diff options
Diffstat (limited to 'module/plugins/internal')
-rw-r--r-- | module/plugins/internal/AbstractExtractor.py | 109 | ||||
-rw-r--r-- | module/plugins/internal/DeadCrypter.py | 20 | ||||
-rw-r--r-- | module/plugins/internal/DeadHoster.py | 28 | ||||
-rw-r--r-- | module/plugins/internal/MultiHoster.py | 205 | ||||
-rw-r--r-- | module/plugins/internal/SimpleCrypter.py | 172 | ||||
-rw-r--r-- | module/plugins/internal/SimpleHoster.py | 422 | ||||
-rw-r--r-- | module/plugins/internal/UnRar.py | 221 | ||||
-rw-r--r-- | module/plugins/internal/UnZip.py | 41 | ||||
-rw-r--r-- | module/plugins/internal/__init__.py | 0 |
9 files changed, 0 insertions, 1218 deletions
diff --git a/module/plugins/internal/AbstractExtractor.py b/module/plugins/internal/AbstractExtractor.py deleted file mode 100644 index 8a69ebb56..000000000 --- a/module/plugins/internal/AbstractExtractor.py +++ /dev/null @@ -1,109 +0,0 @@ -# -*- 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""" - __license__ = "GPLv3" - __authors__ = [("pyLoad Team", "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/module/plugins/internal/DeadCrypter.py b/module/plugins/internal/DeadCrypter.py deleted file mode 100644 index 4c635e366..000000000 --- a/module/plugins/internal/DeadCrypter.py +++ /dev/null @@ -1,20 +0,0 @@ -# -*- coding: utf-8 -*- - -from module.plugins.Crypter import Crypter as _Crypter - - -class DeadCrypter(_Crypter): - __name__ = "DeadCrypter" - __type__ = "crypter" - __version__ = "0.02" - - __pattern__ = r'^unmatchable$' - - __description__ = """ Crypter is no longer available """ - __license__ = "GPLv3" - __authors__ = [("stickell", "l.stickell@yahoo.it")] - - - def setup(self): - self.pyfile.error = "Crypter is no longer available" - self.offline() #@TODO: self.offline("Crypter is no longer available") diff --git a/module/plugins/internal/DeadHoster.py b/module/plugins/internal/DeadHoster.py deleted file mode 100644 index b78068069..000000000 --- a/module/plugins/internal/DeadHoster.py +++ /dev/null @@ -1,28 +0,0 @@ -# -*- coding: utf-8 -*- - -from module.plugins.Hoster import Hoster as _Hoster - - -def create_getInfo(plugin): - - def getInfo(urls): - yield map(lambda url: ('#N/A: ' + url, 0, 1, url), urls) - - return getInfo - - -class DeadHoster(_Hoster): - __name__ = "DeadHoster" - __type__ = "hoster" - __version__ = "0.12" - - __pattern__ = r'^unmatchable$' - - __description__ = """ Hoster is no longer available """ - __license__ = "GPLv3" - __authors__ = [("zoidberg", "zoidberg@mujmail.cz")] - - - def setup(self): - self.pyfile.error = "Hoster is no longer available" - self.offline() #@TODO: self.offline("Hoster is no longer available") diff --git a/module/plugins/internal/MultiHoster.py b/module/plugins/internal/MultiHoster.py deleted file mode 100644 index f0d3993a7..000000000 --- a/module/plugins/internal/MultiHoster.py +++ /dev/null @@ -1,205 +0,0 @@ -# -*- coding: utf-8 -*- - -import re - -from module.plugins.Hook import Hook -from module.utils import remove_chars - - -class MultiHoster(Hook): - __name__ = "AbtractExtractor" - __type__ = "hook" - __version__ = "0.19" - - __description__ = """Generic MultiHoster plugin""" - __license__ = "GPLv3" - __authors__ = [("pyLoad Team", "admin@pyload.org")] - - - interval = 24 * 60 * 60 #: reload hosters daily - - HOSTER_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")] - HOSTER_EXCLUDED = [] - - - def setup(self): - self.hosters = [] - self.supported = [] - self.new_supported = [] - - - 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 getHosterCached(self): - if not self.hosters: - - try: - hosterSet = self.toHosterSet(self.getHoster()) - set(self.HOSTER_EXCLUDED) - except Exception, e: - self.logError(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(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.HOSTER_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", ", ".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.iteritems() 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", ", ".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"), ", ".join(sorted(excludedList))) - - if self.new_supported: - self.logDebug("New Hosters", ", ".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", 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$') - dict['re'] = re.compile(dict['pattern']) - - - def downloadFailed(self, pyfile): - """remove plugin override if download fails but not if file is offline/temp.offline""" - if pyfile.hasStatus("failed") and self.getConfig("unloadFailing", True): - hdict = self.core.pluginManager.hosterPlugins[pyfile.pluginname] - if "new_name" in hdict and hdict['new_name'] == self.__name__: - self.logDebug("Unload MultiHoster", pyfile.pluginname, hdict) - self.unloadHoster(pyfile.pluginname) - pyfile.setStatus("queued") diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py deleted file mode 100644 index 0e43496c4..000000000 --- a/module/plugins/internal/SimpleCrypter.py +++ /dev/null @@ -1,172 +0,0 @@ -# -*- coding: utf-8 -*- - -import re - -from urlparse import urlparse - -from module.plugins.Crypter import Crypter -from module.plugins.Plugin import Fail -from module.plugins.internal.SimpleHoster import _error, _wait, parseFileInfo, replace_patterns, set_cookies -from module.utils import fixup, html_unescape - - -class SimpleCrypter(Crypter): - __name__ = "SimpleCrypter" - __type__ = "crypter" - __version__ = "0.28" - - __pattern__ = r'^unmatchable$' - __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)] - - __description__ = """Simple decrypter plugin""" - __license__ = "GPLv3" - __authors__ = [("stickell", "l.stickell@yahoo.it"), - ("zoidberg", "zoidberg@mujmail.cz"), - ("Walter Purcaro", "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="(.+?)"' - - NAME_PATTERN: (optional) folder name or webpage title - example: NAME_PATTERN = r'<title>Files of: (?P<N>[^<]+) 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' - - - You can override the getLinks method if you need a more sophisticated way to extract the links. - - - If the links are splitted on multiple pages you can define the PAGES_PATTERN regex: - - PAGES_PATTERN: (optional) group(1) should be the number of overall pages containing the links - example: PAGES_PATTERN = r'Pages: (\d+)' - - and its loadPage method: - - - def loadPage(self, page_n): - 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): - self.info = {} - - account_name = (self.__name__ + ".py").replace("Folder.py", "").replace(".py", "") - account = self.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.account = account - - - def prepare(self): - if self.LOGIN_ACCOUNT and not self.account: - self.fail(_("Required account not found")) - - if self.LOGIN_PREMIUM and not self.premium: - self.fail(_("Required premium account not found")) - - if isinstance(self.COOKIES, list): - set_cookies(self.req.cj, self.COOKIES) - - self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS) - - if self.html is None: - self.html = self.load(self.pyfile.url, decode=not self.TEXT_ENCODING, cookies=bool(self.COOKIES)) - - if isinstance(self.TEXT_ENCODING, basestring): - self.html = unicode(self.html, self.TEXT_ENCODING) - - - def decrypt(self, pyfile): - self.prepare() - - if self.html is None: - self.fail(_("No html retrieved")) - - if not self.info: - self.getFileInfo() - - self.links = self.getLinks() - - if hasattr(self, 'PAGES_PATTERN') and hasattr(self, 'loadPage'): - self.handleMultiPages() - - self.logDebug("Package has %d links" % len(self.links)) - - if self.links: - self.packages = [(self.info['name'], self.links, self.info['folder'])] - - - def getFileInfo(self): - name, size, status, url = parseFileInfo(self) - - if name and name != url: - self.pyfile.name = name - else: - self.pyfile.name = self.info['name'] = urlparse(html_unescape(name)).path.split("/")[-1] - - if status is 1: - self.offline() - - elif status is 6: - self.tempOffline() - - self.info['folder'] = self.pyfile.name - - self.logDebug("FILE NAME: %s" % self.pyfile.name) - return self.info - - - 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 handleMultiPages(self): - try: - m = re.search(self.PAGES_PATTERN, self.html) - pages = int(m.group(1)) - except: - pages = 1 - - for p in xrange(2, pages + 1): - self.html = self.loadPage(p) - self.links += self.getLinks() - - - #@TODO: Remove in 0.4.10 - def wait(self, seconds=0, reconnect=None): - return _wait(self, seconds, reconnect) - - - def error(self, reason="", type="parse"): - return _error(self, reason, type) diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py deleted file mode 100644 index 6726d4fa5..000000000 --- a/module/plugins/internal/SimpleHoster.py +++ /dev/null @@ -1,422 +0,0 @@ -# -*- coding: utf-8 -*- - -import re - -from time import time -from urlparse import urlparse - -from pycurl import FOLLOWLOCATION - -from module.network.CookieJar import CookieJar -from module.network.RequestFactory import getURL -from module.plugins.Hoster import Hoster -from module.plugins.Plugin import Fail -from module.utils import fixup, html_unescape, parseFileSize - - -#@TODO: Remove in 0.4.10 and redirect to self.error instead -def _error(self, reason, type): - if not reason and not type: - type = "unknown" - - msg = _("%s error") % type.strip().capitalize() if type else _("Error") - msg += ": " + reason.strip() if reason else "" - msg += _(" | Plugin may be out of date") - - raise Fail(msg) - - -#@TODO: Remove in 0.4.10 -def _wait(self, seconds, reconnect): - if seconds: - self.setWait(seconds, reconnect) - super(SimpleHoster, self).wait() - - -def replace_patterns(string, ruleslist): - for r in ruleslist: - rf, rt = r - string = re.sub(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.iteritems(): - 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=""): - if not url and hasattr(self, "pyfile"): - url = self.pyfile.url - - info = {'name': url, 'size': 0, 'status': 3} - - if not html: - if url: - return create_getInfo(self)([url]).next() - - elif hasattr(self, "req") and self.req.http.code == '404': - info['status'] = 1 - - elif hasattr(self, "html"): - html = self.html - - if 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 ("INFO_PATTERN", "NAME_PATTERN", "SIZE_PATTERN", - "FILE_INFO_PATTERN", "FILE_NAME_PATTERN", "FILE_SIZE_PATTERN"): #@TODO: Remove in 0.4.10 - 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'].strip(), - self.FILE_NAME_REPLACEMENTS if hasattr(self, "FILE_NAME_REPLACEMENTS") else self.NAME_REPLACEMENTS) #@TODO: Remove FILE_NAME_REPLACEMENTS check in 0.4.10 - - if 'S' in info: - size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'], - self.FILE_SIZE_REPLACEMENTS if hasattr(self, "FILE_SIZE_REPLACEMENTS") else self.SIZE_REPLACEMENTS) #@TODO: Remove FILE_SIZE_REPLACEMENTS check in 0.4.10 - info['size'] = parseFileSize(size) - - elif isinstance(info['size'], basestring): - unit = info['units'] if 'units' in info else None - info['size'] = parseFileSize(info['size'], unit) - - if hasattr(self, "html") and self.html is None: - self.html = html - - if hasattr(self, "info"): - try: - self.logDebug(_("File info (before update): %s") % self.info) - except: - pass - - self.info.update(info) - - try: - self.logDebug(_("File info (after update): %s") % self.info) - except: - pass - - return info['name'], info['size'], info['status'], url - - -def create_getInfo(plugin): - - def getInfo(urls): - for url in urls: - if hasattr(plugin, "COOKIES") and isinstance(plugin.COOKIES, list): - cj = CookieJar(plugin.__name__) - set_cookies(cj, plugin.COOKIES) - else: - cj = None - - if hasattr(plugin, "URL_REPLACEMENTS"): - url = replace_patterns(url, plugin.URL_REPLACEMENTS) - - elif hasattr(plugin, "FILE_URL_REPLACEMENTS"): #@TODO: Remove in 0.4.10 - url = replace_patterns(url, plugin.FILE_URL_REPLACEMENTS) - - if hasattr(plugin, "TEXT_ENCODING"): - html = getURL(url, cookies=bool(cj), decode=not plugin.TEXT_ENCODING) - if isinstance(plugin.TEXT_ENCODING, basestring): - html = unicode(html, plugin.TEXT_ENCODING) - else: - html = getURL(url, cookies=bool(cj), decode=True) - - yield parseFileInfo(plugin, url, html) - - return getInfo - - -def timestamp(): - return int(time() * 1000) - - -class SimpleHoster(Hoster): - __name__ = "SimpleHoster" - __type__ = "hoster" - __version__ = "0.53" - - __pattern__ = r'^unmatchable$' - - __description__ = """Simple hoster plugin""" - __license__ = "GPLv3" - __authors__ = [("zoidberg", "zoidberg@mujmail.cz"), - ("stickell", "l.stickell@yahoo.it"), - ("Walter Purcaro", "vuolter@gmail.com")] - - - """ - Following patterns should be defined by each hoster: - - INFO_PATTERN: (optional) 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 - example: NAME_PATTERN = r'(?P<N>file_name)' - SIZE_PATTERN: (optional) Size that will be checked for the file - example: SIZE_PATTERN = r'(?P<S>file_size) (?P<U>size_unit)' - - 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 (maintenance|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' - - - Instead overriding handleFree and handlePremium methods now you can define patterns for direct download: - - 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="(.+?)"' - """ - - NAME_REPLACEMENTS = [("&#?\w+;", fixup)] - SIZE_REPLACEMENTS = [] - 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)] - FORCE_CHECK_TRAFFIC = False #: Set to True to force checking traffic left for premium account - - - def init(self): - self.info = {} - - - def setup(self): - self.resumeDownload = self.multiDL = self.premium - - - def prepare(self): - if isinstance(self.COOKIES, list): - set_cookies(self.req.cj, self.COOKIES) - - self.req.setOption("timeout", 120) - - 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 - - if self.premium: - self.logDebug(_("Looking for direct download link...")) - direct_link = self.getDirectLink(self.pyfile.url) - if direct_link: - return direct_link - else: - self.logDebug(_("No direct download link found")) - self.html = None - self.info = {} - - if self.html is None: - self.html = self.load(self.pyfile.url, decode=not self.TEXT_ENCODING, cookies=bool(self.COOKIES)) - - if isinstance(self.TEXT_ENCODING, basestring): - self.html = unicode(self.html, self.TEXT_ENCODING) - - - def process(self, pyfile): - direct_link = self.prepare() - - if isinstance(direct_link, basestring): - self.logInfo(_("Direct download link detected")) - self.download(direct_link, ref=True, cookies=True, disposition=True) - - elif self.html is None: - self.fail(_("No html retrieved")) - - else: - premium_only = hasattr(self, 'PREMIUM_ONLY_PATTERN') and re.search(self.PREMIUM_ONLY_PATTERN, self.html) - if not premium_only and not self.info: #: Usually premium only pages doesn't show any file information - self.getFileInfo() - - if self.premium and (not self.FORCE_CHECK_TRAFFIC or self.checkTrafficLeft()): - self.logDebug("Handle as premium download") - self.handlePremium() - elif premium_only: - self.fail(_("Link require a premium account to be handled")) - else: - self.logDebug("Handle as free download") - self.handleFree() - - - def getDirectLink(self, url): - self.req.http.c.setopt(FOLLOWLOCATION, 0) - - html = self.load(url, ref=True, decode=True) - - self.req.http.c.setopt(FOLLOWLOCATION, 1) - - if parseFileInfo(self, url, html)[2] is not 2: - try: - return re.search(r'Location\s*:\s*(.+)', self.req.http.header, re.I).group(1).rstrip() #@TODO: Remove .rstrip() in 0.4.10 - except: - pass - - - def getFileInfo(self): - name, size, status, url = parseFileInfo(self) - - if name and name != url: - self.pyfile.name = name - else: - self.pyfile.name = self.info['name'] = urlparse(html_unescape(name)).path.split("/")[-1] - - if status is 1: - self.offline() - - elif status is 6: - self.tempOffline() - - elif status is not 2: - self.error(_("File info: %s") % self.info) - - if size: - self.pyfile.size = size - else: - self.logError(_("File size not parsed")) - - self.logDebug("FILE NAME: %s" % self.pyfile.name, "FILE SIZE: %d" % self.pyfile.size or _("Unknown")) - return self.info - - - def handleFree(self): - if not hasattr(self, 'LINK_FREE_PATTERN'): - self.fail(_("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")) - - link = m.group(1) - except Exception, e: - self.fail(str(e)) - else: - self.download(link, ref=True, cookies=True, disposition=True) - - - def handlePremium(self): - if not hasattr(self, 'LINK_PREMIUM_PATTERN'): - self.fail(_("Premium download not implemented")) - - try: - m = re.search(self.LINK_PREMIUM_PATTERN, self.html) - if m is None: - self.error(_("Premium download link not found")) - - link = m.group(1) - except Exception, e: - self.fail(str(e)) - else: - self.download(link, ref=True, cookies=True, disposition=True) - - - 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 is None: - return False - elif traffic == -1: - return True - else: - 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 0.4.10 - def wait(self, seconds=0, reconnect=None): - return _wait(self, seconds, reconnect) - - - def error(self, reason="", type="parse"): - return _error(self, reason, type) diff --git a/module/plugins/internal/UnRar.py b/module/plugins/internal/UnRar.py deleted file mode 100644 index 12bd84d20..000000000 --- a/module/plugins/internal/UnRar.py +++ /dev/null @@ -1,221 +0,0 @@ -# -*- coding: utf-8 -*- - -import os -import re - -from glob import glob -from os.path import basename, join -from string import digits -from subprocess import Popen, PIPE - -from module.plugins.internal.AbstractExtractor import AbtractExtractor, WrongPassword, ArchiveError, CRCError -from module.utils import save_join, decode - - -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" - - -class UnRar(AbtractExtractor): - __name__ = "UnRar" - __version__ = "0.18" - - __description__ = """Rar extractor plugin""" - __license__ = "GPLv3" - __authors__ = [("RaNaN", "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\d+)", 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 basename(self.file): - return glob(re.sub("(?<=\.part)([01]+)", "*", self.file, re.I)) - # get files which matches .r* and filter unsuited files out - parts = glob(re.sub(r"(?<=\.r)ar$", "*", self.file, re.I)) - 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(save_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 diff --git a/module/plugins/internal/UnZip.py b/module/plugins/internal/UnZip.py deleted file mode 100644 index e754141a1..000000000 --- a/module/plugins/internal/UnZip.py +++ /dev/null @@ -1,41 +0,0 @@ -# -*- coding: utf-8 -*- - -import sys -import zipfile - -from module.plugins.internal.AbstractExtractor import AbtractExtractor - - -class UnZip(AbtractExtractor): - __name__ = "UnZip" - __version__ = "0.1" - - __description__ = """Zip extractor plugin""" - __license__ = "GPLv3" - __authors__ = [("RaNaN", "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/module/plugins/internal/__init__.py b/module/plugins/internal/__init__.py deleted file mode 100644 index e69de29bb..000000000 --- a/module/plugins/internal/__init__.py +++ /dev/null |