diff options
Diffstat (limited to 'pyload/plugins/internal/SimpleCrypter.py')
-rw-r--r-- | pyload/plugins/internal/SimpleCrypter.py | 135 |
1 files changed, 81 insertions, 54 deletions
diff --git a/pyload/plugins/internal/SimpleCrypter.py b/pyload/plugins/internal/SimpleCrypter.py index 6c5c9593f..634ec5f12 100644 --- a/pyload/plugins/internal/SimpleCrypter.py +++ b/pyload/plugins/internal/SimpleCrypter.py @@ -2,22 +2,28 @@ import re +from urlparse import urlparse + from pyload.plugins.Crypter import Crypter -from pyload.plugins.internal.SimpleHoster import PluginParseError, replace_patterns, set_cookies +from module.plugins.Plugin import Fail +from module.plugins.internal.SimpleHoster import _error, _wait, parseFileInfo, replace_patterns, set_cookies from pyload.utils import fixup, html_unescape class SimpleCrypter(Crypter): - __name__ = "SimpleCrypter" - __type__ = "crypter" - __version__ = "0.13" + __name__ = "SimpleCrypter" + __type__ = "crypter" + __version__ = "0.28" - __pattern__ = None + __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""" - __authors__ = [("stickell", "l.stickell@yahoo.it"), - ("zoidberg", "zoidberg@mujmail.cz"), - ("Walter Purcaro", "vuolter@gmail.com")] + __license__ = "GPLv3" + __authors__ = [("stickell", "l.stickell@yahoo.it"), + ("zoidberg", "zoidberg@mujmail.cz"), + ("Walter Purcaro", "vuolter@gmail.com")] """ @@ -26,8 +32,8 @@ class SimpleCrypter(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="(.+?)"' - TITLE_PATTERN: (optional) group(1) should be the folder name or the webpage title - example: TITLE_PATTERN = r'<title>Files of: ([^<]+) folder</title>' + 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)' @@ -46,87 +52,103 @@ class SimpleCrypter(Crypter): and its loadPage method: + def loadPage(self, page_n): return the html of the page number page_n """ - TITLE_REPLACEMENTS = [("&#?\w+;", fixup)] - URL_REPLACEMENTS = [] + 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)] + 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!') + self.fail(_("Required account not found")) if self.LOGIN_PREMIUM and not self.premium: - self.fail('Required premium account not found!') + 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) - def decrypt(self, pyfile): - self.prepare() + if self.html is None: + self.html = self.load(self.pyfile.url, decode=not self.TEXT_ENCODING, cookies=bool(self.COOKIES)) - pyfile.url = replace_patterns(pyfile.url, self.URL_REPLACEMENTS) + if isinstance(self.TEXT_ENCODING, basestring): + self.html = unicode(self.html, self.TEXT_ENCODING) - self.html = self.load(pyfile.url, decode=not self.TEXT_ENCODING) - self.checkOnline() + def decrypt(self, pyfile): + self.prepare() - package_name, folder_name = self.getPackageNameAndFolder() + if self.html is None: + self.fail(_("No html retrieved")) - self.package_links = self.getLinks() + 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.package_links)) + self.logDebug("Package has %d links" % len(self.links)) - if self.package_links: - self.packages = [(package_name, self.package_links, folder_name)] - else: - self.fail('Could not extract any links') + if self.links: + self.packages = [(self.info['name'], self.links, self.info['folder'])] - 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 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] - def checkOnline(self): - if hasattr(self, "OFFLINE_PATTERN") and re.search(self.OFFLINE_PATTERN, self.html): + if status is 1: self.offline() - elif hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, self.html): + + elif status is 6: self.tempOffline() + self.info['folder'] = self.pyfile.name - def getPackageNameAndFolder(self): - if hasattr(self, 'TITLE_PATTERN'): - try: - m = re.search(self.TITLE_PATTERN, self.html) - name = replace_patterns(m.group(1).strip(), self.TITLE_REPLACEMENTS) - folder = html_unescape(name) - except: - pass - else: - self.logDebug("Found name [%s] and folder [%s] in package info" % (name, folder)) - return name, folder + self.logDebug("FILE NAME: %s" % self.pyfile.name) + return self.info - 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 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): @@ -138,8 +160,13 @@ class SimpleCrypter(Crypter): for p in xrange(2, pages + 1): self.html = self.loadPage(p) - self.package_links += self.getLinks() + self.links += self.getLinks() + + + #@TODO: Remove in 0.4.10 + def wait(self, seconds=0, reconnect=None): + return _wait(self, seconds, reconnect) - def parseError(self, msg): - raise PluginParseError(msg) + def error(self, reason="", type="parse"): + return _error(self, reason, type) |