summaryrefslogtreecommitdiffstats
path: root/pyload/plugins/internal
diff options
context:
space:
mode:
Diffstat (limited to 'pyload/plugins/internal')
-rw-r--r--pyload/plugins/internal/AbstractExtractor.py101
-rw-r--r--pyload/plugins/internal/CaptchaService.py96
-rw-r--r--pyload/plugins/internal/DeadCrypter.py19
-rw-r--r--pyload/plugins/internal/DeadHoster.py27
-rw-r--r--pyload/plugins/internal/MultiHoster.py192
-rw-r--r--pyload/plugins/internal/SimpleCrypter.py118
-rw-r--r--pyload/plugins/internal/SimpleHoster.py292
-rw-r--r--pyload/plugins/internal/UnRar.py212
-rw-r--r--pyload/plugins/internal/UnZip.py38
-rw-r--r--pyload/plugins/internal/XFSPAccount.py69
-rw-r--r--pyload/plugins/internal/__init__.py0
11 files changed, 1164 insertions, 0 deletions
diff --git a/pyload/plugins/internal/AbstractExtractor.py b/pyload/plugins/internal/AbstractExtractor.py
new file mode 100644
index 000000000..d1d1a09cb
--- /dev/null
+++ b/pyload/plugins/internal/AbstractExtractor.py
@@ -0,0 +1,101 @@
+# -*- coding: utf-8 -*-
+
+class ArchiveError(Exception):
+ pass
+
+
+class CRCError(Exception):
+ pass
+
+
+class WrongPassword(Exception):
+ pass
+
+
+class AbtractExtractor:
+ __name__ = "AbtractExtractor"
+ __version__ = "0.1"
+
+ __description__ = """Abtract extractor plugin"""
+ __author_name__ = "pyLoad Team"
+ __author_mail__ = "admin@pyload.org"
+
+
+ @staticmethod
+ def checkDeps():
+ """ Check if system statisfy dependencies
+ :return: boolean
+ """
+ return True
+
+ @staticmethod
+ def getTargets(files_ids):
+ """ Filter suited targets from list of filename id tuple list
+ :param files_ids: List of filepathes
+ :return: List of targets, id tuple list
+ """
+ raise NotImplementedError
+
+ def __init__(self, m, file, out, fullpath, overwrite, excludefiles, renice):
+ """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
+ self.out = out
+ self.fullpath = fullpath
+ self.overwrite = overwrite
+ self.excludefiles = excludefiles
+ self.renice = renice
+ self.files = [] #: Store extracted files here
+
+ def init(self):
+ """ Initialize additional data structures """
+ pass
+
+ def checkArchive(self):
+ """Check if password if needed. Raise ArchiveError if integrity is
+ questionable.
+
+ :return: boolean
+ :raises ArchiveError
+ """
+ return False
+
+ def checkPassword(self, password):
+ """ Check if the given password is/might be correct.
+ If it can not be decided at this point return true.
+
+ :param password:
+ :return: boolean
+ """
+ return True
+
+ def extract(self, progress, 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 WrongPassword
+ :raises CRCError
+ :raises ArchiveError
+ :return:
+ """
+ raise NotImplementedError
+
+ def getDeleteFiles(self):
+ """Return list of files to delete, do *not* delete them here.
+
+ :return: List with paths of files to delete
+ """
+ raise NotImplementedError
+
+ def getExtractedFiles(self):
+ """Populate self.files at some point while extracting"""
+ return self.files
diff --git a/pyload/plugins/internal/CaptchaService.py b/pyload/plugins/internal/CaptchaService.py
new file mode 100644
index 000000000..b247ba654
--- /dev/null
+++ b/pyload/plugins/internal/CaptchaService.py
@@ -0,0 +1,96 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from random import random
+
+
+class CaptchaService:
+ __name__ = "CaptchaService"
+ __version__ = "0.05"
+
+ __description__ = """Captcha service plugin"""
+ __author_name__ = "pyLoad Team"
+ __author_mail__ = "admin@pyload.org"
+
+
+ def __init__(self, plugin):
+ self.plugin = plugin
+
+
+class ReCaptcha:
+ RECAPTCHA_KEY_PATTERN = r"https?://(?:www\.)?google\.com/recaptcha/api/challenge\?k=(?P<key>\w+)"
+ RECAPTCHA_KEY_AJAX_PATTERN = r"Recaptcha\.create\s*\(\s*[\"'](?P<key>\w+)[\"']\s*,"
+
+ recaptcha_key = None
+
+
+ def __init__(self, plugin):
+ self.plugin = plugin
+
+ def detect_key(self, html):
+ m = re.search(self.RECAPTCHA_KEY_PATTERN, html)
+ if m is None:
+ m = re.search(self.RECAPTCHA_KEY_AJAX_PATTERN, html)
+ if m:
+ self.recaptcha_key = m.group('key')
+ return self.recaptcha_key
+ else:
+ return None
+
+ def challenge(self, key=None):
+ if key is None and self.recaptcha_key:
+ key = self.recaptcha_key
+ else:
+ raise TypeError("ReCaptcha key not found")
+
+ js = self.plugin.req.load("http://www.google.com/recaptcha/api/challenge", get={"k": key}, cookies=True)
+
+ try:
+ challenge = re.search("challenge : '(.*?)',", js).group(1)
+ server = re.search("server : '(.*?)',", js).group(1)
+ except:
+ self.plugin.fail("recaptcha error")
+ result = self.result(server, challenge)
+
+ return challenge, result
+
+ def result(self, server, challenge):
+ return self.plugin.decryptCaptcha("%simage" % server, get={"c": challenge},
+ cookies=True, forceUser=True, imgtype="jpg")
+
+
+class AdsCaptcha(CaptchaService):
+
+ def challenge(self, src):
+ js = self.plugin.req.load(src, cookies=True)
+
+ try:
+ challenge = re.search("challenge: '(.*?)',", js).group(1)
+ server = re.search("server: '(.*?)',", js).group(1)
+ except:
+ self.plugin.fail("adscaptcha error")
+ result = self.result(server, challenge)
+
+ return challenge, result
+
+ def result(self, server, challenge):
+ return self.plugin.decryptCaptcha("%sChallenge.aspx" % server, get={"cid": challenge, "dummy": random()},
+ cookies=True, imgtype="jpg")
+
+
+class SolveMedia(CaptchaService):
+
+ def challenge(self, src):
+ html = self.plugin.req.load("http://api.solvemedia.com/papi/challenge.noscript?k=%s" % src, cookies=True)
+ try:
+ challenge = re.search(r'<input type=hidden name="adcopy_challenge" id="adcopy_challenge" value="([^"]+)">',
+ html).group(1)
+ except:
+ self.plugin.fail("solvemedia error")
+ result = self.result(challenge)
+
+ return challenge, result
+
+ def result(self, challenge):
+ return self.plugin.decryptCaptcha("http://api.solvemedia.com/papi/media?c=%s" % challenge, imgtype="gif")
diff --git a/pyload/plugins/internal/DeadCrypter.py b/pyload/plugins/internal/DeadCrypter.py
new file mode 100644
index 000000000..ea9c414cb
--- /dev/null
+++ b/pyload/plugins/internal/DeadCrypter.py
@@ -0,0 +1,19 @@
+# -*- coding: utf-8 -*-
+
+from pyload.plugins.Crypter import Crypter as _Crypter
+
+
+class DeadCrypter(_Crypter):
+ __name__ = "DeadCrypter"
+ __type__ = "crypter"
+ __version__ = "0.01"
+
+ __pattern__ = None
+
+ __description__ = """Crypter is no longer available"""
+ __author_name__ = "stickell"
+ __author_mail__ = "l.stickell@yahoo.it"
+
+
+ def setup(self):
+ self.fail("Crypter is no longer available")
diff --git a/pyload/plugins/internal/DeadHoster.py b/pyload/plugins/internal/DeadHoster.py
new file mode 100644
index 000000000..0b2398020
--- /dev/null
+++ b/pyload/plugins/internal/DeadHoster.py
@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+
+from pyload.plugins.Hoster import Hoster as _Hoster
+
+
+def create_getInfo(plugin):
+
+ def getInfo(urls):
+ yield [('#N/A: ' + url, 0, 1, url) for url in urls]
+
+ return getInfo
+
+
+class DeadHoster(_Hoster):
+ __name__ = "DeadHoster"
+ __type__ = "hoster"
+ __version__ = "0.11"
+
+ __pattern__ = None
+
+ __description__ = """Hoster is no longer available"""
+ __author_name__ = "zoidberg"
+ __author_mail__ = "zoidberg@mujmail.cz"
+
+
+ def setup(self):
+ self.fail("Hoster is no longer available")
diff --git a/pyload/plugins/internal/MultiHoster.py b/pyload/plugins/internal/MultiHoster.py
new file mode 100644
index 000000000..d99ae6ff9
--- /dev/null
+++ b/pyload/plugins/internal/MultiHoster.py
@@ -0,0 +1,192 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from pyload.plugins.Hook import Hook
+from pyload.utils import remove_chars
+
+
+class MultiHoster(Hook):
+ __name__ = "MultiHoster"
+ __type__ = "hook"
+ __version__ = "0.20"
+
+ __description__ = """Generic MultiHoster plugin"""
+ __author_name__ = "pyLoad Team"
+ __author_mail__ = "admin@pyload.org"
+
+ replacements = [("2shared.com", "twoshared.com"), ("4shared.com", "fourshared.com"), ("cloudnator.com", "shragle.com"),
+ ("ifile.it", "filecloud.io"), ("easy-share.com", "crocko.com"), ("freakshare.net", "freakshare.com"),
+ ("hellshare.com", "hellshare.cz"), ("share-rapid.cz", "sharerapid.com"), ("sharerapid.cz", "sharerapid.com"),
+ ("ul.to", "uploaded.to"), ("uploaded.net", "uploaded.to"), ("1fichier.com", "onefichier.com")]
+ ignored = []
+ interval = 24 * 60 * 60 #: reload hosters daily
+
+
+ def setup(self):
+ self.hosters = []
+ self.supported = []
+ self.new_supported = []
+
+ def getConfig(self, option, default=''):
+ """getConfig with default value - subclass may not implements all config options"""
+ try:
+ # Fixed loop due to getConf deprecation in 0.4.10
+ return super(MultiHoster, self).getConfig(option)
+ except KeyError:
+ return default
+
+ def getHosterCached(self):
+ if not self.hosters:
+ try:
+ hosterSet = self.toHosterSet(self.getHoster()) - set(self.ignored)
+ except Exception, e:
+ self.logError("%s" % str(e))
+ return []
+
+ try:
+ configMode = self.getConfig('hosterListMode', 'all')
+ if configMode in ("listed", "unlisted"):
+ configSet = self.toHosterSet(self.getConfig('hosterList', '').replace('|', ',').replace(';', ',').split(','))
+
+ if configMode == "listed":
+ hosterSet &= configSet
+ else:
+ hosterSet -= configSet
+
+ except Exception, e:
+ self.logError("%s" % str(e))
+
+ self.hosters = list(hosterSet)
+
+ return self.hosters
+
+ def toHosterSet(self, hosters):
+ hosters = set((str(x).strip().lower() for x in hosters))
+
+ for rep in self.replacements:
+ if rep[0] in hosters:
+ hosters.remove(rep[0])
+ hosters.add(rep[1])
+
+ hosters.discard('')
+ return hosters
+
+ def getHoster(self):
+ """Load list of supported hoster
+
+ :return: List of domain names
+ """
+ raise NotImplementedError
+
+ def coreReady(self):
+ if self.cb:
+ self.core.scheduler.removeJob(self.cb)
+
+ self.setConfig("activated", True) #: config not in sync after plugin reload
+
+ cfg_interval = self.getConfig("interval", None) #: reload interval in hours
+ if cfg_interval is not None:
+ self.interval = cfg_interval * 60 * 60
+
+ if self.interval:
+ self._periodical()
+ else:
+ self.periodical()
+
+ def initPeriodical(self):
+ pass
+
+ def periodical(self):
+ """reload hoster list periodically"""
+ self.logInfo("Reloading supported hoster list")
+
+ old_supported = self.supported
+ self.supported, self.new_supported, self.hosters = [], [], []
+
+ self.overridePlugins()
+
+ old_supported = [hoster for hoster in old_supported if hoster not in self.supported]
+ if old_supported:
+ self.logDebug("UNLOAD: %s" % ", ".join(old_supported))
+ for hoster in old_supported:
+ self.unloadHoster(hoster)
+
+ def overridePlugins(self):
+ pluginMap = {}
+ for name in self.core.pluginManager.hosterPlugins.keys():
+ pluginMap[name.lower()] = name
+
+ accountList = [name.lower() for name, data in self.core.accountManager.accounts.items() if data]
+ excludedList = []
+
+ for hoster in self.getHosterCached():
+ name = remove_chars(hoster.lower(), "-.")
+
+ if name in accountList:
+ excludedList.append(hoster)
+ else:
+ if name in pluginMap:
+ self.supported.append(pluginMap[name])
+ else:
+ self.new_supported.append(hoster)
+
+ if not self.supported and not self.new_supported:
+ self.logError(_("No Hoster loaded"))
+ return
+
+ module = self.core.pluginManager.getPlugin(self.__name__)
+ klass = getattr(module, self.__name__)
+
+ # inject plugin plugin
+ self.logDebug("Overwritten Hosters: %s" % ", ".join(sorted(self.supported)))
+ for hoster in self.supported:
+ dict = self.core.pluginManager.hosterPlugins[hoster]
+ dict['new_module'] = module
+ dict['new_name'] = self.__name__
+
+ if excludedList:
+ self.logInfo("The following hosters were not overwritten - account exists: %s" % ", ".join(sorted(excludedList)))
+
+ if self.new_supported:
+ self.logDebug("New Hosters: %s" % ", ".join(sorted(self.new_supported)))
+
+ # create new regexp
+ regexp = r".*(%s).*" % "|".join([x.replace(".", "\\.") for x in self.new_supported])
+ if hasattr(klass, "__pattern__") and isinstance(klass.__pattern__, basestring) and '://' in klass.__pattern__:
+ regexp = r"%s|%s" % (klass.__pattern__, regexp)
+
+ self.logDebug("Regexp: %s" % regexp)
+
+ dict = self.core.pluginManager.hosterPlugins[self.__name__]
+ dict['pattern'] = regexp
+ dict['re'] = re.compile(regexp)
+
+ def unloadHoster(self, hoster):
+ dict = self.core.pluginManager.hosterPlugins[hoster]
+ if "module" in dict:
+ del dict['module']
+
+ if "new_module" in dict:
+ del dict['new_module']
+ del dict['new_name']
+
+ def unload(self):
+ """Remove override for all hosters. Scheduler job is removed by hookmanager"""
+ for hoster in self.supported:
+ self.unloadHoster(hoster)
+
+ # reset pattern
+ klass = getattr(self.core.pluginManager.getPlugin(self.__name__), self.__name__)
+ dict = self.core.pluginManager.hosterPlugins[self.__name__]
+ dict['pattern'] = getattr(klass, "__pattern__", r'^unmatchable$')
+ dict['re'] = re.compile(dict['pattern'])
+
+ def downloadFailed(self, pyfile):
+ """remove plugin override if download fails but not if file is offline/temp.offline"""
+ if pyfile.hasStatus("failed") and self.getConfig("unloadFailing", True):
+ hdict = self.core.pluginManager.hosterPlugins[pyfile.pluginname]
+ if "new_name" in hdict and hdict['new_name'] == self.__name__:
+ self.logDebug("Unload MultiHoster", pyfile.pluginname, hdict)
+ self.unloadHoster(pyfile.pluginname)
+ pyfile.setStatus("queued")
diff --git a/pyload/plugins/internal/SimpleCrypter.py b/pyload/plugins/internal/SimpleCrypter.py
new file mode 100644
index 000000000..6e639c946
--- /dev/null
+++ b/pyload/plugins/internal/SimpleCrypter.py
@@ -0,0 +1,118 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from pyload.plugins.Crypter import Crypter
+from pyload.plugins.internal.SimpleHoster import PluginParseError, replace_patterns, set_cookies
+from pyload.utils import html_unescape
+
+
+class SimpleCrypter(Crypter):
+ __name__ = "SimpleCrypter"
+ __type__ = "crypter"
+ __version__ = "0.10"
+
+ __pattern__ = None
+
+ __description__ = """Simple decrypter plugin"""
+ __author_name__ = ("stickell", "zoidberg", "Walter Purcaro")
+ __author_mail__ = ("l.stickell@yahoo.it", "zoidberg@mujmail.cz", "vuolter@gmail.com")
+
+ """
+ Following patterns should be defined by each crypter:
+
+ LINK_PATTERN: group(1) must be a download link or a regex to catch more links
+ example: LINK_PATTERN = r'<div class="link"><a href="(http://speedload.org/\w+)'
+
+ TITLE_PATTERN: (optional) The group defined by 'title' should be the title
+ example: TITLE_PATTERN = r'<title>Files of: (?P<title>[^<]+) folder</title>'
+
+ OFFLINE_PATTERN: (optional) Checks if the file is yet available online
+ example: OFFLINE_PATTERN = r'File (deleted|not found)'
+
+ TEMP_OFFLINE_PATTERN: (optional) Checks if the file is temporarily offline
+ example: TEMP_OFFLINE_PATTERN = r'Server maintainance'
+
+
+ If it's impossible to extract the links using the LINK_PATTERN only you can override the getLinks method.
+
+ If the links are disposed on multiple pages you need to define a pattern:
+
+ PAGES_PATTERN: The group defined by 'pages' must be the total number of pages
+ example: PAGES_PATTERN = r'Pages: (?P<pages>\d+)'
+
+ and a function:
+
+ loadPage(self, page_n):
+ return the html of the page number 'page_n'
+ """
+
+ URL_REPLACEMENTS = []
+
+ SH_COOKIES = True # or False or list of tuples [(domain, name, value)]
+
+
+ def setup(self):
+ if isinstance(self.SH_COOKIES, list):
+ set_cookies(self.req.cj, self.SH_COOKIES)
+
+ def decrypt(self, pyfile):
+ pyfile.url = replace_patterns(pyfile.url, self.URL_REPLACEMENTS)
+
+ self.html = self.load(pyfile.url, decode=True)
+
+ self.checkOnline()
+
+ package_name, folder_name = self.getPackageNameAndFolder()
+
+ self.package_links = self.getLinks()
+
+ if hasattr(self, 'PAGES_PATTERN') and hasattr(self, 'loadPage'):
+ self.handleMultiPages()
+
+ self.logDebug('Package has %d links' % len(self.package_links))
+
+ if self.package_links:
+ self.packages = [(package_name, self.package_links, folder_name)]
+ else:
+ self.fail('Could not extract any links')
+
+ def getLinks(self):
+ """
+ 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)
+
+ def checkOnline(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 getPackageNameAndFolder(self):
+ if hasattr(self, 'TITLE_PATTERN'):
+ m = re.search(self.TITLE_PATTERN, self.html)
+ if m:
+ name = folder = html_unescape(m.group('title').strip())
+ self.logDebug("Found name [%s] and folder [%s] in package info" % (name, folder))
+ return name, folder
+
+ name = self.pyfile.package().name
+ folder = self.pyfile.package().folder
+ self.logDebug("Package info not found, defaulting to pyfile name [%s] and folder [%s]" % (name, folder))
+ return name, folder
+
+ def handleMultiPages(self):
+ pages = re.search(self.PAGES_PATTERN, self.html)
+ if pages:
+ pages = int(pages.group('pages'))
+ else:
+ pages = 1
+
+ for p in xrange(2, pages + 1):
+ self.html = self.loadPage(p)
+ self.package_links += self.getLinks()
+
+ def parseError(self, msg):
+ raise PluginParseError(msg)
diff --git a/pyload/plugins/internal/SimpleHoster.py b/pyload/plugins/internal/SimpleHoster.py
new file mode 100644
index 000000000..ca320732f
--- /dev/null
+++ b/pyload/plugins/internal/SimpleHoster.py
@@ -0,0 +1,292 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from time import time
+from urlparse import urlparse
+
+from pyload.network.CookieJar import CookieJar
+from pyload.network.RequestFactory import getURL
+from pyload.plugins.Hoster import Hoster
+from pyload.utils import fixup, html_unescape, parseFileSize
+
+
+def replace_patterns(string, ruleslist):
+ for r in ruleslist:
+ rf, rt = r
+ string = re.sub(rf, rt, string)
+ #self.logDebug(rf, rt, string)
+ return string
+
+
+def set_cookies(cj, cookies):
+ for cookie in cookies:
+ if isinstance(cookie, tuple) and len(cookie) == 3:
+ domain, name, value = cookie
+ cj.setCookie(domain, name, value)
+
+
+def parseHtmlTagAttrValue(attr_name, tag):
+ m = re.search(r"%s\s*=\s*([\"']?)((?<=\")[^\"]+|(?<=')[^']+|[^>\s\"'][^>\s]*)\1" % attr_name, tag, re.I)
+ return m.group(2) if m else None
+
+
+def parseHtmlForm(attr_str, html, input_names=None):
+ for form in re.finditer(r"(?P<tag><form[^>]*%s[^>]*>)(?P<content>.*?)</?(form|body|html)[^>]*>" % attr_str,
+ html, re.S | re.I):
+ inputs = {}
+ action = parseHtmlTagAttrValue("action", form.group('tag'))
+ for inputtag in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('content'), re.S | re.I):
+ name = parseHtmlTagAttrValue("name", inputtag.group(1))
+ if name:
+ value = parseHtmlTagAttrValue("value", inputtag.group(1))
+ if not value:
+ inputs[name] = inputtag.group(3) or ''
+ else:
+ inputs[name] = value
+
+ if isinstance(input_names, dict):
+ # check input attributes
+ for key, val in input_names.items():
+ if key in inputs:
+ if isinstance(val, basestring) and inputs[key] == val:
+ continue
+ elif isinstance(val, tuple) and inputs[key] in val:
+ continue
+ elif hasattr(val, "search") and re.match(val, inputs[key]):
+ continue
+ break # attibute value does not match
+ else:
+ break # attibute name does not match
+ else:
+ return action, inputs # passed attribute check
+ else:
+ # no attribute check
+ return action, inputs
+
+ return {}, None # no matching form found
+
+
+def parseFileInfo(self, url='', html=''):
+ info = {"name": url, "size": 0, "status": 3}
+
+ if hasattr(self, "pyfile"):
+ url = self.pyfile.url
+
+ if hasattr(self, "req") and self.req.http.code == '404':
+ info['status'] = 1
+ else:
+ if not html and hasattr(self, "html"):
+ html = self.html
+ if isinstance(self.SH_BROKEN_ENCODING, (str, unicode)):
+ html = unicode(html, self.SH_BROKEN_ENCODING)
+ if hasattr(self, "html"):
+ self.html = html
+
+ if hasattr(self, "OFFLINE_PATTERN") and re.search(self.OFFLINE_PATTERN, html):
+ info['status'] = 1
+ elif hasattr(self, "FILE_OFFLINE_PATTERN") and re.search(self.FILE_OFFLINE_PATTERN, html): #@TODO: Remove in 0.4.10
+ info['status'] = 1
+ elif hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, html):
+ info['status'] = 6
+ else:
+ online = False
+ try:
+ info.update(re.match(self.__pattern__, url).groupdict())
+ except:
+ pass
+
+ for pattern in ("FILE_INFO_PATTERN", "FILE_NAME_PATTERN", "FILE_SIZE_PATTERN"):
+ try:
+ info.update(re.search(getattr(self, pattern), html).groupdict())
+ online = True
+ except AttributeError:
+ continue
+
+ if online:
+ # File online, return name and size
+ info['status'] = 2
+ if 'N' in info:
+ info['name'] = replace_patterns(info['N'], self.FILE_NAME_REPLACEMENTS)
+ if 'S' in info:
+ size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'],
+ self.FILE_SIZE_REPLACEMENTS)
+ info['size'] = parseFileSize(size)
+ elif isinstance(info['size'], (str, unicode)):
+ if 'units' in info:
+ info['size'] += info['units']
+ info['size'] = parseFileSize(info['size'])
+
+ if hasattr(self, "file_info"):
+ self.file_info = info
+
+ return info['name'], info['size'], info['status'], url
+
+
+def create_getInfo(plugin):
+
+ def getInfo(urls):
+ for url in urls:
+ cj = CookieJar(plugin.__name__)
+ if isinstance(plugin.SH_COOKIES, list):
+ set_cookies(cj, plugin.SH_COOKIES)
+ file_info = parseFileInfo(plugin, url, getURL(replace_patterns(url, plugin.FILE_URL_REPLACEMENTS),
+ decode=not plugin.SH_BROKEN_ENCODING, cookies=cj))
+ yield file_info
+
+ return getInfo
+
+
+def timestamp():
+ return int(time() * 1000)
+
+
+class PluginParseError(Exception):
+
+ def __init__(self, msg):
+ Exception.__init__(self)
+ self.value = 'Parse error (%s) - plugin may be out of date' % msg
+
+ def __str__(self):
+ return repr(self.value)
+
+
+class SimpleHoster(Hoster):
+ __name__ = "SimpleHoster"
+ __type__ = "hoster"
+ __version__ = "0.35"
+
+ __pattern__ = None
+
+ __description__ = """Simple hoster plugin"""
+ __author_name__ = ("zoidberg", "stickell")
+ __author_mail__ = ("zoidberg@mujmail.cz", "l.stickell@yahoo.it")
+
+ """
+ Following patterns should be defined by each hoster:
+
+ FILE_INFO_PATTERN: Name and Size of the file
+ example: FILE_INFO_PATTERN = r'(?P<N>file_name) (?P<S>file_size) (?P<U>size_unit)'
+ or
+ FILE_NAME_PATTERN: Name that will be set for the file
+ example: FILE_NAME_PATTERN = r'(?P<N>file_name)'
+ FILE_SIZE_PATTERN: Size that will be checked for the file
+ example: FILE_SIZE_PATTERN = r'(?P<S>file_size) (?P<U>size_unit)'
+
+ OFFLINE_PATTERN: Checks if the file is yet available online
+ example: OFFLINE_PATTERN = r'File (deleted|not found)'
+
+ TEMP_OFFLINE_PATTERN: Checks if the file is temporarily offline
+ example: TEMP_OFFLINE_PATTERN = r'Server maintainance'
+
+ PREMIUM_ONLY_PATTERN: (optional) Checks if the file can be downloaded only with a premium account
+ example: PREMIUM_ONLY_PATTERN = r'Premium account required'
+ """
+
+ FILE_NAME_REPLACEMENTS = [("&#?\w+;", fixup)]
+ FILE_SIZE_REPLACEMENTS = []
+ FILE_URL_REPLACEMENTS = []
+
+ SH_BROKEN_ENCODING = False # Set to True or encoding name if encoding in http header is not correct
+ SH_COOKIES = True # or False or list of tuples [(domain, name, value)]
+ SH_CHECK_TRAFFIC = False # True = force check traffic left for a premium account
+
+
+ def init(self):
+ self.file_info = {}
+
+ def setup(self):
+ self.resumeDownload = self.multiDL = self.premium
+ if isinstance(self.SH_COOKIES, list):
+ set_cookies(self.req.cj, self.SH_COOKIES)
+
+ def process(self, pyfile):
+ pyfile.url = replace_patterns(pyfile.url, self.FILE_URL_REPLACEMENTS)
+ self.req.setOption("timeout", 120)
+ # Due to a 0.4.9 core bug self.load would keep previous cookies even if overridden by cookies parameter.
+ # Workaround using getURL. Can be reverted in 0.5 as the cookies bug has been fixed.
+ self.html = getURL(pyfile.url, decode=not self.SH_BROKEN_ENCODING, cookies=self.SH_COOKIES)
+ premium_only = hasattr(self, 'PREMIUM_ONLY_PATTERN') and re.search(self.PREMIUM_ONLY_PATTERN, self.html)
+ if not premium_only: # Usually premium only pages doesn't show the file information
+ self.getFileInfo()
+
+ if self.premium and (not self.SH_CHECK_TRAFFIC or self.checkTrafficLeft()):
+ self.handlePremium()
+ elif premium_only:
+ self.fail("This link require a premium account")
+ else:
+ # This line is required due to the getURL workaround. Can be removed in 0.5
+ self.html = self.load(pyfile.url, decode=not self.SH_BROKEN_ENCODING, cookies=self.SH_COOKIES)
+ self.handleFree()
+
+ def load(self, url, get={}, post={}, ref=True, cookies=True, just_header=False, decode=False):
+ if type(url) == unicode:
+ url = url.encode('utf8')
+ return Hoster.load(self, url=url, get=get, post=post, ref=ref, cookies=cookies,
+ just_header=just_header, decode=decode)
+
+ def getFileInfo(self):
+ self.logDebug("URL: %s" % self.pyfile.url)
+
+ name, size, status = parseFileInfo(self)[:3]
+
+ if status == 1:
+ self.offline()
+ elif status == 6:
+ self.tempOffline()
+ elif status != 2:
+ self.logDebug(self.file_info)
+ self.parseError('File info')
+
+ if name:
+ self.pyfile.name = name
+ else:
+ self.pyfile.name = html_unescape(urlparse(self.pyfile.url).path.split("/")[-1])
+
+ if size:
+ self.pyfile.size = size
+ else:
+ self.logError("File size not parsed")
+
+ self.logDebug("FILE NAME: %s FILE SIZE: %s" % (self.pyfile.name, self.pyfile.size))
+ return self.file_info
+
+ def handleFree(self):
+ self.fail("Free download not implemented")
+
+ def handlePremium(self):
+ self.fail("Premium download not implemented")
+
+ def parseError(self, msg):
+ raise PluginParseError(msg)
+
+ def longWait(self, wait_time=None, max_tries=3):
+ if wait_time and isinstance(wait_time, (int, long, float)):
+ time_str = "%dh %dm" % divmod(wait_time / 60, 60)
+ else:
+ wait_time = 900
+ time_str = "(unknown time)"
+ max_tries = 100
+
+ self.logInfo("Download limit reached, reconnect or wait %s" % time_str)
+
+ self.setWait(wait_time, True)
+ self.wait()
+ self.retry(max_tries=max_tries, reason="Download limit reached")
+
+ def parseHtmlForm(self, attr_str='', input_names=None):
+ return parseHtmlForm(attr_str, self.html, input_names)
+
+ def checkTrafficLeft(self):
+ traffic = self.account.getAccountInfo(self.user, True)['trafficleft']
+ if traffic == -1:
+ return True
+ size = self.pyfile.size / 1024
+ self.logInfo("Filesize: %i KiB, Traffic left for user %s: %i KiB" % (size, self.user, traffic))
+ return size <= traffic
+
+ # TODO: Remove in 0.5
+ def wait(self, seconds=False, reconnect=False):
+ if seconds:
+ self.setWait(seconds, reconnect)
+ super(SimpleHoster, self).wait()
diff --git a/pyload/plugins/internal/UnRar.py b/pyload/plugins/internal/UnRar.py
new file mode 100644
index 000000000..ed8478a3a
--- /dev/null
+++ b/pyload/plugins/internal/UnRar.py
@@ -0,0 +1,212 @@
+# -*- coding: utf-8 -*-
+
+import os
+import re
+
+from glob import glob
+from os.path import join
+from string import digits
+from subprocess import Popen, PIPE
+
+from pyload.plugins.internal.AbstractExtractor import AbtractExtractor, WrongPassword, ArchiveError, CRCError
+from pyload.utils import safe_join, decode
+
+
+class UnRar(AbtractExtractor):
+ __name__ = "UnRar"
+ __version__ = "0.16"
+
+ __description__ = """Rar extractor plugin"""
+ __author_name__ = "RaNaN"
+ __author_mail__ = "RaNaN@pyload.org"
+
+ CMD = "unrar"
+
+ # there are some more uncovered rar formats
+ re_version = re.compile(r"(UNRAR 5[\.\d]+(.*?)freeware)")
+ re_splitfile = re.compile(r"(.*)\.part(\d+)\.rar$", re.I)
+ re_partfiles = re.compile(r".*\.(rar|r[0-9]+)", re.I)
+ re_filelist = re.compile(r"(.+)\s+(\d+)\s+(\d+)\s+")
+ re_filelist5 = re.compile(r"(.+)\s+(\d+)\s+\d\d-\d\d-\d\d\s+\d\d:\d\d\s+(.+)")
+ re_wrongpwd = re.compile("(Corrupt file or wrong password|password incorrect)", re.I)
+
+
+ @staticmethod
+ def checkDeps():
+ if os.name == "nt":
+ UnRar.CMD = join(pypath, "UnRAR.exe")
+ p = Popen([UnRar.CMD], stdout=PIPE, stderr=PIPE)
+ p.communicate()
+ else:
+ try:
+ p = Popen([UnRar.CMD], stdout=PIPE, stderr=PIPE)
+ p.communicate()
+ except OSError:
+
+ # fallback to rar
+ UnRar.CMD = "rar"
+ p = Popen([UnRar.CMD], stdout=PIPE, stderr=PIPE)
+ p.communicate()
+
+ return True
+
+ @staticmethod
+ def getTargets(files_ids):
+ result = []
+
+ for file, id in files_ids:
+ if not file.endswith(".rar"):
+ continue
+
+ match = UnRar.re_splitfile.findall(file)
+ if match:
+ # only add first parts
+ if int(match[0][1]) == 1:
+ result.append((file, id))
+ else:
+ result.append((file, id))
+
+ return result
+
+ def init(self):
+ self.passwordProtected = False
+ self.headerProtected = False #: list files will not work without password
+ self.smallestFile = None #: small file to test passwords
+ self.password = "" #: save the correct password
+
+ def checkArchive(self):
+ p = self.call_unrar("l", "-v", self.file)
+ out, err = p.communicate()
+ if self.re_wrongpwd.search(err):
+ self.passwordProtected = True
+ self.headerProtected = True
+ return True
+
+ # output only used to check if passworded files are present
+ if self.re_version.search(out):
+ for attr, size, name in self.re_filelist5.findall(out):
+ if attr.startswith("*"):
+ self.passwordProtected = True
+ return True
+ else:
+ for name, size, packed in self.re_filelist.findall(out):
+ if name.startswith("*"):
+ self.passwordProtected = True
+ return True
+
+ self.listContent()
+ if not self.files:
+ raise ArchiveError("Empty Archive")
+
+ return False
+
+ def checkPassword(self, password):
+ # at this point we can only verify header protected files
+ if self.headerProtected:
+ p = self.call_unrar("l", "-v", self.file, password=password)
+ out, err = p.communicate()
+ if self.re_wrongpwd.search(err):
+ return False
+
+ return True
+
+ def extract(self, progress, password=None):
+ command = "x" if self.fullpath else "e"
+
+ p = self.call_unrar(command, self.file, self.out, password=password)
+ renice(p.pid, self.renice)
+
+ progress(0)
+ progressstring = ""
+ while True:
+ c = p.stdout.read(1)
+ # quit loop on eof
+ if not c:
+ break
+ # reading a percentage sign -> set progress and restart
+ if c == '%':
+ progress(int(progressstring))
+ progressstring = ""
+ # not reading a digit -> therefore restart
+ elif c not in digits:
+ progressstring = ""
+ # add digit to progressstring
+ else:
+ progressstring = progressstring + c
+ progress(100)
+
+ # retrieve stderr
+ err = p.stderr.read()
+
+ if "CRC failed" in err and not password and not self.passwordProtected:
+ raise CRCError
+ elif "CRC failed" in err:
+ raise WrongPassword
+ if err.strip(): #: raise error if anything is on stderr
+ raise ArchiveError(err.strip())
+ if p.returncode:
+ raise ArchiveError("Process terminated")
+
+ if not self.files:
+ self.password = password
+ self.listContent()
+
+ def getDeleteFiles(self):
+ if ".part" in self.file:
+ return glob(re.sub("(?<=\.part)([01]+)", "*", self.file, re.IGNORECASE))
+ # get files which matches .r* and filter unsuited files out
+ parts = glob(re.sub(r"(?<=\.r)ar$", "*", self.file, re.IGNORECASE))
+ return filter(lambda x: self.re_partfiles.match(x), parts)
+
+ def listContent(self):
+ command = "vb" if self.fullpath else "lb"
+ p = self.call_unrar(command, "-v", self.file, password=self.password)
+ out, err = p.communicate()
+
+ if "Cannot open" in err:
+ raise ArchiveError("Cannot open file")
+
+ if err.strip(): #: only log error at this point
+ self.m.logError(err.strip())
+
+ result = set()
+
+ for f in decode(out).splitlines():
+ f = f.strip()
+ result.add(safe_join(self.out, f))
+
+ self.files = result
+
+ def call_unrar(self, command, *xargs, **kwargs):
+ args = []
+ # overwrite flag
+ args.append("-o+") if self.overwrite else args.append("-o-")
+
+ if self.excludefiles:
+ for word in self.excludefiles.split(';'):
+ args.append("-x%s" % word)
+
+ # assume yes on all queries
+ 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.m.logDebug(" ".join(call))
+
+ p = Popen(call, stdout=PIPE, stderr=PIPE)
+
+ return p
+
+
+def renice(pid, value):
+ if os.name != "nt" and value:
+ try:
+ Popen(["renice", str(value), str(pid)], stdout=PIPE, stderr=PIPE, bufsize=-1)
+ except:
+ print "Renice failed"
diff --git a/pyload/plugins/internal/UnZip.py b/pyload/plugins/internal/UnZip.py
new file mode 100644
index 000000000..65a5a82bb
--- /dev/null
+++ b/pyload/plugins/internal/UnZip.py
@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+
+import sys
+import zipfile
+
+from pyload.plugins.internal.AbstractExtractor import AbtractExtractor
+
+
+class UnZip(AbtractExtractor):
+ __name__ = "UnZip"
+ __version__ = "0.1"
+
+ __description__ = """Zip extractor plugin"""
+ __author_name__ = "RaNaN"
+ __author_mail__ = "RaNaN@pyload.org"
+
+
+ @staticmethod
+ def checkDeps():
+ return sys.version_info[:2] >= (2, 6)
+
+ @staticmethod
+ def getTargets(files_ids):
+ result = []
+
+ for file, id in files_ids:
+ if file.endswith(".zip"):
+ result.append((file, id))
+
+ return result
+
+ def extract(self, progress, password=None):
+ z = zipfile.ZipFile(self.file)
+ self.files = z.namelist()
+ z.extractall(self.out)
+
+ def getDeleteFiles(self):
+ return [self.file]
diff --git a/pyload/plugins/internal/XFSPAccount.py b/pyload/plugins/internal/XFSPAccount.py
new file mode 100644
index 000000000..aec9b7dbc
--- /dev/null
+++ b/pyload/plugins/internal/XFSPAccount.py
@@ -0,0 +1,69 @@
+# -*- coding: utf-8 -*-
+
+import re
+
+from time import mktime, strptime
+
+from pyload.plugins.Account import Account
+from pyload.plugins.internal.SimpleHoster import parseHtmlForm
+from pyload.utils import parseFileSize
+
+
+class XFSPAccount(Account):
+ __name__ = "XFSPAccount"
+ __type__ = "account"
+ __version__ = "0.06"
+
+ __description__ = """XFileSharingPro base account plugin"""
+ __author_name__ = "zoidberg"
+ __author_mail__ = "zoidberg@mujmail.cz"
+
+ MAIN_PAGE = None
+
+ VALID_UNTIL_PATTERN = r'>Premium.[Aa]ccount expire:</TD><TD><b>([^<]+)</b>'
+ TRAFFIC_LEFT_PATTERN = r'>Traffic available today:</TD><TD><b>([^<]+)</b>'
+ LOGIN_FAIL_PATTERN = r'Incorrect Login or Password|>Error<'
+ PREMIUM_PATTERN = r'>Renew premium<'
+
+
+ def loadAccountInfo(self, user, req):
+ html = req.load(self.MAIN_PAGE + "?op=my_account", decode=True)
+
+ validuntil = trafficleft = None
+ premium = True if re.search(self.PREMIUM_PATTERN, html) else False
+
+ m = re.search(self.VALID_UNTIL_PATTERN, html)
+ if m:
+ premium = True
+ trafficleft = -1
+ try:
+ self.logDebug(m.group(1))
+ validuntil = mktime(strptime(m.group(1), "%d %B %Y"))
+ except Exception, e:
+ self.logError(e)
+ else:
+ m = re.search(self.TRAFFIC_LEFT_PATTERN, html)
+ if m:
+ trafficleft = m.group(1)
+ if "Unlimited" in trafficleft:
+ premium = True
+ else:
+ trafficleft = parseFileSize(trafficleft) / 1024
+
+ return {"validuntil": validuntil, "trafficleft": trafficleft, "premium": premium}
+
+ def login(self, user, data, req):
+ html = req.load('%slogin.html' % self.MAIN_PAGE, decode=True)
+
+ action, inputs = parseHtmlForm('name="FL"', html)
+ if not inputs:
+ inputs = {"op": "login",
+ "redirect": self.MAIN_PAGE}
+
+ inputs.update({"login": user,
+ "password": data['password']})
+
+ html = req.load(self.MAIN_PAGE, post=inputs, decode=True)
+
+ if re.search(self.LOGIN_FAIL_PATTERN, html):
+ self.wrongPassword()
diff --git a/pyload/plugins/internal/__init__.py b/pyload/plugins/internal/__init__.py
new file mode 100644
index 000000000..e69de29bb
--- /dev/null
+++ b/pyload/plugins/internal/__init__.py
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-03 13:56:15 +0100