
+
+ self.createPackages()
+
+
+ def decrypt(self, pyfile):
+ raise NotImplementedError
+
+ def createPackages(self):
+ """ create new packages from self.packages """
+ for pack in self.packages:
+
+ self.log.debug("Parsed package %(name)s with %(len)d links" % { "name" : pack[0], "len" : len(pack[1]) } )
+
+ links = [x.decode("utf-8") for x in pack[1]]
+
+ pid = self.core.api.addPackage(pack[0], links, self.pyfile.package().queue)
+
+ if self.pyfile.package().password:
+ self.core.api.setPackageData(pid, {"password": self.pyfile.package().password})
+
+ if self.urls:
+ self.core.api.generateAndAddPackages(self.urls)
+
diff --git a/module/plugins/internal/DeadCrypter.py b/module/plugins/internal/DeadCrypter.py
index 0fa23eef3..ef0d12b91 100644
--- a/module/plugins/internal/DeadCrypter.py
+++ b/module/plugins/internal/DeadCrypter.py
@@ -1,27 +1,24 @@
# -*- coding: utf-8 -*-
-from urllib import unquote
-from urlparse import urlparse
-
+from module.plugins.internal.Crypter import Crypter
from module.plugins.internal.SimpleCrypter import create_getInfo
-from module.plugins.Crypter import Crypter as _Crypter
-class DeadCrypter(_Crypter):
+class DeadCrypter(Crypter):
__name__ = "DeadCrypter"
__type__ = "crypter"
- __version__ = "0.04"
+ __version__ = "0.06"
__pattern__ = r'^unmatchable$'
- __description__ = """ Crypter is no longer available """
+ __description__ = """Crypter is no longer available"""
__license__ = "GPLv3"
__authors__ = [("stickell", "l.stickell@yahoo.it")]
@classmethod
- def apiInfo(cls, url="", get={}, post={}):
- api = super(DeadCrypter, self).apiInfo(url, get, post)
+ def apiInfo(cls, *args, **kwargs):
+ api = super(DeadCrypter, cls).apiInfo(*args, **kwargs)
api['status'] = 1
return api
diff --git a/module/plugins/internal/DeadHoster.py b/module/plugins/internal/DeadHoster.py
index cc7adf4df..accb15a78 100644
--- a/module/plugins/internal/DeadHoster.py
+++ b/module/plugins/internal/DeadHoster.py
@@ -1,27 +1,24 @@
# -*- coding: utf-8 -*-
-from urllib import unquote
-from urlparse import urlparse
-
+from module.plugins.internal.Hoster import Hoster
from module.plugins.internal.SimpleHoster import create_getInfo
-from module.plugins.Hoster import Hoster as _Hoster
-class DeadHoster(_Hoster):
+class DeadHoster(Hoster):
__name__ = "DeadHoster"
__type__ = "hoster"
- __version__ = "0.14"
+ __version__ = "0.16"
__pattern__ = r'^unmatchable$'
- __description__ = """ Hoster is no longer available """
+ __description__ = """Hoster is no longer available"""
__license__ = "GPLv3"
__authors__ = [("zoidberg", "zoidberg@mujmail.cz")]
@classmethod
- def apiInfo(cls, url="", get={}, post={}):
- api = super(DeadHoster, self).apiInfo(url, get, post)
+ def apiInfo(cls, *args, **kwargs):
+ api = super(DeadHoster, cls).apiInfo(*args, **kwargs)
api['status'] = 1
return api
diff --git a/module/plugins/internal/Extractor.py b/module/plugins/internal/Extractor.py
index 0b2462dac..1a98060d9 100644
--- a/module/plugins/internal/Extractor.py
+++ b/module/plugins/internal/Extractor.py
@@ -1,5 +1,11 @@
# -*- coding: utf-8 -*-
+import os
+import re
+
+from module.PyFile import PyFile
+
+
class ArchiveError(Exception):
pass
@@ -14,28 +20,36 @@ class PasswordError(Exception):
class Extractor:
__name__ = "Extractor"
- __version__ = "0.13"
+ __version__ = "0.24"
__description__ = """Base extractor plugin"""
__license__ = "GPLv3"
- __authors__ = [("RaNaN", "ranan@pyload.org"),
- ("Walter Purcaro", "vuolter@gmail.com")]
+ __authors__ = [("Walter Purcaro", "vuolter@gmail.com"),
+ ("Immenz" , "immenz@gmx.net" )]
EXTENSIONS = []
+ REPAIR = False
+ VERSION = ""
@classmethod
- def checkDeps(cls):
- """ Check if system statisfy dependencies
- :return: boolean
- """
- return True
+ def isArchive(cls, filename):
+ name = os.path.basename(filename).lower()
+ return any(name.endswith(ext) for ext in cls.EXTENSIONS)
@classmethod
- def isArchive(cls, file):
- raise NotImplementedError
+ def isMultipart(cls, filename):
+ return False
+
+
+ @classmethod
+ def isUsable(cls):
+ """ Check if system statisfy dependencies
+ :return: boolean
+ """
+ return None
@classmethod
@@ -45,28 +59,29 @@ class Extractor:
:return: List of targets, id tuple list
"""
targets = []
-
- for file, id in files_ids:
- if cls.isArchive(file):
- targets.append((file, id))
-
+ processed = []
+
+ for fname, id, fout in files_ids:
+ if cls.isArchive(fname):
+ pname = re.sub(cls.re_multipart, '', fname) if cls.isMultipart(fname) else os.path.splitext(fname)[0]
+ if pname not in processed:
+ processed.append(pname)
+ targets.append((fname, id, fout))
return targets
- def __init__(self, m, file, out, password, fullpath, overwrite, excludefiles, renice, delete, keepbroken):
- """Initialize extractor for specific file
-
- :param m: ExtractArchive Hook plugin
- :param file: Absolute filepath
- :param out: Absolute path to destination directory
- :param fullpath: extract to fullpath
- :param overwrite: Overwrite existing archives
- :param renice: Renice value
- """
- self.m = m
- self.file = file
+ def __init__(self, manager, filename, out,
+ fullpath=True,
+ overwrite=False,
+ excludefiles=[],
+ renice=0,
+ delete='No',
+ keepbroken=False,
+ fid=None):
+ """ Initialize extractor for specific file """
+ self.manager = manager
+ self.filename = filename
self.out = out
- self.password = password
self.fullpath = fullpath
self.overwrite = overwrite
self.excludefiles = excludefiles
@@ -75,50 +90,45 @@ class Extractor:
self.keepbroken = keepbroken
self.files = [] #: Store extracted files here
+ pyfile = self.manager.core.files.getFile(fid) if fid else None
+ self.notifyProgress = lambda x: pyfile.setProgress(x) if pyfile else lambda x: None
+
def init(self):
""" Initialize additional data structures """
pass
- def verify(self):
- """Check if password if needed. Raise ArchiveError if integrity is
- questionable.
+ def check(self):
+ """Quick Check by listing content of archive.
+ Raises error if password is needed, integrity is questionable or else.
+ :raises PasswordError
+ :raises CRCError
:raises ArchiveError
"""
- pass
-
+ raise NotImplementedError
- def isPassword(self, password):
- """ Check if the given password is/might be correct.
- If it can not be decided at this point return true.
+ def verify(self):
+ """Testing with Extractors buildt-in method
+ Raises error if password is needed, integrity is questionable or else.
- :param password:
- :return: boolean
+ :raises PasswordError
+ :raises CRCError
+ :raises ArchiveError
"""
- if isinstance(password, basestring):
- return True
- else:
- return False
-
-
- def setPassword(self, password):
- if self.isPassword(password):
- self.password = password
- return True
- else:
- return False
+ raise NotImplementedError
def repair(self):
- return False
+ return None
- def extract(self, progress=lambda x: None):
+ def extract(self, password=None):
"""Extract the archive. Raise specific errors in case of failure.
:param progress: Progress function, call this to update status
+ :param password password to use
:raises PasswordError
:raises CRCError
:raises ArchiveError
@@ -132,9 +142,9 @@ class Extractor:
:return: List with paths of files to delete
"""
- raise NotImplementedError
+ return [self.filename]
- def getExtractedFiles(self):
+ def list(self, password=None):
"""Populate self.files at some point while extracting"""
return self.files
diff --git a/module/plugins/internal/Hook.py b/module/plugins/internal/Hook.py
new file mode 100644
index 000000000..5f2639dce
--- /dev/null
+++ b/module/plugins/internal/Hook.py
@@ -0,0 +1,161 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: mkaay
+ @interface-version: 0.2
+"""
+
+from traceback import print_exc
+
+from Plugin import Base
+
+class Expose(object):
+ """ used for decoration to declare rpc services """
+
+ def __new__(cls, f, *args, **kwargs):
+ hookManager.addRPC(f.__module__, f.func_name, f.func_doc)
+ return f
+
+def threaded(f):
+ def run(*args,**kwargs):
+ hookManager.startThread(f, *args, **kwargs)
+ return run
+
+class Hook(Base):
+ """
+ Base class for hook plugins.
+ """
+ __name__ = "Hook"
+ __version__ = "0.02"
+ __type__ = "hook"
+ __threaded__ = []
+ __config__ = [ ("name", "type", "desc" , "default") ]
+ __description__ = """interface for hook"""
+ __author_name__ = ("mkaay", "RaNaN")
+ __author_mail__ = ("mkaay@mkaay.de", "RaNaN@pyload.org")
+
+ #: automatically register event listeners for functions, attribute will be deleted dont use it yourself
+ event_map = None
+
+ # Alternative to event_map
+ #: List of events the plugin can handle, name the functions exactly like eventname.
+ event_list = None # dont make duplicate entries in event_map
+
+
+ #: periodic call interval in secondc
+ interval = 60
+
+ def __init__(self, core, manager):
+ Base.__init__(self, core)
+
+ #: Provide information in dict here, usable by API `getInfo`
+ self.info = None
+
+ #: Callback of periodical job task, used by hookmanager
+ self.cb = None
+
+ #: `HookManager`
+ self.manager = manager
+
+ #register events
+ if self.event_map:
+ for event, funcs in self.event_map.iteritems():
+ if type(funcs) in (list, tuple):
+ for f in funcs:
+ self.manager.addEvent(event, getattr(self,f))
+ else:
+ self.manager.addEvent(event, getattr(self,funcs))
+
+ #delete for various reasons
+ self.event_map = None
+
+ if self.event_list:
+ for f in self.event_list:
+ self.manager.addEvent(f, getattr(self,f))
+
+ self.event_list = None
+
+ self.initPeriodical()
+ self.setup()
+
+ def initPeriodical(self):
+ if self.interval >=1:
+ self.cb = self.core.scheduler.addJob(0, self._periodical, threaded=False)
+
+ def _periodical(self):
+ try:
+ if self.isActivated(): self.periodical()
+ except Exception, e:
+ self.core.log.error(_("Error executing hooks: %s") % str(e))
+ if self.core.debug:
+ print_exc()
+
+ self.cb = self.core.scheduler.addJob(self.interval, self._periodical, threaded=False)
+
+
+ def __repr__(self):
+ return "<Hook %s>" % self.__name__
+
+ def setup(self):
+ """ more init stuff if needed """
+ pass
+
+ def unload(self):
+ """ called when hook was deactivated """
+ pass
+
+ def isActivated(self):
+ """ checks if hook is activated"""
+ return self.config.getPlugin(self.__name__, "activated")
+
+
+ #event methods - overwrite these if needed
+ def coreReady(self):
+ pass
+
+ def coreExiting(self):
+ pass
+
+ def downloadPreparing(self, pyfile):
+ pass
+
+ def downloadFinished(self, pyfile):
+ pass
+
+ def downloadFailed(self, pyfile):
+ pass
+
+ def packageFinished(self, pypack):
+ pass
+
+ def beforeReconnecting(self, ip):
+ pass
+
+ def afterReconnecting(self, ip):
+ pass
+
+ def periodical(self):
+ pass
+
+ def newCaptchaTask(self, task):
+ """ new captcha task for the plugin, it MUST set the handler and timeout or will be ignored """
+ pass
+
+ def captchaCorrect(self, task):
+ pass
+
+ def captchaInvalid(self, task):
+ pass \ No newline at end of file
diff --git a/module/plugins/internal/Hoster.py b/module/plugins/internal/Hoster.py
new file mode 100644
index 000000000..3fed8a7c6
--- /dev/null
+++ b/module/plugins/internal/Hoster.py
@@ -0,0 +1,33 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: mkaay
+"""
+
+from module.plugins.internal.Plugin import Plugin
+
+def getInfo(self):
+ #result = [ .. (name, size, status, url) .. ]
+ return
+
+class Hoster(Plugin):
+ __name__ = "Hoster"
+ __version__ = "0.02"
+ __pattern__ = None
+ __type__ = "hoster"
+ __description__ = """Base hoster plugin"""
+ __author_name__ = ("mkaay")
+ __author_mail__ = ("mkaay@mkaay.de")
diff --git a/module/plugins/internal/MultiHook.py b/module/plugins/internal/MultiHook.py
index a3b266679..4a2c6654b 100644
--- a/module/plugins/internal/MultiHook.py
+++ b/module/plugins/internal/MultiHook.py
@@ -1,38 +1,32 @@
# -*- coding: utf-8 -*-
import re
+import time
+import traceback
-from time import sleep
-
-from module.plugins.Hook import Hook
+from module.plugins.internal.Hook import Hook
from module.utils import decode, remove_chars
class MultiHook(Hook):
__name__ = "MultiHook"
__type__ = "hook"
- __version__ = "0.35"
+ __version__ = "0.46"
- __config__ = [("pluginmode" , "all;listed;unlisted", "Use for plugins" , "all"),
- ("pluginlist" , "str" , "Plugin list (comma separated)" , "" ),
- ("revertfailed" , "bool" , "Revert to standard download if fails", True ),
- ("retry" , "int" , "Number of retries before revert" , 10 ),
- ("retryinterval" , "int" , "Retry interval in minutes" , 1 ),
- ("reload" , "bool" , "Reload plugin list" , True ),
- ("reloadinterval", "int" , "Reload interval in hours" , 12 )]
+ __config__ = [("pluginmode" , "all;listed;unlisted", "Use for plugins" , "all"),
+ ("pluginlist" , "str" , "Plugin list (comma separated)", "" ),
+ ("reload" , "bool" , "Reload plugin list" , True ),
+ ("reloadinterval", "int" , "Reload interval in hours" , 12 )]
__description__ = """Hook plugin for multi hoster/crypter"""
__license__ = "GPLv3"
- __authors__ = [("pyLoad Team", "admin@pyload.org"),
+ __authors__ = [("pyLoad Team" , "admin@pyload.org" ),
("Walter Purcaro", "vuolter@gmail.com")]
- MIN_INTERVAL = 1 * 60 * 60
+ MIN_RELOAD_INTERVAL = 1 * 60 * 60 #: 1 hour
DOMAIN_REPLACEMENTS = [(r'180upload\.com' , "hundredeightyupload.com"),
- (r'1fichier\.com' , "onefichier.com" ),
- (r'2shared\.com' , "twoshared.com" ),
- (r'4shared\.com' , "fourshared.com" ),
(r'bayfiles\.net' , "bayfiles.com" ),
(r'cloudnator\.com' , "shragle.com" ),
(r'dfiles\.eu' , "depositfiles.com" ),
@@ -48,10 +42,21 @@ class MultiHook(Hook):
(r'uploaded\.net' , "uploaded.to" ),
(r'uploadhero\.co' , "uploadhero.com" ),
(r'zshares\.net' , "zshare.net" ),
- (r'\d+.+' , "X\0" )]
+ (r'^1' , "one" ),
+ (r'^2' , "two" ),
+ (r'^3' , "three" ),
+ (r'^4' , "four" ),
+ (r'^5' , "five" ),
+ (r'^6' , "six" ),
+ (r'^7' , "seven" ),
+ (r'^8' , "eight" ),
+ (r'^9' , "nine" ),
+ (r'^0' , "zero" )]
def setup(self):
+ self.info = {} #@TODO: Remove in 0.4.10
+
self.plugins = []
self.supported = []
self.new_supported = []
@@ -62,23 +67,22 @@ class MultiHook(Hook):
self.pluginname = None
self.plugintype = None
- self._initPlugin()
+ self.initPlugin()
- def _initPlugin(self):
- plugin, type = self.core.pluginManager.findPlugin(self.__name__)
+ def initPlugin(self):
+ self.pluginname = self.__name__.rsplit("Hook", 1)[0]
+ plugin, self.plugintype = self.core.pluginManager.findPlugin(self.pluginname)
- if not plugin:
+ if plugin:
+ self.pluginmodule = self.core.pluginManager.loadModule(self.plugintype, self.pluginname)
+ self.pluginclass = getattr(self.pluginmodule, self.pluginname)
+ else:
self.logWarning("Hook plugin will be deactivated due missing plugin reference")
self.setConfig('activated', False)
- else:
- self.pluginname = self.__name__
- self.plugintype = type
- self.pluginmodule = self.core.pluginManager.loadModule(type, self.__name__)
- self.pluginclass = getattr(self.pluginmodule, self.__name__)
- def _loadAccount(self):
+ def loadAccount(self):
self.account = self.core.accountManager.getAccountPlugin(self.pluginname)
if self.account and not self.account.canUse():
@@ -89,10 +93,6 @@ class MultiHook(Hook):
self.setConfig('activated', False)
- def coreReady(self):
- self._loadAccount()
-
-
def getURL(self, *args, **kwargs): #@TODO: Remove in 0.4.10
""" see HTTPRequest for argument list """
h = pyreq.getHTTPRequest(timeout=120)
@@ -106,7 +106,7 @@ class MultiHook(Hook):
return rep
- def getConfig(self, option, default=''):
+ def getConfig(self, option, default=''): #@TODO: Remove in 0.4.10
"""getConfig with default value - sublass may not implements all config options"""
try:
return self.getConf(option)
@@ -118,18 +118,18 @@ class MultiHook(Hook):
def pluginsCached(self):
if self.plugins:
return self.plugins
-
- for _i in xrange(3):
+
+ for _i in xrange(2):
try:
- pluginset = self._pluginSet(self.getHosters() if self.plugintype == "hoster" else self.getCrypters())
-
- except Exception, e:
- self.logError(e, "Waiting 1 minute and retry")
- sleep(60)
-
- else:
+ pluginset = self._pluginSet(self.getHosters())
break
+
+ except Exception, e:
+ self.logDebug(e, "Waiting 1 minute and retry")
+ time.sleep(60)
else:
+ self.logWarning(_("Fallback to default reload interval due plugin parse error"))
+ self.interval = self.MIN_RELOAD_INTERVAL
return list()
try:
@@ -152,17 +152,15 @@ class MultiHook(Hook):
def _pluginSet(self, plugins):
- plugins = set((decode(x).strip().lower() for x in plugins if '.' in x))
+ regexp = re.compile(r'^[\w\-.^_]{3,63}\.[a-zA-Z]{2,}$', re.U)
+ plugins = [decode(p.strip()).lower() for p in plugins if regexp.match(p.strip())]
- for rf, rt in self.DOMAIN_REPLACEMENTS:
- regex = re.compile(rf)
- for p in filter(lambda x: regex.match(x), plugins):
- plugins.remove(p)
- plugins.add(re.sub(rf, rt, p))
+ for r in self.DOMAIN_REPLACEMENTS:
+ rf, rt = r
+ repr = re.compile(rf, re.I|re.U)
+ plugins = [re.sub(rf, rt, p) if repr.match(p) else p for p in plugins]
- plugins.discard('')
-
- return plugins
+ return set(plugins)
def getHosters(self):
@@ -173,16 +171,30 @@ class MultiHook(Hook):
raise NotImplementedError
- def getCrypters(self):
- """Load list of supported crypters
+ #: Threaded _periodical, remove in 0.4.10 and use built-in flag for that
+ def _periodical(self):
+ try:
+ if self.isActivated():
+ self.periodical()
- :return: List of domain names
- """
- raise NotImplementedError
+ except Exception, e:
+ self.core.log.error(_("Error executing hooks: %s") % str(e))
+ if self.core.debug:
+ traceback.print_exc()
+
+ self.cb = self.core.scheduler.addJob(self.interval, self._periodical)
def periodical(self):
"""reload plugin list periodically"""
+ self.loadAccount()
+
+ if self.getConfig("reload", True):
+ self.interval = max(self.getConfig("reloadinterval", 12) * 60 * 60, self.MIN_RELOAD_INTERVAL)
+ else:
+ self.core.scheduler.removeJob(self.cb)
+ self.cb = None
+
self.logInfo(_("Reloading supported %s list") % self.plugintype)
old_supported = self.supported
@@ -200,12 +212,6 @@ class MultiHook(Hook):
for plugin in old_supported:
self.unloadPlugin(plugin)
- if self.getConfig("reload", True):
- self.interval = max(self.getConfig("reloadinterval", 12), self.MIN_INTERVAL)
- else:
- self.core.scheduler.removeJob(self.cb)
- self.cb = None
-
def overridePlugins(self):
excludedList = []
@@ -249,7 +255,7 @@ class MultiHook(Hook):
self.logDebug("New %ss: %s" % (self.plugintype, ", ".join(plugins)))
# create new regexp
- regexp = r'.*(?P<DOMAIN>%s).*' % "|".join([x.replace(".", "\.") for x in plugins])
+ regexp = r'.*(?P<DOMAIN>%s).*' % "|".join(x.replace('.', '\.') for x in plugins)
if hasattr(self.pluginclass, "__pattern__") and isinstance(self.pluginclass.__pattern__, basestring) and '://' in self.pluginclass.__pattern__:
regexp = r'%s|%s' % (self.pluginclass.__pattern__, regexp)
@@ -263,11 +269,11 @@ class MultiHook(Hook):
def unloadPlugin(self, plugin):
hdict = self.core.pluginManager.plugins[self.plugintype][plugin]
if "module" in hdict:
- del hdict['module']
+ hdict.pop('module', None)
if "new_module" in hdict:
- del hdict['new_module']
- del hdict['new_name']
+ hdict.pop('new_module', None)
+ hdict.pop('new_name', None)
def unload(self):
@@ -280,25 +286,3 @@ class MultiHook(Hook):
hdict['pattern'] = getattr(self.pluginclass, "__pattern__", r'^unmatchable$')
hdict['re'] = re.compile(hdict['pattern'])
-
-
- def downloadFailed(self, pyfile):
- """remove plugin override if download fails but not if file is offline/temp.offline"""
- if pyfile.status != 8 or not self.getConfig("revertfailed", True):
- return
-
- hdict = self.core.pluginManager.plugins[self.plugintype][pyfile.pluginname]
- if "new_name" in hdict and hdict['new_name'] == self.pluginname:
- if pyfile.error == "MultiHook":
- self.logDebug("Unload MultiHook", pyfile.pluginname, hdict)
- self.unloadPlugin(pyfile.pluginname)
- pyfile.setStatus("queued")
- else:
- retries = max(self.getConfig("retry", 10), 0)
- wait_time = max(self.getConfig("retryinterval", 1), 0)
-
- if 0 < retries > pyfile.plugin.retries:
- pyfile.setCustomStatus("MultiHook", "queued")
- pyfile.plugin.retries += 1
- pyfile.plugin.setWait(wait_time)
- pyfile.plugin.wait()
diff --git a/module/plugins/internal/MultiHoster.py b/module/plugins/internal/MultiHoster.py
index 8ca4d427f..2b3eb8941 100644
--- a/module/plugins/internal/MultiHoster.py
+++ b/module/plugins/internal/MultiHoster.py
@@ -2,22 +2,24 @@
import re
+from module.plugins.internal.Plugin import Fail, Retry
from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo, replace_patterns, set_cookies
class MultiHoster(SimpleHoster):
__name__ = "MultiHoster"
__type__ = "hoster"
- __version__ = "0.32"
+ __version__ = "0.42"
__pattern__ = r'^unmatchable$'
+ __config__ = [("use_premium" , "bool", "Use premium account if available" , True),
+ ("revertfailed", "bool", "Revert to standard download if fails", True)]
__description__ = """Multi hoster plugin"""
__license__ = "GPLv3"
__authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
- CHECK_TRAFFIC = True
LOGIN_ACCOUNT = True
@@ -28,9 +30,13 @@ class MultiHoster(SimpleHoster):
def prepare(self):
- self.info = {}
- self.link = "" #@TODO: Move to hoster class in 0.4.10
- self.directDL = False #@TODO: Move to hoster class in 0.4.10
+ self.info = {}
+ self.html = ""
+ self.link = "" #@TODO: Move to Hoster in 0.4.10
+ self.directDL = False #@TODO: Move to Hoster in 0.4.10
+
+ if not self.getConfig('use_premium', True):
+ self.retryFree()
if self.LOGIN_ACCOUNT and not self.account:
self.fail(_("Required account not found"))
@@ -41,47 +47,64 @@ class MultiHoster(SimpleHoster):
set_cookies(self.req.cj, self.COOKIES)
if self.DIRECT_LINK is None:
- self.directDL = self.__pattern__ != r'^unmatchable$'
+ self.directDL = self.__pattern__ != r'^unmatchable$' and re.match(self.__pattern__, self.pyfile.url)
else:
self.directDL = self.DIRECT_LINK
- self.pyfile.url = replace_patterns(self.pyfile.url,
- self.FILE_URL_REPLACEMENTS if hasattr(self, "FILE_URL_REPLACEMENTS") else self.URL_REPLACEMENTS) #@TODO: Remove FILE_URL_REPLACEMENTS check in 0.4.10
+ self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS)
def process(self, pyfile):
- self.prepare()
+ try:
+ self.prepare()
+
+ if self.directDL:
+ self.checkInfo()
+ self.logDebug("Looking for direct download link...")
+ self.handleDirect(pyfile)
+
+ if not self.link and not self.lastDownload:
+ self.preload()
+
+ self.checkErrors()
+ self.checkStatus(getinfo=False)
+
+ if self.premium and (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.logDebug("Handled as premium download")
+ self.handlePremium(pyfile)
+
+ elif not self.LOGIN_ACCOUNT or (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.logDebug("Handled as free download")
+ self.handleFree(pyfile)
- if self.__pattern__ != r'^unmatchable$' and re.match(self.__pattern__, pyfile.url):
- self.checkInfo()
+ self.download(self.link, ref=False, disposition=True)
+ self.checkFile()
- if self.directDL:
- self.logDebug("Looking for direct download link...")
- self.handleDirect(pyfile)
+ except Fail, e: #@TODO: Move to PluginThread in 0.4.10
+ err = str(e) #@TODO: Recheck in 0.4.10
- if not self.link and not self.lastDownload:
- self.preload()
+ if self.premium:
+ self.logWarning(_("Premium download failed"))
+ self.retryFree()
- self.checkErrors()
- self.checkStatus(getinfo=False)
+ elif self.getConfig("revertfailed", True) \
+ and "new_module" in self.core.pluginManager.hosterPlugins[self.__name__]:
+ hdict = self.core.pluginManager.hosterPlugins[self.__name__]
- if self.premium and (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
- self.logDebug("Handled as premium download")
- self.handlePremium(pyfile)
+ tmp_module = hdict['new_module']
+ tmp_name = hdict['new_name']
+ hdict.pop('new_module', None)
+ hdict.pop('new_name', None)
- elif not self.LOGIN_ACCOUNT or (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
- self.logDebug("Handled as free download")
- self.handleFree(pyfile)
+ pyfile.initPlugin()
- self.downloadLink(self.link)
- self.checkFile()
+ hdict['new_module'] = tmp_module
+ hdict['new_name'] = tmp_name
+ raise Retry(_("Revert to original hoster plugin"))
- #@TODO: Remove in 0.4.10
- def downloadLink(self, link):
- if link and isinstance(link, basestring):
- self.correctCaptcha()
- self.download(link, disposition=True)
+ else:
+ raise Fail(err)
def handlePremium(self, pyfile):
diff --git a/module/plugins/internal/Plugin.py b/module/plugins/internal/Plugin.py
new file mode 100644
index 000000000..228685ee5
--- /dev/null
+++ b/module/plugins/internal/Plugin.py
@@ -0,0 +1,598 @@
+# -*- coding: utf-8 -*-
+
+"""
+ This program is free software; you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License,
+ or (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program; if not, see <http://www.gnu.org/licenses/>.
+
+ @author: RaNaN, spoob, mkaay
+"""
+
+from time import time, sleep
+from random import randint
+
+import os
+from os import remove, makedirs, chmod, stat
+from os.path import exists, join
+
+if os.name != "nt":
+ from os import chown
+ from pwd import getpwnam
+ from grp import getgrnam
+
+from itertools import islice
+
+from module.plugins.Plugin import Abort, Fail, Reconnect, Retry, SkipDownload
+from module.utils import save_join, save_path, fs_encode, fs_decode
+
+def chunks(iterable, size):
+ it = iter(iterable)
+ item = list(islice(it, size))
+ while item:
+ yield item
+ item = list(islice(it, size))
+
+
+class Base(object):
+ """
+ A Base class with log/config/db methods *all* plugin types can use
+ """
+
+ def __init__(self, core):
+ #: Core instance
+ self.core = core
+ #: logging instance
+ self.log = core.log
+ #: core config
+ self.config = core.config
+
+ #log functions
+ def logInfo(self, *args):
+ self.log.info("%s: %s" % (self.__name__, " | ".join([a if isinstance(a, basestring) else str(a) for a in args])))
+
+ def logWarning(self, *args):
+ self.log.warning("%s: %s" % (self.__name__, " | ".join([a if isinstance(a, basestring) else str(a) for a in args])))
+
+ def logError(self, *args):
+ self.log.error("%s: %s" % (self.__name__, " | ".join([a if isinstance(a, basestring) else str(a) for a in args])))
+
+ def logDebug(self, *args):
+ self.log.debug("%s: %s" % (self.__name__, " | ".join([a if isinstance(a, basestring) else str(a) for a in args])))
+
+
+ def setConf(self, option, value):
+ """ see `setConfig` """
+ self.core.config.setPlugin(self.__name__, option, value)
+
+ def setConfig(self, option, value):
+ """ Set config value for current plugin
+
+ :param option:
+ :param value:
+ :return:
+ """
+ self.setConf(option, value)
+
+ def getConf(self, option):
+ """ see `getConfig` """
+ return self.core.config.getPlugin(self.__name__, option)
+
+ def getConfig(self, option):
+ """ Returns config value for current plugin
+
+ :param option:
+ :return:
+ """
+ return self.getConf(option)
+
+ def setStorage(self, key, value):
+ """ Saves a value persistently to the database """
+ self.core.db.setStorage(self.__name__, key, value)
+
+ def store(self, key, value):
+ """ same as `setStorage` """
+ self.core.db.setStorage(self.__name__, key, value)
+
+ def getStorage(self, key=None, default=None):
+ """ Retrieves saved value or dict of all saved entries if key is None """
+ if key is not None:
+ return self.core.db.getStorage(self.__name__, key) or default
+ return self.core.db.getStorage(self.__name__, key)
+
+ def retrieve(self, *args, **kwargs):
+ """ same as `getStorage` """
+ return self.getStorage(*args, **kwargs)
+
+ def delStorage(self, key):
+ """ Delete entry in db """
+ self.core.db.delStorage(self.__name__, key)
+
+
+class Plugin(Base):
+ """
+ Base plugin for hoster/crypter.
+ Overwrite `process` / `decrypt` in your subclassed plugin.
+ """
+ __name__ = "Plugin"
+ __version__ = "0.05"
+ __pattern__ = None
+ __type__ = "hoster"
+ __config__ = [("name", "type", "desc", "default")]
+ __description__ = """Base Plugin"""
+ __author_name__ = ("RaNaN", "spoob", "mkaay")
+ __author_mail__ = ("RaNaN@pyload.org", "spoob@pyload.org", "mkaay@mkaay.de")
+
+ def __init__(self, pyfile):
+ Base.__init__(self, pyfile.m.core)
+
+ self.wantReconnect = False
+ #: enables simultaneous processing of multiple downloads
+ self.multiDL = True
+ self.limitDL = 0
+ #: chunk limit
+ self.chunkLimit = 1
+ self.resumeDownload = False
+
+ #: time() + wait in seconds
+ self.waitUntil = 0
+ self.waiting = False
+
+ self.ocr = None #captcha reader instance
+ #: account handler instance, see :py:class:`Account`
+ self.account = pyfile.m.core.accountManager.getAccountPlugin(self.__name__)
+
+ #: premium status
+ self.premium = False
+ #: username/login
+ self.user = None
+
+ if self.account and not self.account.canUse(): self.account = None
+ if self.account:
+ self.user, data = self.account.selectAccount()
+ #: Browser instance, see `network.Browser`
+ self.req = self.account.getAccountRequest(self.user)
+ self.chunkLimit = -1 # chunk limit, -1 for unlimited
+ #: enables resume (will be ignored if server dont accept chunks)
+ self.resumeDownload = True
+ self.multiDL = True #every hoster with account should provide multiple downloads
+ #: premium status
+ self.premium = self.account.isPremium(self.user)
+ else:
+ self.req = pyfile.m.core.requestFactory.getRequest(self.__name__)
+
+ #: associated pyfile instance, see `PyFile`
+ self.pyfile = pyfile
+ self.thread = None # holds thread in future
+
+ #: location where the last call to download was saved
+ self.lastDownload = ""
+ #: re match of the last call to `checkDownload`
+ self.lastCheck = None
+ #: js engine, see `JsEngine`
+ self.js = self.core.js
+ self.cTask = None #captcha task
+
+ self.retries = 0 # amount of retries already made
+ self.html = None # some plugins store html code here
+
+ self.init()
+
+ def getChunkCount(self):
+ if self.chunkLimit <= 0:
+ return self.config["download"]["chunks"]
+ return min(self.config["download"]["chunks"], self.chunkLimit)
+
+ def __call__(self):
+ return self.__name__
+
+ def init(self):
+ """initialize the plugin (in addition to `__init__`)"""
+ pass
+
+ def setup(self):
+ """ setup for enviroment and other things, called before downloading (possibly more than one time)"""
+ pass
+
+ def preprocessing(self, thread):
+ """ handles important things to do before starting """
+ self.thread = thread
+
+ if self.account:
+ self.account.checkLogin(self.user)
+ else:
+ self.req.clearCookies()
+
+ self.setup()
+
+ self.pyfile.setStatus("starting")
+
+ return self.process(self.pyfile)
+
+
+ def process(self, pyfile):
+ """the 'main' method of every plugin, you **have to** overwrite it"""
+ raise NotImplementedError
+
+ def resetAccount(self):
+ """ dont use account and retry download """
+ self.account = None
+ self.req = self.core.requestFactory.getRequest(self.__name__)
+ self.retry()
+
+ def checksum(self, local_file=None):
+ """
+ return codes:
+ 0 - checksum ok
+ 1 - checksum wrong
+ 5 - can't get checksum
+ 10 - not implemented
+ 20 - unknown error
+ """
+ #@TODO checksum check hook
+
+ return True, 10
+
+
+ def setWait(self, seconds, reconnect=False):
+ """Set a specific wait time later used with `wait`
+
+ :param seconds: wait time in seconds
+ :param reconnect: True if a reconnect would avoid wait time
+ """
+ if reconnect:
+ self.wantReconnect = True
+ self.pyfile.waitUntil = time() + int(seconds)
+
+ def wait(self):
+ """ waits the time previously set """
+ self.waiting = True
+ self.pyfile.setStatus("waiting")
+
+ while self.pyfile.waitUntil > time():
+ self.thread.m.reconnecting.wait(2)
+
+ if self.pyfile.abort: raise Abort
+ if self.thread.m.reconnecting.isSet():
+ self.waiting = False
+ self.wantReconnect = False
+ raise Reconnect
+
+ self.waiting = False
+ self.pyfile.setStatus("starting")
+
+ def fail(self, reason):
+ """ fail and give reason """
+ raise Fail(reason)
+
+ def offline(self):
+ """ fail and indicate file is offline """
+ raise Fail("offline")
+
+ def tempOffline(self):
+ """ fail and indicates file ist temporary offline, the core may take consequences """
+ raise Fail("temp. offline")
+
+ def retry(self, max_tries=3, wait_time=1, reason=""):
+ """Retries and begin again from the beginning
+
+ :param max_tries: number of maximum retries
+ :param wait_time: time to wait in seconds
+ :param reason: reason for retrying, will be passed to fail if max_tries reached
+ """
+ if 0 < max_tries <= self.retries:
+ if not reason: reason = "Max retries reached"
+ raise Fail(reason)
+
+ self.wantReconnect = False
+ self.setWait(wait_time)
+ self.wait()
+
+ self.retries += 1
+ raise Retry(reason)
+
+ def invalidCaptcha(self):
+ if self.cTask:
+ self.cTask.invalid()
+
+ def correctCaptcha(self):
+ if self.cTask:
+ self.cTask.correct()
+
+ def decryptCaptcha(self, url, get={}, post={}, cookies=False, forceUser=False, imgtype='jpg',
+ result_type='textual'):
+ """ Loads a captcha and decrypts it with ocr, plugin, user input
+
+ :param url: url of captcha image
+ :param get: get part for request
+ :param post: post part for request
+ :param cookies: True if cookies should be enabled
+ :param forceUser: if True, ocr is not used
+ :param imgtype: Type of the Image
+ :param result_type: 'textual' if text is written on the captcha\
+ or 'positional' for captcha where the user have to click\
+ on a specific region on the captcha
+
+ :return: result of decrypting
+ """
+
+ img = self.load(url, get=get, post=post, cookies=cookies)
+
+ id = ("%.2f" % time())[-6:].replace(".", "")
+ temp_file = open(join("tmp", "tmpCaptcha_%s_%s.%s" % (self.__name__, id, imgtype)), "wb")
+ temp_file.write(img)
+ temp_file.close()
+
+ has_plugin = self.__name__ in self.core.pluginManager.captchaPlugins
+
+ if self.core.captcha:
+ Ocr = self.core.pluginManager.loadClass("captcha", self.__name__)
+ else:
+ Ocr = None
+
+ if Ocr and not forceUser:
+ sleep(randint(3000, 5000) / 1000.0)
+ if self.pyfile.abort: raise Abort
+
+ ocr = Ocr()
+ result = ocr.get_captcha(temp_file.name)
+ else:
+ captchaManager = self.core.captchaManager
+ task = captchaManager.newTask(img, imgtype, temp_file.name, result_type)
+ self.cTask = task
+ captchaManager.handleCaptcha(task)
+
+ while task.isWaiting():
+ if self.pyfile.abort:
+ captchaManager.removeTask(task)
+ raise Abort
+ sleep(1)
+
+ captchaManager.removeTask(task)
+
+ if task.error and has_plugin: #ignore default error message since the user could use OCR
+ self.fail(_("Pil and tesseract not installed and no Client connected for captcha decrypting"))
+ elif task.error:
+ self.fail(task.error)
+ elif not task.result:
+ self.fail(_("No captcha result obtained in appropiate time by any of the plugins."))
+
+ result = task.result
+ self.log.debug("Received captcha result: %s" % str(result))
+
+ if not self.core.debug:
+ try:
+ remove(temp_file.name)
+ except:
+ pass
+
+ return result
+
+
+ def load(self, url, get={}, post={}, ref=True, cookies=True, just_header=False, decode=False):
+ """Load content at url and returns it
+
+ :param url:
+ :param get:
+ :param post:
+ :param ref:
+ :param cookies:
+ :param just_header: if True only the header will be retrieved and returned as dict
+ :param decode: Wether to decode the output according to http header, should be True in most cases
+ :return: Loaded content
+ """
+ if self.pyfile.abort: raise Abort
+ #utf8 vs decode -> please use decode attribute in all future plugins
+ if type(url) == unicode: url = str(url)
+
+ res = self.req.load(url, get, post, ref, cookies, just_header, decode=decode)
+
+ if self.core.debug:
+ from inspect import currentframe
+
+ frame = currentframe()
+ if not exists(join("tmp", self.__name__)):
+ makedirs(join("tmp", self.__name__))
+
+ f = open(
+ join("tmp", self.__name__, "%s_line%s.dump.html" % (frame.f_back.f_code.co_name, frame.f_back.f_lineno))
+ , "wb")
+ del frame # delete the frame or it wont be cleaned
+
+ try:
+ tmp = res.encode("utf8")
+ except:
+ tmp = res
+
+ f.write(tmp)
+ f.close()
+
+ if just_header:
+ #parse header
+ header = {"code": self.req.code}
+ for line in res.splitlines():
+ line = line.strip()
+ if not line or ":" not in line: continue
+
+ key, none, value = line.partition(":")
+ key = key.lower().strip()
+ value = value.strip()
+
+ if key in header:
+ if type(header[key]) == list:
+ header[key].append(value)
+ else:
+ header[key] = [header[key], value]
+ else:
+ header[key] = value
+ res = header
+
+ return res
+
+ def download(self, url, get={}, post={}, ref=True, cookies=True, disposition=False):
+ """Downloads the content at url to download folder
+
+ :param url:
+ :param get:
+ :param post:
+ :param ref:
+ :param cookies:
+ :param disposition: if True and server provides content-disposition header\
+ the filename will be changed if needed
+ :return: The location where the file was saved
+ """
+
+ self.checkForSameFiles()
+
+ self.pyfile.setStatus("downloading")
+
+ download_folder = self.config['general']['download_folder']
+
+ location = save_join(download_folder, self.pyfile.package().folder)
+
+ if not exists(location):
+ makedirs(location, int(self.core.config["permission"]["folder"], 8))
+
+ if self.core.config["permission"]["change_dl"] and os.name != "nt":
+ try:
+ uid = getpwnam(self.config["permission"]["user"])[2]
+ gid = getgrnam(self.config["permission"]["group"])[2]
+
+ chown(location, uid, gid)
+ except Exception, e:
+ self.log.warning(_("Setting User and Group failed: %s") % str(e))
+
+ # convert back to unicode
+ location = fs_decode(location)
+ name = save_path(self.pyfile.name)
+
+ filename = join(location, name)
+
+ self.core.hookManager.dispatchEvent("downloadStarts", self.pyfile, url, filename)
+
+ try:
+ newname = self.req.httpDownload(url, filename, get=get, post=post, ref=ref, cookies=cookies,
+ chunks=self.getChunkCount(), resume=self.resumeDownload,
+ progressNotify=self.pyfile.setProgress, disposition=disposition)
+ finally:
+ self.pyfile.size = self.req.size
+
+ if disposition and newname and newname != name: #triple check, just to be sure
+ self.log.info("%(name)s saved as %(newname)s" % {"name": name, "newname": newname})
+ self.pyfile.name = newname
+ filename = join(location, newname)
+
+ fs_filename = fs_encode(filename)
+
+ if self.core.config["permission"]["change_file"]:
+ chmod(fs_filename, int(self.core.config["permission"]["file"], 8))
+
+ if self.core.config["permission"]["change_dl"] and os.name != "nt":
+ try:
+ uid = getpwnam(self.config["permission"]["user"])[2]
+ gid = getgrnam(self.config["permission"]["group"])[2]
+
+ chown(fs_filename, uid, gid)
+ except Exception, e:
+ self.log.warning(_("Setting User and Group failed: %s") % str(e))
+
+ self.lastDownload = filename
+ return self.lastDownload
+
+ def checkDownload(self, rules, api_size=0, max_size=50000, delete=True, read_size=0):
+ """ checks the content of the last downloaded file, re match is saved to `lastCheck`
+
+ :param rules: dict with names and rules to match (compiled regexp or strings)
+ :param api_size: expected file size
+ :param max_size: if the file is larger then it wont be checked
+ :param delete: delete if matched
+ :param read_size: amount of bytes to read from files larger then max_size
+ :return: dictionary key of the first rule that matched
+ """
+ lastDownload = fs_encode(self.lastDownload)
+ if not exists(lastDownload): return None
+
+ size = stat(lastDownload)
+ size = size.st_size
+
+ if api_size and api_size <= size: return None
+ elif size > max_size and not read_size: return None
+ self.log.debug("Download Check triggered")
+ f = open(lastDownload, "rb")
+ content = f.read(read_size if read_size else -1)
+ f.close()
+ #produces encoding errors, better log to other file in the future?
+ #self.log.debug("Content: %s" % content)
+ for name, rule in rules.iteritems():
+ if type(rule) in (str, unicode):
+ if rule in content:
+ if delete:
+ remove(lastDownload)
+ return name
+ elif hasattr(rule, "search"):
+ m = rule.search(content)
+ if m:
+ if delete:
+ remove(lastDownload)
+ self.lastCheck = m
+ return name
+
+
+ def getPassword(self):
+ """ get the password the user provided in the package"""
+ password = self.pyfile.package().password
+ if not password: return ""
+ return password
+
+
+ def checkForSameFiles(self, starting=False):
+ """ checks if same file was/is downloaded within same package
+
+ :param starting: indicates that the current download is going to start
+ :raises SkipDownload:
+ """
+
+ pack = self.pyfile.package()
+
+ for pyfile in self.core.files.cache.values():
+ if pyfile != self.pyfile and pyfile.name == self.pyfile.name and pyfile.package().folder == pack.folder:
+ if pyfile.status in (0, 12): #finished or downloading
+ raise SkipDownload(pyfile.pluginname)
+ elif pyfile.status in (
+ 5, 7) and starting: #a download is waiting/starting and was appenrently started before
+ raise SkipDownload(pyfile.pluginname)
+
+ download_folder = self.config['general']['download_folder']
+ location = save_join(download_folder, pack.folder, self.pyfile.name)
+
+ if starting and self.core.config['download']['skip_existing'] and exists(location):
+ size = os.stat(location).st_size
+ if size >= self.pyfile.size:
+ raise SkipDownload("File exists.")
+
+ pyfile = self.core.db.findDuplicates(self.pyfile.id, self.pyfile.package().folder, self.pyfile.name)
+ if pyfile:
+ if exists(location):
+ raise SkipDownload(pyfile[0])
+
+ self.log.debug("File %s not skipped, because it does not exists." % self.pyfile.name)
+
+ def clean(self):
+ """ clean everything and remove references """
+ if hasattr(self, "pyfile"):
+ del self.pyfile
+ if hasattr(self, "req"):
+ self.req.close()
+ del self.req
+ if hasattr(self, "thread"):
+ del self.thread
+ if hasattr(self, "html"):
+ del self.html
diff --git a/module/plugins/internal/ReCaptcha.py b/module/plugins/internal/ReCaptcha.py
new file mode 100644
index 000000000..a9d0f3752
--- /dev/null
+++ b/module/plugins/internal/ReCaptcha.py
@@ -0,0 +1,195 @@
+# -*- coding: utf-8 -*-
+
+import random
+import re
+import time
+import urlparse
+
+from base64 import b64encode
+
+from module.plugins.internal.Captcha import Captcha
+
+
+class ReCaptcha(Captcha):
+ __name__ = "ReCaptcha"
+ __type__ = "captcha"
+ __version__ = "0.17"
+
+ __description__ = """ReCaptcha captcha service plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("pyLoad Team", "admin@pyload.org"),
+ ("Walter Purcaro", "vuolter@gmail.com"),
+ ("zapp-brannigan", "fuerst.reinje@web.de")]
+
+
+ KEY_V1_PATTERN = r'(?:recaptcha(?:/api|\.net)/(?:challenge|noscript)\?k=|Recaptcha\.create\s*\(\s*["\'])([\w-]+)'
+ KEY_V2_PATTERN = r'(?:data-sitekey=["\']|["\']sitekey["\']:\s*["\'])([\w-]+)'
+
+
+ def detect_key(self, html=None):
+ html = html or self.retrieve_html()
+
+ m = re.search(self.KEY_V2_PATTERN, html) or re.search(self.KEY_V1_PATTERN, html)
+ if m:
+ self.key = m.group(1).strip()
+ self.logDebug("Key: %s" % self.key)
+ return self.key
+ else:
+ self.logWarning("Key pattern not found")
+ return None
+
+
+ def challenge(self, key=None, html=None, version=None):
+ key = key or self.retrieve_key(html)
+
+ if version in (1, 2):
+ return getattr(self, "_challenge_v%s" % version)(key)
+
+ else:
+ return self.challenge(key,
+ version=2 if re.search(self.KEY_V2_PATTERN, html or self.retrieve_html()) else 1)
+
+
+ def _challenge_v1(self, key):
+ html = self.plugin.req.load("http://www.google.com/recaptcha/api/challenge",
+ get={'k': key})
+ try:
+ challenge = re.search("challenge : '(.+?)',", html).group(1)
+ server = re.search("server : '(.+?)',", html).group(1)
+
+ except AttributeError:
+ self.fail(_("ReCaptcha challenge pattern not found"))
+
+ self.logDebug("Challenge: %s" % challenge)
+
+ return self.result(server, challenge, key)
+
+
+ def result(self, server, challenge, key):
+ self.plugin.req.load("http://www.google.com/recaptcha/api/js/recaptcha.js")
+ html = self.plugin.req.load("http://www.google.com/recaptcha/api/reload",
+ get={'c' : challenge,
+ 'k' : key,
+ 'reason': "i",
+ 'type' : "image"})
+
+ try:
+ challenge = re.search('\(\'(.+?)\',',html).group(1)
+
+ except AttributeError:
+ self.fail(_("ReCaptcha second challenge pattern not found"))
+
+ self.logDebug("Second challenge: %s" % challenge)
+ result = self.plugin.decryptCaptcha("%simage" % server,
+ get={'c': challenge},
+ cookies=True,
+ forceUser=True,
+ imgtype="jpg")
+
+ self.logDebug("Result: %s" % result)
+
+ return result, challenge
+
+
+ def _collectApiInfo(self):
+ html = self.plugin.req.load("http://www.google.com/recaptcha/api.js")
+ a = re.search(r'po.src = \'(.*?)\';', html).group(1)
+ vers = a.split("/")[5]
+
+ self.logDebug("API version: %s" % vers)
+
+ language = a.split("__")[1].split(".")[0]
+
+ self.logDebug("API language: %s" % language)
+
+ html = self.plugin.req.load("https://apis.google.com/js/api.js")
+ b = re.search(r'"h":"(.*?)","', html).group(1)
+ jsh = b.decode('unicode-escape')
+
+ self.logDebug("API jsh-string: %s" % jsh)
+
+ return vers, language, jsh
+
+
+ def _prepareTimeAndRpc(self):
+ self.plugin.req.load("http://www.google.com/recaptcha/api2/demo")
+
+ millis = int(round(time.time() * 1000))
+
+ self.logDebug("Time: %s" % millis)
+
+ rand = random.randint(1, 99999999)
+ a = "0.%s" % str(rand * 2147483647)
+ rpc = int(100000000 * float(a))
+
+ self.logDebug("Rpc-token: %s" % rpc)
+
+ return millis, rpc
+
+
+ def _challenge_v2(self, key, parent=None):
+ if parent is None:
+ try:
+ parent = urlparse.urljoin("http://", urlparse.urlparse(self.plugin.pyfile.url).netloc)
+
+ except Exception:
+ parent = ""
+
+ botguardstring = "!A"
+ vers, language, jsh = self._collectApiInfo()
+ millis, rpc = self._prepareTimeAndRpc()
+
+ html = self.plugin.req.load("https://www.google.com/recaptcha/api2/anchor",
+ get={'k' : key,
+ 'hl' : language,
+ 'v' : vers,
+ 'usegapi' : "1",
+ 'jsh' : "%s#id=IO_%s" % (jsh, millis),
+ 'parent' : parent,
+ 'pfname' : "",
+ 'rpctoken': rpc})
+
+ token1 = re.search(r'id="recaptcha-token" value="(.*?)">', html)
+ self.logDebug("Token #1: %s" % token1.group(1))
+
+ html = self.plugin.req.load("https://www.google.com/recaptcha/api2/frame",
+ get={'c' : token1.group(1),
+ 'hl' : language,
+ 'v' : vers,
+ 'bg' : botguardstring,
+ 'k' : key,
+ 'usegapi': "1",
+ 'jsh' : jsh}).decode('unicode-escape')
+
+ token2 = re.search(r'"finput","(.*?)",', html)
+ self.logDebug("Token #2: %s" % token2.group(1))
+
+ token3 = re.search(r'"rresp","(.*?)",', html)
+ self.logDebug("Token #3: %s" % token3.group(1))
+
+ millis_captcha_loading = int(round(time.time() * 1000))
+ captcha_response = self.plugin.decryptCaptcha("https://www.google.com/recaptcha/api2/payload",
+ get={'c':token3.group(1), 'k':key},
+ cookies=True,
+ forceUser=True)
+ response = b64encode('{"response":"%s"}' % captcha_response)
+
+ self.logDebug("Result: %s" % response)
+
+ timeToSolve = int(round(time.time() * 1000)) - millis_captcha_loading
+ timeToSolveMore = timeToSolve + int(float("0." + str(random.randint(1, 99999999))) * 500)
+
+ html = self.plugin.req.load("https://www.google.com/recaptcha/api2/userverify",
+ post={'k' : key,
+ 'c' : token3.group(1),
+ 'response': response,
+ 't' : timeToSolve,
+ 'ct' : timeToSolveMore,
+ 'bg' : botguardstring})
+
+ token4 = re.search(r'"uvresp","(.*?)",', html)
+ self.logDebug("Token #4: %s" % token4.group(1))
+
+ result = token4.group(1)
+
+ return result, None
diff --git a/module/plugins/internal/SevenZip.py b/module/plugins/internal/SevenZip.py
new file mode 100644
index 000000000..624f6c939
--- /dev/null
+++ b/module/plugins/internal/SevenZip.py
@@ -0,0 +1,153 @@
+# -*- coding: utf-8 -*-
+
+import os
+import re
+import subprocess
+
+from module.plugins.internal.UnRar import ArchiveError, CRCError, PasswordError, UnRar, renice
+from module.utils import fs_encode, save_join
+
+
+class SevenZip(UnRar):
+ __name__ = "SevenZip"
+ __version__ = "0.11"
+
+ __description__ = """7-Zip extractor plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("Michael Nowak" , "" ),
+ ("Walter Purcaro", "vuolter@gmail.com")]
+
+
+ CMD = "7z"
+ VERSION = ""
+
+ EXTENSIONS = [".7z", ".xz", ".zip", ".gz", ".gzip", ".tgz", ".bz2", ".bzip2",
+ ".tbz2", ".tbz", ".tar", ".wim", ".swm", ".lzma", ".rar", ".cab",
+ ".arj", ".z", ".taz", ".cpio", ".rpm", ".deb", ".lzh", ".lha",
+ ".chm", ".chw", ".hxs", ".iso", ".msi", ".doc", ".xls", ".ppt",
+ ".dmg", ".xar", ".hfs", ".exe", ".ntfs", ".fat", ".vhd", ".mbr",
+ ".squashfs", ".cramfs", ".scap"]
+
+
+ #@NOTE: there are some more uncovered 7z formats
+ re_filelist = re.compile(r'([\d\:]+)\s+([\d\:]+)\s+([\w\.]+)\s+(\d+)\s+(\d+)\s+(.+)')
+ re_wrongpwd = re.compile(r'(Can not open encrypted archive|Wrong password|Encrypted\s+\=\s+\+)', re.I)
+ re_wrongcrc = re.compile(r'CRC Failed|Can not open file', re.I)
+ re_version = re.compile(r'7-Zip\s(?:\[64\]\s)?(\d+\.\d+)', re.I)
+
+
+ @classmethod
+ def isUsable(cls):
+ if os.name == "nt":
+ cls.CMD = os.path.join(pypath, "7z.exe")
+ p = subprocess.Popen([cls.CMD], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+ else:
+ p = subprocess.Popen([cls.CMD], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+
+ m = cls.re_version.search(out)
+ cls.VERSION = m.group(1) if m else '(version unknown)'
+
+ return True
+
+
+ def verify(self, password):
+ # 7z can't distinguish crc and pw error in test
+ p = self.call_cmd("l", "-slt", fs_encode(self.filename))
+ out, err = p.communicate()
+
+ if self.re_wrongpwd.search(out):
+ raise PasswordError
+
+ if self.re_wrongpwd.search(err):
+ raise PasswordError
+
+ if self.re_wrongcrc.search(err):
+ raise CRCError(err)
+
+
+
+ def check(self, password):
+ p = self.call_cmd("l", "-slt", fs_encode(self.filename))
+ out, err = p.communicate()
+
+ # check if output or error macthes the 'wrong password'-Regexp
+ if self.re_wrongpwd.search(out):
+ raise PasswordError
+
+ if self.re_wrongcrc.search(out):
+ raise CRCError(_("Header protected"))
+
+
+ def repair(self):
+ return False
+
+
+ def extract(self, password=None):
+ command = "x" if self.fullpath else "e"
+
+ p = self.call_cmd(command, '-o' + self.out, fs_encode(self.filename), password=password)
+
+ renice(p.pid, self.renice)
+
+ # communicate and retrieve stderr
+ self._progress(p)
+ err = p.stderr.read().strip()
+
+ if err:
+ if self.re_wrongpwd.search(err):
+ raise PasswordError
+
+ elif self.re_wrongcrc.search(err):
+ raise CRCError(err)
+
+ else: #: raise error if anything is on stderr
+ raise ArchiveError(err)
+
+ if p.returncode > 1:
+ raise ArchiveError(_("Process return code: %d") % p.returncode)
+
+ self.files = self.list(password)
+
+
+ def list(self, password=None):
+ command = "l" if self.fullpath else "l"
+
+ p = self.call_cmd(command, fs_encode(self.filename), password=password)
+ out, err = p.communicate()
+
+ if "Can not open" in err:
+ raise ArchiveError(_("Cannot open file"))
+
+ if p.returncode > 1:
+ raise ArchiveError(_("Process return code: %d") % p.returncode)
+
+ result = set()
+ for groups in self.re_filelist.findall(out):
+ f = groups[-1].strip()
+ result.add(save_join(self.out, f))
+
+ return list(result)
+
+
+ def call_cmd(self, command, *xargs, **kwargs):
+ args = []
+
+ #overwrite flag
+ if self.overwrite:
+ args.append("-y")
+
+ #set a password
+ if "password" in kwargs and kwargs["password"]:
+ args.append("-p%s" % kwargs["password"])
+ else:
+ args.append("-p-")
+
+ #@NOTE: return codes are not reliable, some kind of threading, cleanup whatever issue
+ call = [self.CMD, command] + args + list(xargs)
+
+ self.manager.logDebug(" ".join(call))
+
+ p = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ return p
diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py
index 43b1347fd..be0d5e9d5 100644
--- a/module/plugins/internal/SimpleCrypter.py
+++ b/module/plugins/internal/SimpleCrypter.py
@@ -1,29 +1,25 @@
# -*- coding: utf-8 -*-
import re
+import urlparse
-from urlparse import urlparse
-
-from module.plugins.Crypter import Crypter
+from module.plugins.internal.Crypter import Crypter
from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo, replace_patterns, set_cookies
-from module.utils import fixup
+from module.utils import fixup, html_unescape
class SimpleCrypter(Crypter, SimpleHoster):
__name__ = "SimpleCrypter"
__type__ = "crypter"
- __version__ = "0.38"
+ __version__ = "0.53"
__pattern__ = r'^unmatchable$'
- __config__ = [("use_subfolder", "bool", "Save package to subfolder", True), #: Overrides core.config['general']['folder_per_package']
- ("subfolder_per_package", "bool", "Create a subfolder for each package", True)]
+ __config__ = [("use_subfolder" , "bool", "Save package to subfolder" , True), #: Overrides core.config['general']['folder_per_package']
+ ("subfolder_per_pack", "bool", "Create a subfolder for each package", True)]
__description__ = """Simple decrypter plugin"""
__license__ = "GPLv3"
- __authors__ = [("stickell", "l.stickell@yahoo.it"),
- ("zoidberg", "zoidberg@mujmail.cz"),
- ("Walter Purcaro", "vuolter@gmail.com")]
-
+ __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
"""
Following patterns should be defined by each crypter:
@@ -56,27 +52,15 @@ class SimpleCrypter(Crypter, SimpleHoster):
return the html of the page number page_n
"""
- LINK_PATTERN = None
-
- NAME_REPLACEMENTS = [("&#?\w+;", fixup)]
- URL_REPLACEMENTS = []
-
- TEXT_ENCODING = False #: Set to True or encoding name if encoding in http header is not correct
- COOKIES = True #: or False or list of tuples [(domain, name, value)]
-
- LOGIN_ACCOUNT = False
- LOGIN_PREMIUM = False
-
-
#@TODO: Remove in 0.4.10
def init(self):
account_name = (self.__name__ + ".py").replace("Folder.py", "").replace(".py", "")
- account = self.core.accountManager.getAccountPlugin(account_name)
+ account = self.pyfile.m.core.accountManager.getAccountPlugin(account_name)
if account and account.canUse():
self.user, data = account.selectAccount()
- self.req = account.getAccountRequest(self.user)
- self.premium = account.isPremium(self.user)
+ self.req = account.getAccountRequest(self.user)
+ self.premium = account.isPremium(self.user)
self.account = account
@@ -85,7 +69,9 @@ class SimpleCrypter(Crypter, SimpleHoster):
self.pyfile.error = "" #@TODO: Remove in 0.4.10
self.info = {}
- self.links = [] #@TODO: Move to hoster class in 0.4.10
+ self.html = ""
+ self.link = "" #@TODO: Move to Hoster in 0.4.10
+ self.links = [] #@TODO: Move to Hoster in 0.4.10
if self.LOGIN_PREMIUM and not self.premium:
self.fail(_("Required premium account not found"))
@@ -101,24 +87,46 @@ class SimpleCrypter(Crypter, SimpleHoster):
self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS)
+ def handleDirect(self, pyfile):
+ for i in xrange(10): #@TODO: Use `pycurl.MAXREDIRS` value in 0.4.10
+ redirect = self.link or pyfile.url
+ self.logDebug("Redirect #%d to: %s" % (i, redirect))
+
+ header = self.load(redirect, just_header=True, decode=True)
+ if 'location' in header and header['location']:
+ self.link = header['location']
+ else:
+ break
+ else:
+ self.logError(_("Too many redirects"))
+
+
def decrypt(self, pyfile):
self.prepare()
- self.preload()
- self.checkInfo()
+ self.logDebug("Looking for link redirect...")
+ self.handleDirect(pyfile)
+
+ if self.link:
+ self.urls = [self.link]
- self.links = self.getLinks()
+ else:
+ self.preload()
+ self.checkInfo()
- if hasattr(self, 'PAGES_PATTERN') and hasattr(self, 'loadPage'):
- self.handlePages(pyfile)
+ self.links = self.getLinks()
- self.logDebug("Package has %d links" % len(self.links))
+ if hasattr(self, 'PAGES_PATTERN') and hasattr(self, 'loadPage'):
+ self.handlePages(pyfile)
+
+ self.logDebug("Package has %d links" % len(self.links))
if self.links:
+ self.links = [html_unescape(l.decode('unicode-escape').strip()) for l in self.links] #@TODO: Move to Crypter in 0.4.10
self.packages = [(self.info['name'], self.links, self.info['folder'])]
elif not self.urls and not self.packages: #@TODO: Remove in 0.4.10
- self.fail("No link grabbed")
+ self.fail(_("No link grabbed"))
def checkNameSize(self, getinfo=True):
@@ -128,8 +136,8 @@ class SimpleCrypter(Crypter, SimpleHoster):
self.logDebug("File info (AFTER): %s" % self.info)
try:
- url = self.info['url']
- name = self.info['name']
+ url = self.info['url'].strip()
+ name = self.info['name'].strip()
if name and name != url:
self.pyfile.name = name
@@ -151,13 +159,17 @@ class SimpleCrypter(Crypter, SimpleHoster):
Returns the links extracted from self.html
You should override this only if it's impossible to extract links using only the LINK_PATTERN.
"""
- return re.findall(self.LINK_PATTERN, self.html)
+ url_p = urlparse.urlparse(self.pyfile.url)
+ baseurl = "%s://%s" % (url_p.scheme, url_p.netloc)
+
+ return [urlparse.urljoin(baseurl, link) if not urlparse.urlparse(link).scheme else link \
+ for link in re.findall(self.LINK_PATTERN, self.html)]
def handlePages(self, pyfile):
try:
pages = int(re.search(self.PAGES_PATTERN, self.html).group(1))
- except:
+ except Exception:
pages = 1
for p in xrange(2, pages + 1):
diff --git a/module/plugins/internal/SimpleDereferer.py b/module/plugins/internal/SimpleDereferer.py
deleted file mode 100644
index 53b80f827..000000000
--- a/module/plugins/internal/SimpleDereferer.py
+++ /dev/null
@@ -1,99 +0,0 @@
-# -*- coding: utf-8 -*-
-
-import re
-
-from urllib import unquote
-
-from module.plugins.Crypter import Crypter
-from module.plugins.internal.SimpleHoster import directLink, set_cookies
-
-
-class SimpleDereferer(Crypter):
- __name__ = "SimpleDereferer"
- __type__ = "crypter"
- __version__ = "0.03"
-
- __pattern__ = r'^unmatchable$'
- __config__ = [("use_subfolder", "bool", "Save package to subfolder", True),
- ("subfolder_per_package", "bool", "Create a subfolder for each package", True)]
-
- __description__ = """Simple dereferer plugin"""
- __license__ = "GPLv3"
- __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
-
-
- """
- Following patterns should be defined by each crypter:
-
- LINK_PATTERN: Regex to catch the redirect url in group(1)
- example: LINK_PATTERN = r'<div class="link"><a href="(.+?)"'
-
- OFFLINE_PATTERN: (optional) Checks if the page is unreachable
- example: OFFLINE_PATTERN = r'File (deleted|not found)'
-
- TEMP_OFFLINE_PATTERN: (optional) Checks if the page is temporarily unreachable
- example: TEMP_OFFLINE_PATTERN = r'Server maintainance'
-
-
- You can override the getLinks method if you need a more sophisticated way to extract the redirect url.
- """
-
- LINK_PATTERN = None
-
- TEXT_ENCODING = False
- COOKIES = True
-
-
- def decrypt(self, pyfile):
- link = directLink(self, pyfile.url)
-
- if not link:
- try:
- link = unquote(re.match(self.__pattern__, pyfile.url).group('LINK'))
-
- except Exception:
- self.prepare()
- self.preload()
-
- if self.html is None:
- self.fail(_("No html retrieved"))
-
- self.checkStatus()
-
- link = self.getLink()
-
- if link.strip():
- self.urls = [link.strip()] #@TODO: Remove `.strip()` in 0.4.10
-
- elif not self.urls and not self.packages: #@TODO: Remove in 0.4.10
- self.fail("No link grabbed")
-
-
- def prepare(self):
- self.req.setOption("timeout", 120)
-
- if isinstance(self.COOKIES, list):
- set_cookies(self.req.cj, self.COOKIES)
-
-
- def preload(self):
- self.html = self.load(self.pyfile.url, cookies=bool(self.COOKIES), decode=not self.TEXT_ENCODING)
-
- if isinstance(self.TEXT_ENCODING, basestring):
- self.html = unicode(self.html, self.TEXT_ENCODING)
-
-
- def checkStatus(self):
- if hasattr(self, "OFFLINE_PATTERN") and re.search(self.OFFLINE_PATTERN, self.html):
- self.offline()
-
- elif hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, self.html):
- self.tempOffline()
-
-
- def getLink(self):
- try:
- return re.search(self.LINK_PATTERN, self.html).group(1)
-
- except Exception:
- pass
diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py
index fa1ea45f2..4a3b7dcf7 100644
--- a/module/plugins/internal/SimpleHoster.py
+++ b/module/plugins/internal/SimpleHoster.py
@@ -1,20 +1,22 @@
# -*- coding: utf-8 -*-
-import re
+from __future__ import with_statement
-from inspect import isclass
-from os.path import exists
-from time import time
-from urllib import unquote
-from urlparse import urljoin, urlparse
+import datetime
+import mimetypes
+import os
+import re
+import time
+import urllib
+import urlparse
from module.PyFile import statusMap as _statusMap
from module.network.CookieJar import CookieJar
from module.network.HTTPRequest import BadHeader
from module.network.RequestFactory import getURL
-from module.plugins.Hoster import Hoster
-from module.plugins.Plugin import Fail
-from module.utils import fixup, fs_encode, parseFileSize
+from module.plugins.internal.Hoster import Hoster
+from module.plugins.internal.Plugin import Fail, Retry
+from module.utils import decode, fixup, fs_encode, html_unescape, parseFileSize
#@TODO: Adapt and move to PyFile in 0.4.10
@@ -27,7 +29,7 @@ def _error(self, reason, type):
type = "unknown"
msg = _("%s error") % type.strip().capitalize() if type else _("Error")
- msg += ": %s" % reason.strip() if reason else ""
+ msg += (": %s" % reason.strip()) if reason else ""
msg += _(" | Plugin may be out of date")
raise Fail(msg)
@@ -74,7 +76,7 @@ def parseHtmlForm(attr_str, html, input_names={}):
if name:
value = parseHtmlTagAttrValue("value", inputtag.group(1))
if not value:
- inputs[name] = inputtag.group(3) or ''
+ inputs[name] = inputtag.group(3) or ""
else:
inputs[name] = value
@@ -100,43 +102,77 @@ def parseHtmlForm(attr_str, html, input_names={}):
return {}, None #: no matching form found
-#: Deprecated
+#@TODO: Remove in 0.4.10
def parseFileInfo(plugin, url="", html=""):
if hasattr(plugin, "getInfo"):
info = plugin.getInfo(url, html)
res = info['name'], info['size'], info['status'], info['url']
else:
- res = urlparse(unquote(url)).path.split('/')[-1] or _("Unknown"), 0, 3, url
+ url = urllib.unquote(url)
+ url_p = urlparse.urlparse(url)
+ res = ((url_p.path.split('/')[-1]
+ or url_p.query.split('=', 1)[::-1][0].split('&', 1)[0]
+ or url_p.netloc.split('.', 1)[0]),
+ 0,
+ 3 if url else 8,
+ url)
return res
#@TODO: Remove in 0.4.10
-#@NOTE: Every plugin must have own parseInfos classmethod to work with 0.4.10
def create_getInfo(plugin):
+ def getInfo(urls):
+ for url in urls:
+ if hasattr(plugin, "URL_REPLACEMENTS"):
+ url = replace_patterns(url, plugin.URL_REPLACEMENTS)
+ yield parseFileInfo(plugin, url)
+
+ return getInfo
+
+
+def timestamp():
+ return int(time.time() * 1000)
+
- def generator(list):
- for x in list:
- yield x
+#@TODO: Move to Hoster in 0.4.10
+def getFileURL(self, url, follow_location=None):
+ link = ""
+ redirect = 1
- if hasattr(plugin, "parseInfos"):
- fn = lambda urls: generator((info['name'], info['size'], info['status'], info['url']) for info in plugin.parseInfos(urls))
+ if type(follow_location) is int:
+ redirect = max(follow_location, 1)
else:
- fn = lambda urls: generator(parseFileInfo(url) for url in urls)
+ redirect = 10
- return fn
+ for i in xrange(redirect):
+ try:
+ self.logDebug("Redirect #%d to: %s" % (i, url))
+ header = self.load(url, just_header=True, decode=True)
+ except Exception: #: Bad bad bad... rewrite this part in 0.4.10
+ req = pyreq.getHTTPRequest()
+ res = req.load(url, just_header=True, decode=True)
-def timestamp():
- return int(time() * 1000)
+ req.close()
+ header = {"code": req.code}
+ for line in res.splitlines():
+ line = line.strip()
+ if not line or ":" not in line:
+ continue
-#@TODO: Move to hoster class in 0.4.10
-def directLink(self, url, resumable=False):
- link = ""
+ key, none, value = line.partition(":")
+ key = key.lower().strip()
+ value = value.strip()
- for i in xrange(5 if resumable else 1):
- header = self.load(url, ref=True, cookies=True, just_header=True, decode=True)
+ if key in header:
+ if type(header[key]) == list:
+ header[key].append(value)
+ else:
+ header[key] = [header[key], value]
+ else:
+ header[key] = value
if 'content-disposition' in header:
link = url
@@ -144,42 +180,59 @@ def directLink(self, url, resumable=False):
elif 'location' in header and header['location']:
location = header['location']
- if not urlparse(location).scheme:
- p = urlparse(url)
- base = "%s://%s" % (p.scheme, p.netloc)
- location = urljoin(base, location)
+ if not urlparse.urlparse(location).scheme:
+ url_p = urlparse.urlparse(url)
+ baseurl = "%s://%s" % (url_p.scheme, url_p.netloc)
+ location = urlparse.urljoin(baseurl, location)
- if resumable:
+ if 'code' in header and header['code'] == 302:
+ link = location
+
+ if follow_location:
url = location
- self.logDebug("Redirect #%d to: %s" % (++i, location))
continue
- elif 'code' in header and header['code'] == 302:
- link = location
+ else:
+ extension = os.path.splitext(urlparse.urlparse(url).path.split('/')[-1])[-1]
- elif 'content-type' in header and header['content-type'] and "html" not in header['content-type']:
- link = url
+ if 'content-type' in header and header['content-type']:
+ mimetype = header['content-type'].split(';')[0].strip()
+
+ elif extension:
+ mimetype = mimetypes.guess_type(extension, False)[0] or "application/octet-stream"
+
+ else:
+ mimetype = ""
+
+ if mimetype and (link or 'html' not in mimetype):
+ link = url
+ else:
+ link = ""
break
+
else:
- self.logError(_("Too many redirects"))
+ try:
+ self.logError(_("Too many redirects"))
+ except Exception:
+ pass
return link
def secondsToMidnight(gmt=0):
- now = datetime.utcnow() + timedelta(hours=gmt)
+ now = datetime.datetime.utcnow() + datetime.timedelta(hours=gmt)
if now.hour is 0 and now.minute < 10:
midnight = now
else:
- midnight = now + timedelta(days=1)
+ midnight = now + datetime.timedelta(days=1)
td = midnight.replace(hour=0, minute=10, second=0, microsecond=0) - now
if hasattr(td, 'total_seconds'):
res = td.total_seconds()
- else: #@NOTE: work-around for python 2.5 and 2.6 missing timedelta.total_seconds
+ else: #@NOTE: work-around for python 2.5 and 2.6 missing datetime.timedelta.total_seconds
res = (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
return int(res)
@@ -188,39 +241,39 @@ def secondsToMidnight(gmt=0):
class SimpleHoster(Hoster):
__name__ = "SimpleHoster"
__type__ = "hoster"
- __version__ = "0.96"
+ __version__ = "1.66"
__pattern__ = r'^unmatchable$'
+ __config__ = [("use_premium", "bool", "Use premium account if available" , True),
+ ("fallback" , "bool", "Fallback to free download if premium fails", True)]
__description__ = """Simple hoster plugin"""
__license__ = "GPLv3"
- __authors__ = [("zoidberg", "zoidberg@mujmail.cz"),
- ("stickell", "l.stickell@yahoo.it"),
- ("Walter Purcaro", "vuolter@gmail.com")]
-
+ __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
"""
- Info patterns should be defined by each hoster:
+ Info patterns:
- INFO_PATTERN: (optional) Name and Size of the file
+ INFO_PATTERN: (mandatory) Name and Size of the file
example: INFO_PATTERN = r'(?P<N>file_name) (?P<S>file_size) (?P<U>size_unit)'
or
- NAME_PATTERN: (optional) Name that will be set for the file
+ NAME_PATTERN: (mandatory) Name that will be set for the file
example: NAME_PATTERN = r'(?P<N>file_name)'
- SIZE_PATTERN: (optional) Size that will be checked for the file
+
+ SIZE_PATTERN: (mandatory) Size that will be checked for the file
example: SIZE_PATTERN = r'(?P<S>file_size) (?P<U>size_unit)'
HASHSUM_PATTERN: (optional) Hash code and type of the file
example: HASHSUM_PATTERN = r'(?P<H>hash_code) (?P<T>MD5)'
- OFFLINE_PATTERN: (optional) Check if the page is unreachable
+ OFFLINE_PATTERN: (mandatory) Check if the page is unreachable
example: OFFLINE_PATTERN = r'File (deleted|not found)'
TEMP_OFFLINE_PATTERN: (optional) Check if the page is temporarily unreachable
example: TEMP_OFFLINE_PATTERN = r'Server (maintenance|maintainance)'
- Error handling patterns are all optional:
+ Error patterns:
WAIT_PATTERN: (optional) Detect waiting time
example: WAIT_PATTERN = r''
@@ -228,46 +281,65 @@ class SimpleHoster(Hoster):
PREMIUM_ONLY_PATTERN: (optional) Check if the file can be downloaded only with a premium account
example: PREMIUM_ONLY_PATTERN = r'Premium account required'
+ HAPPY_HOUR_PATTERN: (optional)
+ example: HAPPY_HOUR_PATTERN = r'Happy hour'
+
+ IP_BLOCKED_PATTERN: (optional)
+ example: IP_BLOCKED_PATTERN = r'in your country'
+
+ DL_LIMIT_PATTERN: (optional)
+ example: DL_LIMIT_PATTERN = r'download limit'
+
+ SIZE_LIMIT_PATTERN: (optional)
+ example: SIZE_LIMIT_PATTERN = r'up to'
+
ERROR_PATTERN: (optional) Detect any error preventing download
example: ERROR_PATTERN = r''
- Instead overriding handleFree and handlePremium methods you can define the following patterns for direct download:
+ Instead overriding handleFree and handlePremium methods you may define the following patterns for basic link handling:
- LINK_FREE_PATTERN: (optional) group(1) should be the direct link for free download
- example: LINK_FREE_PATTERN = r'<div class="link"><a href="(.+?)"'
+ LINK_PATTERN: (optional) group(1) should be the direct link for free and premium download
+ example: LINK_PATTERN = r'<div class="link"><a href="(.+?)"'
+ or
+ LINK_FREE_PATTERN: (optional) group(1) should be the direct link for free download
+ example: LINK_FREE_PATTERN = r'<div class="link"><a href="(.+?)"'
- LINK_PREMIUM_PATTERN: (optional) group(1) should be the direct link for premium download
- example: LINK_PREMIUM_PATTERN = r'<div class="link"><a href="(.+?)"'
+ LINK_PREMIUM_PATTERN: (optional) group(1) should be the direct link for premium download
+ example: LINK_PREMIUM_PATTERN = r'<div class="link"><a href="(.+?)"'
"""
NAME_REPLACEMENTS = [("&#?\w+;", fixup)]
SIZE_REPLACEMENTS = []
URL_REPLACEMENTS = []
- TEXT_ENCODING = False #: Set to True or encoding name if encoding value in http header is not correct
- COOKIES = True #: or False or list of tuples [(domain, name, value)]
+ FILE_ERRORS = [('Html error' , r'\A(?:\s*<.+>)?((?:[\w\s]*(?:[Ee]rror|ERROR)\s*\:?)?\s*\d{3})(?:\Z|\s+)'),
+ ('Request error', r'([Aa]n error occured while processing your request)' ),
+ ('Html file' , r'\A\s*<!DOCTYPE html' )]
+
+ CHECK_FILE = True #: Set to False to not check the last downloaded file with declared error patterns
CHECK_TRAFFIC = False #: Set to True to force checking traffic left for premium account
+ COOKIES = True #: or False or list of tuples [(domain, name, value)]
DIRECT_LINK = None #: Set to True to looking for direct link (as defined in handleDirect method), set to None to do it if self.account is True else False
- MULTI_HOSTER = False #: Set to True to leech other hoster link (as defined in handleMulti method)
+ DISPOSITION = True #: Set to True to use any content-disposition value in http header as file name
LOGIN_ACCOUNT = False #: Set to True to require account login
+ LOGIN_PREMIUM = False #: Set to True to require premium account login
+ MULTI_HOSTER = False #: Set to True to leech other hoster link (as defined in handleMulti method)
+ TEXT_ENCODING = False #: Set to True or encoding name if encoding value in http header is not correct
- directLink = directLink #@TODO: Remove in 0.4.10
+ LINK_PATTERN = None
- @classmethod
- def parseInfos(cls, urls): #@TODO: Built-in in 0.4.10 core, then remove from plugins
- for url in urls:
- url = replace_patterns(url, cls.FILE_URL_REPLACEMENTS if hasattr(cls, "FILE_URL_REPLACEMENTS") else cls.URL_REPLACEMENTS) #@TODO: Remove FILE_URL_REPLACEMENTS check in 0.4.10
- yield cls.getInfo(url)
+ directLink = getFileURL #@TODO: Remove in 0.4.10
@classmethod
- def apiInfo(cls, url="", get={}, post={}):
- url = unquote(url)
- return {'name' : (urlparse(url).path.split('/')[-1]
- or urlparse(url).query.split('=', 1)[::-1][0].split('&', 1)[0]
- or _("Unknown")),
+ def apiInfo(cls, url):
+ url = urllib.unquote(url)
+ url_p = urlparse.urlparse(url)
+ return {'name' : (url_p.path.split('/')[-1]
+ or url_p.query.split('=', 1)[::-1][0].split('&', 1)[0]
+ or url_p.netloc.split('.', 1)[0]),
'size' : 0,
'status': 3 if url else 8,
'url' : url}
@@ -276,7 +348,7 @@ class SimpleHoster(Hoster):
@classmethod
def getInfo(cls, url="", html=""):
info = cls.apiInfo(url)
- online = False
+ online = True if info['status'] is 2 else False
try:
info['pattern'] = re.match(cls.__pattern__, url).groupdict() #: pattern groups will be saved here
@@ -284,7 +356,7 @@ class SimpleHoster(Hoster):
except Exception:
info['pattern'] = {}
- if not html:
+ if not html and not online:
if not url:
info['error'] = "missing url"
info['status'] = 1
@@ -305,21 +377,18 @@ class SimpleHoster(Hoster):
elif e.code is 503:
info['status'] = 6
+ except Exception:
+ pass
+
if html:
if hasattr(cls, "OFFLINE_PATTERN") and re.search(cls.OFFLINE_PATTERN, html):
info['status'] = 1
- elif hasattr(cls, "FILE_OFFLINE_PATTERN") and re.search(cls.FILE_OFFLINE_PATTERN, html): #@TODO: Remove in 0.4.10
- info['status'] = 1
-
elif hasattr(cls, "TEMP_OFFLINE_PATTERN") and re.search(cls.TEMP_OFFLINE_PATTERN, html):
info['status'] = 6
else:
- for pattern in ("FILE_INFO_PATTERN", "INFO_PATTERN",
- "FILE_NAME_PATTERN", "NAME_PATTERN",
- "FILE_SIZE_PATTERN", "SIZE_PATTERN",
- "HASHSUM_PATTERN"): #@TODO: Remove old patterns starting with "FILE_" in 0.4.10
+ for pattern in ("INFO_PATTERN", "NAME_PATTERN", "SIZE_PATTERN", "HASHSUM_PATTERN"):
try:
attr = getattr(cls, pattern)
pdict = re.search(attr, html).groupdict()
@@ -333,19 +402,16 @@ class SimpleHoster(Hoster):
else:
online = True
- if not info['pattern']:
- info.pop('pattern', None)
-
if online:
info['status'] = 2
if 'N' in info['pattern']:
- info['name'] = replace_patterns(unquote(info['pattern']['N'].strip()),
- cls.FILE_NAME_REPLACEMENTS if hasattr(cls, "FILE_NAME_REPLACEMENTS") else cls.NAME_REPLACEMENTS) #@TODO: Remove FILE_NAME_REPLACEMENTS check in 0.4.10
+ info['name'] = replace_patterns(urllib.unquote(info['pattern']['N'].strip()),
+ cls.NAME_REPLACEMENTS)
if 'S' in info['pattern']:
size = replace_patterns(info['pattern']['S'] + info['pattern']['U'] if 'U' in info['pattern'] else info['pattern']['S'],
- cls.FILE_SIZE_REPLACEMENTS if hasattr(cls, "FILE_SIZE_REPLACEMENTS") else cls.SIZE_REPLACEMENTS) #@TODO: Remove FILE_SIZE_REPLACEMENTS check in 0.4.10
+ cls.SIZE_REPLACEMENTS)
info['size'] = parseFileSize(size)
elif isinstance(info['size'], basestring):
@@ -356,9 +422,49 @@ class SimpleHoster(Hoster):
hashtype = info['pattern']['T'] if 'T' in info['pattern'] else "hash"
info[hashtype] = info['pattern']['H']
+ if not info['pattern']:
+ info.pop('pattern', None)
+
return info
+ #@TODO: Move to Hoster in 0.4.10
+ def _log(self, level, args):
+ log = getattr(self.core.log, level)
+ msg = " | ".join((fs_encode(a) if isinstance(a, unicode) else #@NOTE: `fs_encode` -> `encode` in 0.4.10
+ decode(a) if isinstance(a, str) else
+ str(a)).strip() for a in args if a)
+ log("%(plugin)s[%(id)s]: %(msg)s" % {'plugin': self.__name__,
+ 'id' : self.pyfile.id,
+ 'msg' : msg or _(level.upper() + " MARK")})
+
+
+ #@TODO: Move to Hoster in 0.4.10
+ def logDebug(self, *args):
+ if self.core.debug:
+ return self._log("debug", args)
+
+
+ #@TODO: Move to Hoster in 0.4.10
+ def logInfo(self, *args):
+ return self._log("info", args)
+
+
+ #@TODO: Move to Hoster in 0.4.10
+ def logWarning(self, *args):
+ return self._log("warning", args)
+
+
+ #@TODO: Move to Hoster in 0.4.10
+ def logError(self, *args):
+ return self._log("error", args)
+
+
+ #@TODO: Move to Hoster in 0.4.10
+ def logCritical(self, *args):
+ return self._log("critical", args)
+
+
def setup(self):
self.resumeDownload = self.multiDL = self.premium
@@ -367,9 +473,16 @@ class SimpleHoster(Hoster):
self.pyfile.error = "" #@TODO: Remove in 0.4.10
self.info = {}
- self.link = "" #@TODO: Move to hoster class in 0.4.10
- self.directDL = False #@TODO: Move to hoster class in 0.4.10
- self.multihost = False #@TODO: Move to hoster class in 0.4.10
+ self.html = ""
+ self.link = "" #@TODO: Move to Hoster in 0.4.10
+ self.directDL = False #@TODO: Move to Hoster in 0.4.10
+ self.multihost = False #@TODO: Move to Hoster in 0.4.10
+
+ if not self.getConfig('use_premium', True):
+ self.retryFree()
+
+ if self.LOGIN_PREMIUM and not self.premium:
+ self.fail(_("Required premium account not found"))
if self.LOGIN_ACCOUNT and not self.account:
self.fail(_("Required account not found"))
@@ -379,6 +492,13 @@ class SimpleHoster(Hoster):
if isinstance(self.COOKIES, list):
set_cookies(self.req.cj, self.COOKIES)
+ if self.LINK_PATTERN:
+ if not hasattr(self, 'LINK_FREE_PATTERN'):
+ self.LINK_FREE_PATTERN = self.LINK_PATTERN
+
+ if not hasattr(self, 'LINK_PREMIUM_PATTERN'):
+ self.LINK_PREMIUM_PATTERN = self.LINK_PATTERN
+
if (self.MULTI_HOSTER
and (self.__pattern__ != self.core.pluginManager.hosterPlugins[self.__name__]['pattern']
or re.match(self.__pattern__, self.pyfile.url) is None)):
@@ -390,80 +510,116 @@ class SimpleHoster(Hoster):
else:
self.directDL = self.DIRECT_LINK
- self.pyfile.url = replace_patterns(self.pyfile.url,
- self.FILE_URL_REPLACEMENTS if hasattr(self, "FILE_URL_REPLACEMENTS") else self.URL_REPLACEMENTS) #@TODO: Remove FILE_URL_REPLACEMENTS check in 0.4.10
+ self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS)
def preload(self):
- self.html = self.load(self.pyfile.url, cookies=bool(self.COOKIES), decode=not self.TEXT_ENCODING)
+ self.html = self.load(self.pyfile.url, cookies=bool(self.COOKIES), ref=False, decode=not self.TEXT_ENCODING)
if isinstance(self.TEXT_ENCODING, basestring):
self.html = unicode(self.html, self.TEXT_ENCODING)
def process(self, pyfile):
- self.prepare()
- self.checkInfo()
+ try:
+ self.prepare()
+ self.checkInfo()
- if self.directDL:
- self.logDebug("Looking for direct download link...")
- self.handleDirect(pyfile)
+ if self.directDL:
+ self.logDebug("Looking for direct download link...")
+ self.handleDirect(pyfile)
- if self.multihost and not self.link and not self.lastDownload:
- self.logDebug("Looking for leeched download link...")
- self.handleMulti(pyfile)
+ if self.multihost and not self.link and not self.lastDownload:
+ self.logDebug("Looking for leeched download link...")
+ self.handleMulti(pyfile)
+
+ if not self.link and not self.lastDownload:
+ self.MULTI_HOSTER = False
+ self.retry(1, reason=_("Multi hoster fails"))
if not self.link and not self.lastDownload:
- self.MULTI_HOSTER = False
- self.retry(1, reason="Multi hoster fails")
+ self.preload()
+ self.checkInfo()
+
+ if self.premium and (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.logDebug("Handled as premium download")
+ self.handlePremium(pyfile)
+
+ elif not self.LOGIN_ACCOUNT or (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.logDebug("Handled as free download")
+ self.handleFree(pyfile)
+
+ self.download(self.link, ref=False, disposition=self.DISPOSITION)
+ self.checkFile()
+
+ except Fail, e: #@TODO: Move to PluginThread in 0.4.10
+ err = str(e) #@TODO: Recheck in 0.4.10
+
+ if err == _("No captcha result obtained in appropiate time by any of the plugins."): #@TODO: Fix in 0.4.10
+ self.checkFile()
+
+ elif self.getConfig('fallback', True) and self.premium:
+ self.logWarning(_("Premium download failed"), e)
+ self.retryFree()
+
+ else:
+ raise Fail(err)
- if not self.link and not self.lastDownload:
- self.preload()
- self.checkInfo()
- if self.premium and (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
- self.logDebug("Handled as premium download")
- self.handlePremium(pyfile)
+ def download(self, url, *args, **kwargs):
+ if not url or not isinstance(url, basestring):
+ return
- elif not self.LOGIN_ACCOUNT or (not self.CHECK_TRAFFIC or self.checkTrafficLeft()):
- self.logDebug("Handled as free download")
- self.handleFree(pyfile)
+ self.correctCaptcha()
- self.downloadLink(self.link)
- self.checkFile()
+ url = html_unescape(url.decode('unicode-escape').strip()) #@TODO: Move to Hoster in 0.4.10
+ if not urlparse.urlparse(url).scheme:
+ url_p = urlparse.urlparse(self.pyfile.url)
+ baseurl = "%s://%s" % (url_p.scheme, url_p.netloc)
+ url = urlparse.urljoin(baseurl, url)
- def downloadLink(self, link):
- if link and isinstance(link, basestring):
- self.correctCaptcha()
- self.download(link, disposition=False) #@TODO: Set `disposition=True` in 0.4.10
+ return super(SimpleHoster, self).download(url, *args, **kwargs)
def checkFile(self):
+ lastDownload = fs_encode(self.lastDownload)
+
if self.cTask and not self.lastDownload:
self.invalidCaptcha()
self.retry(10, reason=_("Wrong captcha"))
- elif not self.lastDownload or not exists(fs_encode(self.lastDownload)):
+ elif not self.lastDownload or not os.path.exists(lastDownload):
self.lastDownload = ""
- self.fail(self.pyfile.error or _("No file downloaded"))
+ self.error(self.pyfile.error or _("No file downloaded"))
else:
- rules = {'empty file': re.compile(r'\A\Z'),
- 'html file' : re.compile(r'\A\s*<!DOCTYPE html'),
- 'html error': re.compile(r'\A\s*(<.+>)?\d{3}(\Z|\s+)')}
+ #@TODO: Move to Hoster in 0.4.10
+ if os.stat(lastDownload).st_size < 1 or self.checkDownload({'Empty file': re.compile(r'\A((.|)(\2|\s)*)\Z')}):
+ self.error(_("Empty file"))
- if hasattr(self, 'ERROR_PATTERN'):
- rules['error'] = re.compile(self.ERROR_PATTERN)
+ self.logDebug("Checking last downloaded file with built-in rules")
+ for r, p in self.FILE_ERRORS:
+ errmsg = self.checkDownload({r: re.compile(p)})
+ if errmsg is not None:
+ errmsg = errmsg.strip().capitalize()
+
+ try:
+ errmsg += " | " + self.lastCheck.group(1).strip()
+ except Exception:
+ pass
- check = self.checkDownload(rules)
- if check: #@TODO: Move to hoster in 0.4.10
- errmsg = check.strip().capitalize()
- if self.lastCheck:
- errmsg += " | " + self.lastCheck.group(0).strip()
+ self.logWarning("Check result: " + errmsg, "Waiting 1 minute and retry")
+ self.wantReconnect = True
+ self.retry(wait_time=60, reason=errmsg)
+ else:
+ if self.CHECK_FILE:
+ self.logDebug("Checking last downloaded file with custom rules")
+ with open(lastDownload, "rb") as f:
+ self.html = f.read(50000) #@TODO: Recheck in 0.4.10
+ self.checkErrors()
- self.lastDownload = ""
- self.retry(10, 60, errmsg)
+ self.logDebug("No file errors found")
def checkErrors(self):
@@ -471,30 +627,111 @@ class SimpleHoster(Hoster):
self.logWarning(_("No html code to check"))
return
- if hasattr(self, 'PREMIUM_ONLY_PATTERN') and self.premium and re.search(self.PREMIUM_ONLY_PATTERN, self.html):
- self.fail(_("Link require a premium account to be handled"))
+ if hasattr(self, 'IP_BLOCKED_PATTERN') and re.search(self.IP_BLOCKED_PATTERN, self.html):
+ self.fail(_("Connection from your current IP address is not allowed"))
+
+ elif not self.premium:
+ if hasattr(self, 'PREMIUM_ONLY_PATTERN') and re.search(self.PREMIUM_ONLY_PATTERN, self.html):
+ self.fail(_("File can be downloaded by premium users only"))
+
+ elif hasattr(self, 'SIZE_LIMIT_PATTERN') and re.search(self.SIZE_LIMIT_PATTERN, self.html):
+ self.fail(_("File too large for free download"))
+
+ elif hasattr(self, 'DL_LIMIT_PATTERN') and re.search(self.DL_LIMIT_PATTERN, self.html):
+ m = re.search(self.DL_LIMIT_PATTERN, self.html)
+ try:
+ errmsg = m.group(1).strip()
+ except Exception:
+ errmsg = m.group(0).strip()
+
+ self.info['error'] = re.sub(r'<.*?>', " ", errmsg)
+ self.logWarning(self.info['error'])
+
+ if re.search('da(il)?y|today', errmsg, re.I):
+ wait_time = secondsToMidnight(gmt=2)
+ else:
+ wait_time = sum(int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1, "": 1}[u.lower()] for v, u in
+ re.findall(r'(\d+)\s*(hr|hour|min|sec|)', errmsg, re.I))
- elif hasattr(self, 'ERROR_PATTERN'):
+ self.wantReconnect = wait_time > 300
+ self.retry(1, wait_time, _("Download limit exceeded"))
+
+ if hasattr(self, 'HAPPY_HOUR_PATTERN') and re.search(self.HAPPY_HOUR_PATTERN, self.html):
+ self.multiDL = True
+
+ if hasattr(self, 'ERROR_PATTERN'):
m = re.search(self.ERROR_PATTERN, self.html)
if m:
- errmsg = self.info['error'] = m.group(1)
- self.error(errmsg)
+ try:
+ errmsg = m.group(1).strip()
+ except Exception:
+ errmsg = m.group(0).strip()
+
+ self.info['error'] = re.sub(r'<.*?>', " ", errmsg)
+ self.logWarning(self.info['error'])
+
+ if re.search('limit|wait|slot', errmsg, re.I):
+ if re.search("da(il)?y|today", errmsg):
+ wait_time = secondsToMidnight(gmt=2)
+ else:
+ wait_time = sum(int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1, "": 1}[u.lower()] for v, u in
+ re.findall(r'(\d+)\s*(hr|hour|min|sec|)', errmsg, re.I))
+
+ self.wantReconnect = wait_time > 300
+ self.retry(1, wait_time, _("Download limit exceeded"))
+
+ elif re.search('country|ip|region|nation', errmsg, re.I):
+ self.fail(_("Connection from your current IP address is not allowed"))
+
+ elif re.search('captcha|code', errmsg, re.I):
+ self.invalidCaptcha()
+ self.retry(10, reason=_("Wrong captcha"))
+
+ elif re.search('countdown|expired', errmsg, re.I):
+ self.retry(10, 60, _("Link expired"))
+
+ elif re.search('maintenance|maintainance|temp', errmsg, re.I):
+ self.tempOffline()
+
+ elif re.search('up to|size', errmsg, re.I):
+ self.fail(_("File too large for free download"))
+
+ elif re.search('offline|delet|remov|not? (found|(longer)? available)', errmsg, re.I):
+ self.offline()
+
+ elif re.search('filename', errmsg, re.I):
+ url_p = urlparse.urlparse(self.pyfile.url)
+ self.pyfile.url = "%s://%s/%s" % (url_p.scheme, url_p.netloc, url_p.path.strip('/').split('/')[0])
+ self.retry(1, reason=_("Wrong url"))
+
+ elif re.search('premium', errmsg, re.I):
+ self.fail(_("File can be downloaded by premium users only"))
+
+ else:
+ self.wantReconnect = True
+ self.retry(wait_time=60, reason=errmsg)
elif hasattr(self, 'WAIT_PATTERN'):
m = re.search(self.WAIT_PATTERN, self.html)
if m:
- wait_time = sum([int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1}[u.lower()] for v, u in
- re.findall(r'(\d+)\s*(hr|hour|min|sec)', m.group(0), re.I)])
+ try:
+ waitmsg = m.group(1).strip()
+ except Exception:
+ waitmsg = m.group(0).strip()
+
+ wait_time = sum(int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1, "": 1}[u.lower()] for v, u in
+ re.findall(r'(\d+)\s*(hr|hour|min|sec|)', waitmsg, re.I))
self.wait(wait_time, wait_time > 300)
- return
self.info.pop('error', None)
def checkStatus(self, getinfo=True):
if not self.info or getinfo:
- self.logDebug("File info (BEFORE): %s" % self.info)
+ self.logDebug("Update file info...")
+ self.logDebug("Previous file info: %s" % self.info)
self.info.update(self.getInfo(self.pyfile.url, self.html))
+ self.logDebug("Current file info: %s" % self.info)
try:
status = self.info['status']
@@ -506,22 +743,22 @@ class SimpleHoster(Hoster):
self.tempOffline()
elif status is 8:
- self.fail()
+ self.fail(self.info['error'] if 'error' in self.info else _("Failed"))
finally:
- self.logDebug("File status: %s" % statusMap[status],
- "File info: %s" % self.info)
+ self.logDebug("File status: %s" % statusMap[status])
def checkNameSize(self, getinfo=True):
if not self.info or getinfo:
- self.logDebug("File info (BEFORE): %s" % self.info)
+ self.logDebug("Update file info...")
+ self.logDebug("Previous file info: %s" % self.info)
self.info.update(self.getInfo(self.pyfile.url, self.html))
- self.logDebug("File info (AFTER): %s" % self.info)
+ self.logDebug("Current file info: %s" % self.info)
try:
- url = self.info['url']
- name = self.info['name']
+ url = self.info['url'].strip()
+ name = self.info['name'].strip()
if name and name != url:
self.pyfile.name = name
@@ -537,7 +774,7 @@ class SimpleHoster(Hoster):
pass
self.logDebug("File name: %s" % self.pyfile.name,
- "File size: %s" % self.pyfile.size if self.pyfile.size > 0 else "Unknown")
+ "File size: %s byte" % self.pyfile.size if self.pyfile.size > 0 else "File size: Unknown")
def checkInfo(self):
@@ -562,7 +799,6 @@ class SimpleHoster(Hoster):
if link:
self.logInfo(_("Direct download link detected"))
-
self.link = link
else:
self.logDebug("Direct download link not found")
@@ -576,16 +812,12 @@ class SimpleHoster(Hoster):
if not hasattr(self, 'LINK_FREE_PATTERN'):
self.logError(_("Free download not implemented"))
- try:
- m = re.search(self.LINK_FREE_PATTERN, self.html)
- if m is None:
- self.error(_("Free download link not found"))
-
+ m = re.search(self.LINK_FREE_PATTERN, self.html)
+ if m is None:
+ self.error(_("Free download link not found"))
+ else:
self.link = m.group(1)
- except Exception, e:
- self.fail(e)
-
def handlePremium(self, pyfile):
if not hasattr(self, 'LINK_PREMIUM_PATTERN'):
@@ -593,16 +825,12 @@ class SimpleHoster(Hoster):
self.logDebug("Handled as free download")
self.handleFree(pyfile)
- try:
- m = re.search(self.LINK_PREMIUM_PATTERN, self.html)
- if m is None:
- self.error(_("Premium download link not found"))
-
+ m = re.search(self.LINK_PREMIUM_PATTERN, self.html)
+ if m is None:
+ self.error(_("Premium download link not found"))
+ else:
self.link = m.group(1)
- except Exception, e:
- self.fail(e)
-
def longWait(self, wait_time=None, max_tries=3):
if wait_time and isinstance(wait_time, (int, long, float)):
@@ -614,8 +842,7 @@ class SimpleHoster(Hoster):
self.logInfo(_("Download limit reached, reconnect or wait %s") % time_str)
- self.setWait(wait_time, True)
- self.wait()
+ self.wait(wait_time, True)
self.retry(max_tries=max_tries, reason=_("Download limit reached"))
@@ -640,6 +867,26 @@ class SimpleHoster(Hoster):
#@TODO: Remove in 0.4.10
+ def getConfig(self, option, default=''):
+ """getConfig with default value - sublass may not implements all config options"""
+ try:
+ return self.getConf(option)
+
+ except KeyError:
+ return default
+
+
+ def retryFree(self):
+ if not self.premium:
+ return
+ self.premium = False
+ self.account = None
+ self.req = self.core.requestFactory.getRequest(self.__name__)
+ self.retries = -1
+ raise Retry(_("Fallback to free download"))
+
+
+ #@TODO: Remove in 0.4.10
def wait(self, seconds=0, reconnect=None):
return _wait(self, seconds, reconnect)
diff --git a/module/plugins/internal/SolveMedia.py b/module/plugins/internal/SolveMedia.py
new file mode 100644
index 000000000..d600ef03c
--- /dev/null
+++ b/module/plugins/internal/SolveMedia.py
@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from module.plugins.internal.Plugin import Fail
+from module.plugins.internal.Captcha import Captcha
+
+
+class SolveMedia(Captcha):
+ __name__ = "SolveMedia"
+ __type__ = "captcha"
+ __version__ = "0.14"
+
+ __description__ = """SolveMedia captcha service plugin"""
+ __license__ = "GPLv3"
+ __authors__ = [("pyLoad Team", "admin@pyload.org")]
+
+
+ KEY_PATTERN = r'api\.solvemedia\.com/papi/challenge\.(?:no)?script\?k=(.+?)["\']'
+
+
+ def detect_key(self, html=None):
+ html = html or self.retrieve_html()
+
+ m = re.search(self.KEY_PATTERN, html)
+ if m:
+ self.key = m.group(1).strip()
+ self.logDebug("Key: %s" % self.key)
+ return self.key
+ else:
+ self.logWarning("Key pattern not found")
+ return None
+
+
+ def challenge(self, key=None, html=None):
+ key = key or self.retrieve_key(html)
+
+ html = self.plugin.req.load("http://api.solvemedia.com/papi/challenge.noscript",
+ get={'k': key})
+
+ for i in xrange(1, 11):
+ try:
+ magic = re.search(r'name="magic" value="(.+?)"', html).group(1)
+
+ except AttributeError:
+ self.logWarning("Magic pattern not found")
+ magic = None
+
+ try:
+ challenge = re.search(r'<input type=hidden name="adcopy_challenge" id="adcopy_challenge" value="(.+?)">',
+ html).group(1)
+
+ except AttributeError:
+ self.fail(_("SolveMedia challenge pattern not found"))
+
+ else:
+ self.logDebug("Challenge: %s" % challenge)
+
+ try:
+ result = self.result("http://api.solvemedia.com/papi/media", challenge)
+
+ except Fail, e:
+ self.logWarning(e)
+ self.plugin.invalidCaptcha()
+ result = None
+
+ html = self.plugin.req.load("http://api.solvemedia.com/papi/verify.noscript",
+ post={'adcopy_response' : result,
+ 'k' : key,
+ 'l' : "en",
+ 't' : "img",
+ 's' : "standard",
+ 'magic' : magic,
+ 'adcopy_challenge': challenge,
+ 'ref' : self.plugin.pyfile.url})
+ try:
+ redirect = re.search(r'URL=(.+?)">', html).group(1)
+
+ except AttributeError:
+ self.fail(_("SolveMedia verify pattern not found"))
+
+ else:
+ if "error" in html:
+ self.logWarning("Captcha code was invalid")
+ self.logDebug("Retry #%d" % i)
+ html = self.plugin.req.load(redirect)
+ else:
+ break
+
+ else:
+ self.fail(_("SolveMedia max retries exceeded"))
+
+ return result, challenge
+
+
+ def result(self, server, challenge):
+ result = self.plugin.decryptCaptcha(server,
+ get={'c': challenge},
+ cookies=True,
+ imgtype="gif")
+
+ self.logDebug("Result: %s" % result)
+
+ return result
diff --git a/module/plugins/internal/UnRar.py b/module/plugins/internal/UnRar.py
index 572fe95b9..5b9f2e1c3 100644
--- a/module/plugins/internal/UnRar.py
+++ b/module/plugins/internal/UnRar.py
@@ -2,105 +2,108 @@
import os
import re
+import subprocess
from glob import glob
-from os.path import basename, dirname, join
from string import digits
-from subprocess import Popen, PIPE
from module.plugins.internal.Extractor import Extractor, ArchiveError, CRCError, PasswordError
-from module.utils import save_join, decode
+from module.utils import fs_decode, fs_encode, save_join
def renice(pid, value):
- if os.name != "nt" and value:
+ if value and os.name != "nt":
try:
- Popen(["renice", str(value), str(pid)], stdout=PIPE, stderr=PIPE, bufsize=-1)
- except:
- print "Renice failed"
+ subprocess.Popen(["renice", str(value), str(pid)], stdout=subprocess.PIPE, stderr=subprocess.PIPE, bufsize=-1)
+
+ except Exception:
+ pass
class UnRar(Extractor):
__name__ = "UnRar"
- __version__ = "1.01"
+ __version__ = "1.20"
__description__ = """Rar extractor plugin"""
__license__ = "GPLv3"
- __authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
+ __authors__ = [("RaNaN" , "RaNaN@pyload.org" ),
+ ("Walter Purcaro", "vuolter@gmail.com"),
+ ("Immenz" , "immenz@gmx.net" )]
CMD = "unrar"
+ VERSION = ""
+ EXTENSIONS = [".rar"]
- EXTENSIONS = ["rar", "zip", "cab", "arj", "lzh", "tar", "gz", "bz2", "ace", "uue", "jar", "iso", "7z", "xz", "z"]
+ re_multipart = re.compile(r'\.(part|r)(\d+)(?:\.rar)?(\.rev|\.bad)?',re.I)
- #@NOTE: there are some more uncovered rar formats
- re_rarpart = re.compile(r'(.*)\.part(\d+)\.rar$', re.I)
- re_rarfile = re.compile(r'.*\.(rar|r\d+)$', re.I)
+ re_filefixed = re.compile(r'Building (.+)')
+ re_filelist = re.compile(r'^(.)(\s*[\w\.\-]+)\s+(\d+\s+)+(?:\d+\%\s+)?[\d\-]{8}\s+[\d\:]{5}', re.M|re.I)
- re_filelist = re.compile(r'(.+)\s+(\d+)\s+(\d+)\s+|(.+)\s+(\d+)\s+\d\d-\d\d-\d\d\s+\d\d:\d\d\s+(.+)')
re_wrongpwd = re.compile(r'password', re.I)
- re_wrongcrc = re.compile(r'encrypted|damaged|CRC failed|checksum error', re.I)
+ re_wrongcrc = re.compile(r'encrypted|damaged|CRC failed|checksum error|corrupt', re.I)
+
+ re_version = re.compile(r'(?:UN)?RAR\s(\d+\.\d+)', re.I)
@classmethod
- def checkDeps(cls):
+ def isUsable(cls):
if os.name == "nt":
- cls.CMD = join(pypath, "UnRAR.exe")
- p = Popen([cls.CMD], stdout=PIPE, stderr=PIPE)
- p.communicate()
- else:
try:
- p = Popen([cls.CMD], stdout=PIPE, stderr=PIPE)
- p.communicate()
+ cls.CMD = os.path.join(pypath, "RAR.exe")
+ p = subprocess.Popen([cls.CMD], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+ cls.__name__ = "RAR"
+ cls.REPAIR = True
except OSError:
- # fallback to rar
- cls.CMD = "rar"
- p = Popen([cls.CMD], stdout=PIPE, stderr=PIPE)
- p.communicate()
+ cls.CMD = os.path.join(pypath, "UnRAR.exe")
+ p = subprocess.Popen([cls.CMD], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+ else:
+ try:
+ p = subprocess.Popen(["rar"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+ cls.__name__ = "RAR"
+ cls.REPAIR = True
+
+ except OSError: #: fallback to unrar
+ p = subprocess.Popen([cls.CMD], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ out, err = p.communicate()
+
+ m = cls.re_version.search(out)
+ cls.VERSION = m.group(1) if m else '(version unknown)'
return True
@classmethod
- def isArchive(cls, file):
- f = basename(file).lower()
- return any(f.endswith('.%s' % ext) for ext in cls.EXTENSIONS)
+ def isMultipart(cls, filename):
+ return True if cls.re_multipart.search(filename) else False
- @classmethod
- def getTargets(cls, files_ids):
- targets = []
-
- for file, id in files_ids:
- if not cls.isArchive(file):
- continue
-
- m = cls.re_rarpart.findall(file)
- if m:
- # only add first parts
- if int(m[0][1]) == 1:
- targets.append((file, id))
- else:
- targets.append((file, id))
+ def verify(self, password):
+ p = self.call_cmd("t", "-v", fs_encode(self.filename), password=password)
+ self._progress(p)
+ err = p.stderr.read().strip()
- return targets
+ if self.re_wrongpwd.search(err):
+ raise PasswordError
+ if self.re_wrongcrc.search(err):
+ raise CRCError(err)
- def check(self, out="", err=""):
- if not out or not err:
- return
- if err.strip():
- if self.re_wrongpwd.search(err):
- raise PasswordError
+ def check(self, password):
+ p = self.call_cmd("l", "-v", fs_encode(self.filename), password=password)
+ out, err = p.communicate()
- elif self.re_wrongcrc.search(err):
- raise CRCError
+ if self.re_wrongpwd.search(err):
+ raise PasswordError
- else: #: raise error if anything is on stderr
- raise ArchiveError(err.strip())
+ if self.re_wrongcrc.search(err):
+ raise CRCError(err)
# output only used to check if passworded files are present
for attr in self.re_filelist.findall(out):
@@ -108,114 +111,99 @@ class UnRar(Extractor):
raise PasswordError
- def verify(self):
- p = self.call_cmd("l", "-v", self.file, password=self.password)
-
- self.check(*p.communicate())
-
- if p and p.returncode:
- raise ArchiveError("Process terminated")
-
- if not self.list():
- raise ArchiveError("Empty archive")
-
-
- def isPassword(self, password):
- if isinstance(password, basestring):
- p = self.call_cmd("l", "-v", self.file, password=password)
- out, err = p.communicate()
-
- if not self.re_wrongpwd.search(err):
- return True
-
- return False
-
-
def repair(self):
- p = self.call_cmd("rc", self.file)
- out, err = p.communicate()
-
- if p.returncode or err.strip():
- p = self.call_cmd("r", self.file)
- out, err = p.communicate()
-
- if p.returncode or err.strip():
- return False
- else:
- self.file = join(dirname(self.file), re.search(r'(fixed|rebuild)\.%s' % basename(self.file), out).group(0))
+ p = self.call_cmd("rc", fs_encode(self.filename))
+ # communicate and retrieve stderr
+ self._progress(p)
+ err = p.stderr.read().strip()
+ if err or p.returncode:
+ return False
return True
- def extract(self, progress=lambda x: None):
- self.verify()
-
- progress(0)
-
- command = "x" if self.fullpath else "e"
-
- p = self.call_cmd(command, self.file, self.out, password=self.password)
-
- renice(p.pid, self.renice)
-
- progressstring = ""
+ def _progress(self, process):
+ s = ""
while True:
- c = p.stdout.read(1)
+ c = process.stdout.read(1)
# quit loop on eof
if not c:
break
# reading a percentage sign -> set progress and restart
- if c is '%':
- progress(int(progressstring))
- progressstring = ""
+ if c == '%':
+ self.notifyProgress(int(s))
+ s = ""
# not reading a digit -> therefore restart
elif c not in digits:
- progressstring = ""
+ s = ""
# add digit to progressstring
else:
- progressstring += c
+ s += c
+
+
+ def extract(self, password=None):
+ command = "x" if self.fullpath else "e"
- progress(100)
+ p = self.call_cmd(command, fs_encode(self.filename), self.out, password=password)
- self.files = self.list()
+ renice(p.pid, self.renice)
- # retrieve stderr
- self.check(err=p.stderr.read())
+ # communicate and retrieve stderr
+ self._progress(p)
+ err = p.stderr.read().strip()
+
+ if err:
+ if self.re_wrongpwd.search(err):
+ raise PasswordError
+
+ elif self.re_wrongcrc.search(err):
+ raise CRCError(err)
+
+ else: #: raise error if anything is on stderr
+ raise ArchiveError(err)
if p.returncode:
- raise ArchiveError("Process terminated")
+ raise ArchiveError(_("Process return code: %d") % p.returncode)
+
+ self.files = self.list(password)
def getDeleteFiles(self):
- if ".part" in basename(self.file):
- return glob(re.sub("(?<=\.part)([01]+)", "*", self.file, re.I))
+ dir, name = os.path.split(self.filename)
+
+ # actually extracted file
+ files = [self.filename]
- # get files which matches .r* and filter unsuited files out
- parts = glob(re.sub(r"(?<=\.r)ar$", "*", self.file, re.I))
+ # eventually Multipart Files
+ files.extend(save_join(dir, os.path.basename(file)) for file in filter(self.isMultipart, os.listdir(dir))
+ if re.sub(self.re_multipart,".rar",name) == re.sub(self.re_multipart,".rar",file))
- return filter(lambda x: self.re_rarfile.match(x), parts)
+ return files
- def list(self):
+ def list(self, password=None):
command = "vb" if self.fullpath else "lb"
- p = self.call_cmd(command, "-v", self.file, password=self.password)
+ p = self.call_cmd(command, "-v", fs_encode(self.filename), password=password)
out, err = p.communicate()
- if err.strip():
- self.m.logError(err)
- if "Cannot open" in err:
- return list()
+ if "Cannot open" in err:
+ raise ArchiveError(_("Cannot open file"))
- if p.returncode:
- self.m.logError("Process terminated")
- return list()
+ if err.strip(): #: only log error at this point
+ self.manager.logError(err.strip())
result = set()
-
- for f in decode(out).splitlines():
- f = f.strip()
- result.add(save_join(self.out, f))
+ if not self.fullpath and self.VERSION.startswith('5'):
+ # NOTE: Unrar 5 always list full path
+ for f in fs_decode(out).splitlines():
+ f = save_join(self.out, os.path.basename(f.strip()))
+ if os.path.isfile(f):
+ result.add(save_join(self.out, os.path.basename(f)))
+ else:
+ for f in fs_decode(out).splitlines():
+ f = f.strip()
+ result.add(save_join(self.out, f))
return list(result)
@@ -228,11 +216,11 @@ class UnRar(Extractor):
args.append("-o+")
else:
args.append("-o-")
- if self.delete:
+ if self.delete != 'No':
args.append("-or")
for word in self.excludefiles:
- args.append("-x%s" % word.strip())
+ args.append("-x'%s'" % word.strip())
# assume yes on all queries
args.append("-y")
@@ -248,6 +236,8 @@ class UnRar(Extractor):
# NOTE: return codes are not reliable, some kind of threading, cleanup whatever issue
call = [self.CMD, command] + args + list(xargs)
- self.m.logDebug(" ".join(call))
- return Popen(call, stdout=PIPE, stderr=PIPE)
+ self.manager.logDebug(" ".join(call))
+
+ p = subprocess.Popen(call, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ return p
diff --git a/module/plugins/internal/UnZip.py b/module/plugins/internal/UnZip.py
index 5ec56cbdf..4c18a0e35 100644
--- a/module/plugins/internal/UnZip.py
+++ b/module/plugins/internal/UnZip.py
@@ -2,85 +2,71 @@
from __future__ import with_statement
+import os
import sys
import zipfile
from module.plugins.internal.Extractor import Extractor, ArchiveError, CRCError, PasswordError
+from module.utils import fs_encode
class UnZip(Extractor):
__name__ = "UnZip"
- __version__ = "1.01"
+ __version__ = "1.12"
__description__ = """Zip extractor plugin"""
__license__ = "GPLv3"
__authors__ = [("Walter Purcaro", "vuolter@gmail.com")]
- EXTENSIONS = ["zip", "zip64"]
+ VERSION ="(python %s.%s.%s)" % (sys.version_info[0], sys.version_info[1], sys.version_info[2])
+ EXTENSIONS = [".zip", ".zip64"]
@classmethod
- def checkDeps(cls):
+ def isUsable(cls):
return sys.version_info[:2] >= (2, 6)
- @classmethod
- def isArchive(cls, file):
- return zipfile.is_zipfile(file)
+ def list(self, password=None):
+ with zipfile.ZipFile(fs_encode(self.filename), 'r', allowZip64=True) as z:
+ z.setpassword(password)
+ return z.namelist()
- def verify(self):
- try:
- with zipfile.ZipFile(self.file, 'r', allowZip64=True) as z:
- z.setpassword(self.password)
- badcrc = z.testzip()
-
- except (BadZipfile, LargeZipFile), e:
- raise ArchiveError(e)
+ def check(self, password):
+ pass
- except RuntimeError, e:
- if 'encrypted' in e:
- raise PasswordError
- else:
- raise ArchiveError(e)
- else:
- if badcrc:
- raise CRCError
+ def verify(self):
+ with zipfile.ZipFile(fs_encode(self.filename), 'r', allowZip64=True) as z:
+ badfile = z.testzip()
- if not self.list():
- raise ArchiveError("Empty archive")
+ if badfile:
+ raise CRCError(badfile)
+ else:
+ raise PasswordError
- def list(self):
+ def extract(self, password=None):
try:
- with zipfile.ZipFile(self.file, 'r', allowZip64=True) as z:
- z.setpassword(self.password)
- return z.namelist()
- except Exception:
- return list()
+ with zipfile.ZipFile(fs_encode(self.filename), 'r', allowZip64=True) as z:
+ z.setpassword(password)
+ badfile = z.testzip()
- def extract(self, progress=lambda x: None):
- try:
- with zipfile.ZipFile(self.file, 'r', allowZip64=True) as z:
- progress(0)
- z.extractall(self.out, pwd=self.password)
- progress(100)
+ if badfile:
+ raise CRCError(badfile)
+ else:
+ z.extractall(self.out)
- except (BadZipfile, LargeZipFile), e:
+ except (zipfile.BadZipfile, zipfile.LargeZipFile), e:
raise ArchiveError(e)
except RuntimeError, e:
- if e is "Bad password for file":
+ if "encrypted" in e:
raise PasswordError
else:
raise ArchiveError(e)
-
- finally:
- self.files = self.list()
-
-
- def getDeleteFiles(self):
- return [self.file]
+ else:
+ self.files = z.namelist()
diff --git a/module/plugins/internal/XFSAccount.py b/module/plugins/internal/XFSAccount.py
index c350729ac..f230cedf3 100644
--- a/module/plugins/internal/XFSAccount.py
+++ b/module/plugins/internal/XFSAccount.py
@@ -1,29 +1,29 @@
# -*- coding: utf-8 -*-
import re
+import time
+import urlparse
-from time import gmtime, mktime, strptime
-from urlparse import urljoin
-
-from module.plugins.Account import Account
+from module.plugins.internal.Account import Account
from module.plugins.internal.SimpleHoster import parseHtmlForm, set_cookies
class XFSAccount(Account):
__name__ = "XFSAccount"
__type__ = "account"
- __version__ = "0.35"
+ __version__ = "0.38"
__description__ = """XFileSharing account plugin"""
__license__ = "GPLv3"
- __authors__ = [("zoidberg", "zoidberg@mujmail.cz"),
- ("Walter Purcaro", "vuolter@gmail.com")]
+ __authors__ = [("zoidberg" , "zoidberg@mujmail.cz"),
+ ("Walter Purcaro", "vuolter@gmail.com" )]
HOSTER_DOMAIN = None
HOSTER_URL = None
+ LOGIN_URL = None
- COOKIES = [(HOSTER_DOMAIN, "lang", "english")]
+ COOKIES = True
PREMIUM_PATTERN = r'\(Premium only\)'
@@ -46,9 +46,15 @@ class XFSAccount(Account):
def init(self):
if not self.HOSTER_DOMAIN:
self.logError(_("Missing HOSTER_DOMAIN"))
+ self.COOKIES = False
+
+ else:
+ if not self.HOSTER_URL:
+ self.HOSTER_URL = "http://www.%s/" % self.HOSTER_DOMAIN
- if not self.HOSTER_URL:
- self.HOSTER_URL = "http://www.%s/" % (self.HOSTER_DOMAIN or "")
+ if isinstance(self.COOKIES, list):
+ self.COOKIES.insert((self.HOSTER_DOMAIN, "lang", "english"))
+ set_cookies(req.cj, self.COOKIES)
def loadAccountInfo(self, user, req):
@@ -57,6 +63,12 @@ class XFSAccount(Account):
leechtraffic = None
premium = None
+ if not self.HOSTER_URL: #@TODO: Remove in 0.4.10
+ return {'validuntil' : validuntil,
+ 'trafficleft' : trafficleft,
+ 'leechtraffic': leechtraffic,
+ 'premium' : premium}
+
html = req.load(self.HOSTER_URL, get={'op': "my_account"}, decode=True)
premium = True if re.search(self.PREMIUM_PATTERN, html) else False
@@ -67,7 +79,7 @@ class XFSAccount(Account):
self.logDebug("Expire date: " + expiredate)
try:
- validuntil = mktime(strptime(expiredate, "%d %B %Y"))
+ validuntil = time.mktime(time.strptime(expiredate, "%d %B %Y"))
except Exception, e:
self.logError(e)
@@ -75,7 +87,7 @@ class XFSAccount(Account):
else:
self.logDebug("Valid until: %s" % validuntil)
- if validuntil > mktime(gmtime()):
+ if validuntil > time.mktime(time.gmtime()):
premium = True
trafficleft = -1
else:
@@ -136,25 +148,34 @@ class XFSAccount(Account):
else:
self.logDebug("LEECH_TRAFFIC_PATTERN not found")
- return {'validuntil': validuntil, 'trafficleft': trafficleft, 'leechtraffic': leechtraffic, 'premium': premium}
+ return {'validuntil' : validuntil,
+ 'trafficleft' : trafficleft,
+ 'leechtraffic': leechtraffic,
+ 'premium' : premium}
def login(self, user, data, req):
- if isinstance(self.COOKIES, list):
- set_cookies(req.cj, self.COOKIES)
+ if not self.HOSTER_URL: #@TODO: Remove in 0.4.10
+ raise Exception(_("Missing HOSTER_DOMAIN"))
- url = urljoin(self.HOSTER_URL, "login.html")
- html = req.load(url, decode=True)
+ if not self.LOGIN_URL:
+ self.LOGIN_URL = urlparse.urljoin(self.HOSTER_URL, "login.html")
+ html = req.load(self.LOGIN_URL, decode=True)
action, inputs = parseHtmlForm('name="FL"', html)
if not inputs:
- inputs = {'op': "login",
+ inputs = {'op' : "login",
'redirect': self.HOSTER_URL}
- inputs.update({'login': user,
+ inputs.update({'login' : user,
'password': data['password']})
- html = req.load(self.HOSTER_URL, post=inputs, decode=True)
+ if action:
+ url = urlparse.urljoin("http://", action)
+ else:
+ url = self.HOSTER_URL
+
+ html = req.load(url, post=inputs, decode=True)
if re.search(self.LOGIN_FAIL_PATTERN, html):
self.wrongPassword()
diff --git a/module/plugins/internal/XFSCrypter.py b/module/plugins/internal/XFSCrypter.py
index 3cb837aac..8b333b45c 100644
--- a/module/plugins/internal/XFSCrypter.py
+++ b/module/plugins/internal/XFSCrypter.py
@@ -6,7 +6,7 @@ from module.plugins.internal.SimpleCrypter import SimpleCrypter, create_getInfo
class XFSCrypter(SimpleCrypter):
__name__ = "XFSCrypter"
__type__ = "crypter"
- __version__ = "0.05"
+ __version__ = "0.09"
__pattern__ = r'^unmatchable$'
@@ -19,10 +19,27 @@ class XFSCrypter(SimpleCrypter):
URL_REPLACEMENTS = [(r'&?per_page=\d+', ""), (r'[?/&]+$', ""), (r'(.+/[^?]+)$', r'\1?'), (r'$', r'&per_page=10000')]
- COOKIES = [(HOSTER_DOMAIN, "lang", "english")]
-
- LINK_PATTERN = r'<(?:td|TD).*?>\s*<a href="(.+?)".*?>.+?(?:</a>)?\s*</(?:td|TD)>'
- NAME_PATTERN = r'<[tT]itle>.*?\: (?P<N>.+) folder</[tT]itle>'
+ NAME_PATTERN = r'<[Tt]itle>.*?\: (?P<N>.+) folder</[Tt]itle>'
+ LINK_PATTERN = r'<(?:td|TD).*?>\s*(?:<.+>\s*)?<a href="(.+?)".*?>.+?(?:</a>)?\s*(?:<.+>\s*)?</(?:td|TD)>'
OFFLINE_PATTERN = r'>\s*\w+ (Not Found|file (was|has been) removed)'
TEMP_OFFLINE_PATTERN = r'>\s*\w+ server (is in )?(maintenance|maintainance)'
+
+
+ def prepare(self):
+ if not self.HOSTER_DOMAIN:
+ if self.account:
+ account = self.account
+ else:
+ account_name = (self.__name__ + ".py").replace("Folder.py", "").replace(".py", "")
+ account = self.pyfile.m.core.accountManager.getAccountPlugin(account_name)
+
+ if account and hasattr(account, "HOSTER_DOMAIN") and account.HOSTER_DOMAIN:
+ self.HOSTER_DOMAIN = account.HOSTER_DOMAIN
+ else:
+ self.fail(_("Missing HOSTER_DOMAIN"))
+
+ if isinstance(self.COOKIES, list):
+ self.COOKIES.insert((self.HOSTER_DOMAIN, "lang", "english"))
+
+ return super(XFSCrypter, self).prepare()
diff --git a/module/plugins/internal/XFSHoster.py b/module/plugins/internal/XFSHoster.py
index b32f5978f..0591f1baf 100644
--- a/module/plugins/internal/XFSHoster.py
+++ b/module/plugins/internal/XFSHoster.py
@@ -1,13 +1,12 @@
# -*- coding: utf-8 -*-
+import pycurl
+import random
import re
+import urlparse
-from random import random
-from time import sleep
-
-from pycurl import FOLLOWLOCATION, LOW_SPEED_TIME
-
-from module.plugins.internal.CaptchaService import ReCaptcha, SolveMedia
+from module.plugins.internal.ReCaptcha import ReCaptcha
+from module.plugins.internal.SolveMedia import SolveMedia
from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo, secondsToMidnight
from module.utils import html_unescape
@@ -15,36 +14,33 @@ from module.utils import html_unescape
class XFSHoster(SimpleHoster):
__name__ = "XFSHoster"
__type__ = "hoster"
- __version__ = "0.35"
+ __version__ = "0.53"
__pattern__ = r'^unmatchable$'
__description__ = """XFileSharing hoster plugin"""
__license__ = "GPLv3"
- __authors__ = [("zoidberg", "zoidberg@mujmail.cz"),
- ("stickell", "l.stickell@yahoo.it"),
- ("Walter Purcaro", "vuolter@gmail.com")]
+ __authors__ = [("zoidberg" , "zoidberg@mujmail.cz"),
+ ("stickell" , "l.stickell@yahoo.it"),
+ ("Walter Purcaro", "vuolter@gmail.com" )]
HOSTER_DOMAIN = None
- TEXT_ENCODING = False
- COOKIES = [(HOSTER_DOMAIN, "lang", "english")]
- DIRECT_LINK = None
- MULTI_HOSTER = True #@NOTE: Should be default to False for safe, but I'm lazy...
+ MULTI_HOSTER = True #@NOTE: Should be default to False for safe, but I'm lazy...
NAME_PATTERN = r'(Filename[ ]*:[ ]*</b>(</td><td nowrap>)?|name="fname"[ ]+value="|<[\w^_]+ class="(file)?name">)\s*(?P<N>.+?)(\s*<|")'
SIZE_PATTERN = r'(Size[ ]*:[ ]*</b>(</td><td>)?|File:.*>|</font>\s*\(|<[\w^_]+ class="size">)\s*(?P<S>[\d.,]+)\s*(?P<U>[\w^_]+)'
- OFFLINE_PATTERN = r'>\s*\w+ (Not Found|file (was|has been) removed)'
+ OFFLINE_PATTERN = r'>\s*\w+ (Not Found|file (was|has been) removed|no longer available)'
TEMP_OFFLINE_PATTERN = r'>\s*\w+ server (is in )?(maintenance|maintainance)'
- WAIT_PATTERN = r'<span id="countdown_str">.*?>(\d+)</span>|id="countdown" value=".*?(\d+).*?"'
+ WAIT_PATTERN = r'<span id="countdown_str".*>(\d+)</span>|id="countdown" value=".*?(\d+).*?"'
PREMIUM_ONLY_PATTERN = r'>This file is available for Premium Users only'
+ HAPPY_HOUR_PATTERN = r'>[Hh]appy hour'
ERROR_PATTERN = r'(?:class=["\']err["\'].*?>|<[Cc]enter><b>|>Error</td>|>\(ERROR:)(?:\s*<.+?>\s*)*(.+?)(?:["\']|<|\))'
LINK_LEECH_PATTERN = r'<h2>Download Link</h2>\s*<textarea[^>]*>([^<]+)'
- LINK_PATTERN = None #: final download url pattern
CAPTCHA_PATTERN = r'(https?://[^"\']+?/captchas?/[^"\']+)'
CAPTCHA_BLOCK_PATTERN = r'>Enter code.*?<div.*?>(.+?)</div>'
@@ -56,48 +52,39 @@ class XFSHoster(SimpleHoster):
def setup(self):
- self.chunkLimit = 1
+ self.chunkLimit = -1 if self.premium else 1
self.resumeDownload = self.multiDL = self.premium
def prepare(self):
""" Initialize important variables """
if not self.HOSTER_DOMAIN:
- self.fail(_("Missing HOSTER_DOMAIN"))
+ if self.account:
+ account = self.account
+ else:
+ account = self.pyfile.m.core.accountManager.getAccountPlugin(self.__name__)
+
+ if account and hasattr(account, "HOSTER_DOMAIN") and account.HOSTER_DOMAIN:
+ self.HOSTER_DOMAIN = account.HOSTER_DOMAIN
+ else:
+ self.fail(_("Missing HOSTER_DOMAIN"))
+
+ if isinstance(self.COOKIES, list):
+ self.COOKIES.insert((self.HOSTER_DOMAIN, "lang", "english"))
if not self.LINK_PATTERN:
- pattern = r'(https?://(www\.)?([^/]*?%s|\d+\.\d+\.\d+\.\d+)(\:\d+)?(/d/|(/files)?/\d+/\w+/).+?)["\'<]'
+ pattern = r'(?:file: "(.+?)"|(https?://(?:www\.)?([^/]*?%s|\d+\.\d+\.\d+\.\d+)(\:\d+)?(/d/|(/files)?/\d+/\w+/).+?)["\'<])'
self.LINK_PATTERN = pattern % self.HOSTER_DOMAIN.replace('.', '\.')
- self.captcha = None
- self.errmsg = None
-
super(XFSHoster, self).prepare()
if self.DIRECT_LINK is None:
- self.directDL = bool(self.premium)
-
-
- def downloadLink(self, link):
- if link and isinstance(link, basestring):
- if self.captcha:
- self.correctCaptcha()
-
- self.download(link, ref=True, cookies=True, disposition=False) #@TODO: Set `disposition=True` in 0.4.10
-
- elif self.errmsg:
- if 'captcha' in self.errmsg:
- self.fail(_("No valid captcha code entered"))
- else:
- self.fail(self.errmsg)
-
- else:
- self.fail(_("Download link not found"))
+ self.directDL = self.premium
def handleFree(self, pyfile):
for i in xrange(1, 6):
- self.logDebug("Getting download link: #%d" % i)
+ self.logDebug("Getting download link #%d" % i)
self.checkErrors()
@@ -107,11 +94,11 @@ class XFSHoster(SimpleHoster):
data = self.getPostParameters()
- self.req.http.c.setopt(FOLLOWLOCATION, 0)
+ self.req.http.c.setopt(pycurl.FOLLOWLOCATION, 0)
- self.html = self.load(pyfile.url, post=data, ref=True, decode=True)
+ self.html = self.load(pyfile.url, post=data, decode=True)
- self.req.http.c.setopt(FOLLOWLOCATION, 1)
+ self.req.http.c.setopt(pycurl.FOLLOWLOCATION, 1)
m = re.search(r'Location\s*:\s*(.+)', self.req.http.header, re.I)
if m and not "op=" in m.group(1):
@@ -124,9 +111,7 @@ class XFSHoster(SimpleHoster):
self.logError(data['op'] if 'op' in data else _("UNKNOWN"))
return ""
- self.errmsg = None
-
- self.link = m.group(1).strip() #@TODO: Remove .strip() in 0.4.10
+ self.link = m.group(1).strip() #@TODO: Remove `.strip()` in 0.4.10
def handlePremium(self, pyfile):
@@ -142,7 +127,7 @@ class XFSHoster(SimpleHoster):
action, inputs = self.parseHtmlForm()
- upload_id = "%012d" % int(random() * 10 ** 12)
+ upload_id = "%012d" % int(random.random() * 10 ** 12)
action += upload_id + "&js_on=1&utype=prem&upload_type=url"
inputs['tos'] = '1'
@@ -159,10 +144,7 @@ class XFSHoster(SimpleHoster):
action, inputs = self.parseHtmlForm('F1')
if not inputs:
- if self.errmsg:
- self.retry(reason=self.errmsg)
- else:
- self.error(_("TEXTAREA F1 not found"))
+ self.retry(reason=self.info['error'] if 'error' in self.info else _("TEXTAREA F1 not found"))
self.logDebug(inputs)
@@ -189,61 +171,6 @@ class XFSHoster(SimpleHoster):
if 'location' in header: #: Direct download link
self.link = header['location']
- else:
- self.fail(_("Download link not found"))
-
-
- def checkErrors(self):
- m = re.search(self.ERROR_PATTERN, self.html)
- if m is None:
- self.errmsg = None
- else:
- self.errmsg = m.group(1).strip()
-
- self.logWarning(re.sub(r"<.*?>", " ", self.errmsg))
-
- if 'wait' in self.errmsg:
- wait_time = sum([int(v) * {"hr": 3600, "hour": 3600, "min": 60, "sec": 1}[u.lower()] for v, u in
- re.findall(r'(\d+)\s*(hr|hour|min|sec)', self.errmsg, re.I)])
- self.wait(wait_time, True)
-
- elif 'country' in self.errmsg:
- self.fail(_("Downloads are disabled for your country"))
-
- elif 'captcha' in self.errmsg:
- self.invalidCaptcha()
-
- elif 'premium' in self.errmsg and 'require' in self.errmsg:
- self.fail(_("File can be downloaded by premium users only"))
-
- elif 'limit' in self.errmsg:
- if 'days' in self.errmsg:
- delay = secondsToMidnight(gmt=2)
- retries = 3
- else:
- delay = 1 * 60 * 60
- retries = 24
-
- self.wantReconnect = True
- self.retry(retries, delay, _("Download limit exceeded"))
-
- elif 'countdown' in self.errmsg or 'Expired' in self.errmsg:
- self.retry(reason=_("Link expired"))
-
- elif 'maintenance' in self.errmsg or 'maintainance' in self.errmsg:
- self.tempOffline()
-
- elif 'up to' in self.errmsg:
- self.fail(_("File too large for free download"))
-
- else:
- self.wantReconnect = True
- self.retry(wait_time=60, reason=self.errmsg)
-
- if self.errmsg:
- self.info['error'] = self.errmsg
- else:
- self.info.pop('error', None)
def getPostParameters(self):
@@ -255,10 +182,7 @@ class XFSHoster(SimpleHoster):
if not inputs:
action, inputs = self.parseHtmlForm('F1')
if not inputs:
- if self.errmsg:
- self.retry(reason=self.errmsg)
- else:
- self.error(_("TEXTAREA F1 not found"))
+ self.retry(reason=self.info['error'] if 'error' in self.info else _("TEXTAREA F1 not found"))
self.logDebug(inputs)
@@ -276,8 +200,7 @@ class XFSHoster(SimpleHoster):
wait_time = int(m.group(1))
self.setWait(wait_time, False)
- self.captcha = self.handleCaptcha(inputs)
-
+ self.handleCaptcha(inputs)
self.wait()
else:
inputs['referer'] = self.pyfile.url
@@ -297,39 +220,43 @@ class XFSHoster(SimpleHoster):
if m:
captcha_url = m.group(1)
inputs['code'] = self.decryptCaptcha(captcha_url)
- return 1
+ return
m = re.search(self.CAPTCHA_BLOCK_PATTERN, self.html, re.S)
if m:
captcha_div = m.group(1)
numerals = re.findall(r'<span.*?padding-left\s*:\s*(\d+).*?>(\d)</span>', html_unescape(captcha_div))
+
self.logDebug(captcha_div)
- inputs['code'] = "".join([a[1] for a in sorted(numerals, key=lambda num: int(num[0]))])
+
+ inputs['code'] = "".join(a[1] for a in sorted(numerals, key=lambda num: int(num[0])))
+
self.logDebug("Captcha code: %s" % inputs['code'], numerals)
- return 2
+ return
recaptcha = ReCaptcha(self)
try:
captcha_key = re.search(self.RECAPTCHA_PATTERN, self.html).group(1)
- except:
+
+ except Exception:
captcha_key = recaptcha.detect_key()
+
else:
self.logDebug("ReCaptcha key: %s" % captcha_key)
if captcha_key:
- inputs['recaptcha_challenge_field'], inputs['recaptcha_response_field'] = recaptcha.challenge(captcha_key)
- return 3
+ inputs['recaptcha_response_field'], inputs['recaptcha_challenge_field'] = recaptcha.challenge(captcha_key)
+ return
solvemedia = SolveMedia(self)
try:
captcha_key = re.search(self.SOLVEMEDIA_PATTERN, self.html).group(1)
- except:
+
+ except Exception:
captcha_key = solvemedia.detect_key()
+
else:
self.logDebug("SolveMedia key: %s" % captcha_key)
if captcha_key:
- inputs['adcopy_challenge'], inputs['adcopy_response'] = solvemedia.challenge(captcha_key)
- return 4
-
- return 0
+ inputs['adcopy_response'], inputs['adcopy_challenge'] = solvemedia.challenge(captcha_key)