diff options
Diffstat (limited to 'pyload')
| -rw-r--r-- | pyload/plugins/crypter/LinkCryptWs.py | 63 | ||||
| -rw-r--r-- | pyload/plugins/hoster/OneFichierCom.py | 2 | ||||
| -rw-r--r-- | pyload/plugins/internal/SimpleCrypter.py | 47 | ||||
| -rw-r--r-- | pyload/plugins/internal/SimpleHoster.py | 307 | ||||
| -rw-r--r-- | pyload/plugins/internal/XFSHoster.py | 11 |
5 files changed, 226 insertions, 204 deletions
diff --git a/pyload/plugins/crypter/LinkCryptWs.py b/pyload/plugins/crypter/LinkCryptWs.py index 4b4adc8d1..f01c42268 100644 --- a/pyload/plugins/crypter/LinkCryptWs.py +++ b/pyload/plugins/crypter/LinkCryptWs.py @@ -15,7 +15,7 @@ from pyload.utils import html_unescape class LinkCryptWs(Crypter): __name__ = "LinkCryptWs" __type__ = "crypter" - __version__ = "0.05" + __version__ = "0.06" __pattern__ = r'http://(?:www\.)?linkcrypt\.ws/(dir|container)/(?P<ID>\w+)' @@ -25,22 +25,18 @@ class LinkCryptWs(Crypter): ("glukgluk", None)] - JK_KEY = "jk" CRYPTED_KEY = "crypted" + JK_KEY = "jk" def setup(self): - self.html = None - self.fileid = None self.captcha = False - self.package = None - - self.preferred_sources = ['cnl', 'web', 'dlc', 'rsdf', 'ccf', ] #['cnl', 'rsdf', 'ccf', 'dlc', 'web'] + self.links = [] + self.sources = ['cnl', 'web', 'dlc', 'rsdf', 'ccf'] def prepare(self): # Init - self.package = pyfile.package() self.fileid = re.match(self.__pattern__, pyfile.url).group('ID') self.req.cj.setCookie("linkcrypt.ws", "language", "en") @@ -51,12 +47,9 @@ class LinkCryptWs(Crypter): def decrypt(self, pyfile): - #check if we have js if not self.js: self.fail(_("Missing JS Engine")) - package_found = None - self.prepare() if not self.isOnline(): @@ -85,23 +78,15 @@ class LinkCryptWs(Crypter): self.get_container_html() # Extract package links - package_links = [] + for type in self.sources: + links = self.handleLinkSource(type) - for type_ in self.preferred_sources: - links = self.handleLinkSource(type_) if links: - if isinstance(links, list): - package_links.extend(links) - else: - package_found = True + self.links.extend(links) break - # Pack - if package_links: - self.packages = [(package_name, package_links, folder_name)] - - elif package_found: - self.core.api.deletePackages([self.package.id]) + if self.links: + self.packages = [(package_name, self.links, folder_name)] def isOnline(self): @@ -187,18 +172,18 @@ class LinkCryptWs(Crypter): self.correctCaptcha() - def handleLinkSource(self, type_): - if type_ == 'cnl': + def handleLinkSource(self, type): + if type == 'cnl': return self.handleCNL2() - elif type_ == 'web': + elif type == 'web': return self.handleWebLinks() - elif type_ in ('rsdf', 'ccf', 'dlc'): - return self.handleContainer(type_) + elif type in ('rsdf', 'ccf', 'dlc'): + return self.handleContainer(type) else: - self.error(_("Unknown source type: %s") % type_) + self.fail(_("Unknown source type: %s") % type) #@TODO: Replace with self.error in 0.4.10 def handleWebLinks(self): @@ -247,17 +232,17 @@ class LinkCryptWs(Crypter): return self.js.eval(line.replace('{}))',"{}).replace('document.open();document.write','').replace(';document.close();',''))")) - def handleContainer(self, type_): + def handleContainer(self, type): package_links = [] - type_ = type_.lower() + type = type.lower() - self.logDebug('Search for %s Container links' % type_.upper()) + self.logDebug('Search for %s Container links' % type.upper()) - if not type_.isalnum(): # check to prevent broken re-pattern (cnl2,rsdf,ccf,dlc,web are all alpha-numeric) - self.error(_("unknown container type: %s") % type_) + if not type.isalnum(): # check to prevent broken re-pattern (cnl2,rsdf,ccf,dlc,web are all alpha-numeric) + self.fail(_("Unknown container type: %s") % type) #@TODO: Replace with self.error in 0.4.10 for line in self.container_html: - if(type_ in line): + if type in line: jseval = self.handle_javascript(line) clink = re.search(r'href=["\']([^"\']*?)["\']',jseval,re.I) @@ -267,8 +252,8 @@ class LinkCryptWs(Crypter): self.logDebug("clink avaible") package_name, folder_name = self.getPackageInfo() - self.logDebug("Added package with name %s.%s and container link %s" %( package_name, type_, clink.group(1))) - self.core.api.uploadContainer( "%s.%s" %(package_name, type_), self.load(clink.group(1))) + self.logDebug("Added package with name %s.%s and container link %s" %( package_name, type, clink.group(1))) + self.core.api.uploadContainer( "%s.%s" %(package_name, type), self.load(clink.group(1))) return "Found it" return package_links @@ -281,7 +266,7 @@ class LinkCryptWs(Crypter): cnl_line = None for line in self.container_html: - if("cnl" in line): + if "cnl" in line: cnl_line = line break diff --git a/pyload/plugins/hoster/OneFichierCom.py b/pyload/plugins/hoster/OneFichierCom.py index b30358ff8..6e04776b5 100644 --- a/pyload/plugins/hoster/OneFichierCom.py +++ b/pyload/plugins/hoster/OneFichierCom.py @@ -8,7 +8,7 @@ from pyload.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo class OneFichierCom(SimpleHoster): __name__ = "OneFichierCom" __type__ = "hoster" - __version__ = "0.72" + __version__ = "0.73" __pattern__ = r'https?://(?:www\.)?(?:(?P<ID1>\w+)\.)?(?P<HOST>1fichier\.com|alterupload\.com|cjoint\.net|d(es)?fichiers\.com|dl4free\.com|megadl\.fr|mesfichiers\.org|piecejointe\.net|pjointe\.com|tenvoi\.com)(?:/\?(?P<ID2>\w+))?' diff --git a/pyload/plugins/internal/SimpleCrypter.py b/pyload/plugins/internal/SimpleCrypter.py index 460084919..227c93da6 100644 --- a/pyload/plugins/internal/SimpleCrypter.py +++ b/pyload/plugins/internal/SimpleCrypter.py @@ -13,7 +13,7 @@ from pyload.utils import fixup, html_unescape class SimpleCrypter(Crypter): __name__ = "SimpleCrypter" __type__ = "crypter" - __version__ = "0.29" + __version__ = "0.30" __pattern__ = r'^unmatchable$' __config__ = [("use_subfolder", "bool", "Save package to subfolder", True), #: Overrides core.config['general']['folder_per_package'] @@ -76,12 +76,16 @@ class SimpleCrypter(Crypter): if self.LOGIN_PREMIUM and not self.premium: self.fail(_("Required premium account not found")) + self.req.setOption("timeout", 120) + if isinstance(self.COOKIES, list): set_cookies(self.req.cj, self.COOKIES) self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS) - self.html = self.load(self.pyfile.url, decode=not self.TEXT_ENCODING, cookies=bool(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) @@ -90,11 +94,12 @@ class SimpleCrypter(Crypter): def decrypt(self, pyfile): self.prepare() + self.preload() + if self.html is None: self.fail(_("No html retrieved")) - if not self.info: - self.getFileInfo() + self.checkInfo() self.links = self.getLinks() @@ -107,13 +112,8 @@ class SimpleCrypter(Crypter): 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] + def checkStatus(self): + status = self.info['status'] if status is 1: self.offline() @@ -121,10 +121,31 @@ class SimpleCrypter(Crypter): elif status is 6: self.tempOffline() + + def checkName(self): + name = self.info['name'] + url = self.info['url'] + + if name and name != url: + self.pyfile.name = name + else: + self.pyfile.name = self.info['name'] = urlparse(html_unescape(name)).path.split('/')[-1] + self.info['folder'] = self.pyfile.name - self.logDebug("FILE NAME: %s" % self.pyfile.name) - return self.info + self.logDebug("File name: %s" % self.pyfile.name) + + + def checkInfo(self): + self.logDebug(_("File info (previous): %s") % self.info) + + info = parseFileInfo(self.pyfile.url, self.html or "") + self.info.update(info) + + self.logDebug(_("File info (current): %s") % self.info) + + self.checkName() + self.checkStatus() def getLinks(self): diff --git a/pyload/plugins/internal/SimpleHoster.py b/pyload/plugins/internal/SimpleHoster.py index afd61d821..0efcb9c6f 100644 --- a/pyload/plugins/internal/SimpleHoster.py +++ b/pyload/plugins/internal/SimpleHoster.py @@ -7,6 +7,7 @@ from urlparse import urlparse from pycurl import FOLLOWLOCATION +from pyload.datatype.PyFile import statusMap from pyload.network.CookieJar import CookieJar from pyload.network.RequestFactory import getURL from pyload.plugins.internal.Hoster import Hoster @@ -57,122 +58,50 @@ def parseHtmlForm(attr_str, html, input_names=None): continue elif hasattr(val, "search") and re.match(val, inputs[key]): continue - break # attibute value does not match + break #: attibute value does not match else: - break # attibute name does not match + break #: attibute name does not match else: - return action, inputs # passed attribute check + return action, inputs #: passed attribute check else: # no attribute check return action, inputs - return {}, None # no matching form found + return {}, None #: no matching form found -def parseFileInfo(self, url="", html=""): - if not url and hasattr(self, "pyfile"): - url = self.pyfile.url +def parseFileInfo(plugin, url="", html=""): + info = plugin.getInfo(url, html) + return info['name'], info['size'], info['status'], info['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, "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"): - 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 +def create_getInfo(plugin): + return lambda urls: list(plugin.parseInfo(urls)) - if 'N' in info: - info['name'] = replace_patterns(info['N'].strip(), self.NAME_REPLACEMENTS) - if 'S' in info: - size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'], self.SIZE_REPLACEMENTS) - info['size'] = parseFileSize(size) +def timestamp(): + return int(time() * 1000) - 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 +#@TODO: Move to hoster class in 0.4.10 +def _getDirectLink(self, url): + self.req.http.c.setopt(FOLLOWLOCATION, 0) - if hasattr(self, "info"): - try: - self.logDebug(_("File info (before update): %s") % self.info) - except: - pass + html = self.load(url, ref=True, decode=True) - self.info.update(info) + self.req.http.c.setopt(FOLLOWLOCATION, 1) + if self.getInfo(url, html)['status'] is not 2: try: - self.logDebug(_("File info (after update): %s") % self.info) + 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 - 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) - - 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__ = "0.54" + __version__ = "0.56" __pattern__ = r'^unmatchable$' @@ -217,13 +146,74 @@ class SimpleHoster(Hoster): 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)] + 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)] FORCE_CHECK_TRAFFIC = False #: Set to True to force checking traffic left for premium account + CHECK_DIRECT_LINK = None #: Set to None self-set to True if self.account else to False + CONTENT_DISPOSITION = False #: Set to True to replace file name with content-disposition value in http header + + + @classmethod + def parseInfo(cls, urls): + for url in urls: + url = replace_patterns(url, cls.URL_REPLACEMENTS) + yield cls.getInfo(cls, url) + + + @classmethod + def getInfo(cls, url="", html=""): + info = {'name': url or _("Unknown"), 'size': 0, 'status': 3, 'url': url} + + if not html: + if url: + html = getURL(url, cookies=cls.COOKIES, decode=not cls.TEXT_ENCODING) + if isinstance(cls.TEXT_ENCODING, basestring): + html = unicode(html, cls.TEXT_ENCODING) + else: + return info + + online = False + + if hasattr(cls, "OFFLINE_PATTERN") and re.search(cls.OFFLINE_PATTERN, html): + info['status'] = 1 + + elif hasattr(cls, "TEMP_OFFLINE_PATTERN") and re.search(cls.TEMP_OFFLINE_PATTERN, html): + info['status'] = 6 + + else: + try: + info.update(re.match(cls.__pattern__, url).groupdict()) + except: + pass + + for pattern in ("INFO_PATTERN", "NAME_PATTERN", "SIZE_PATTERN"): + try: + attr = getattr(cls, pattern) + info.update(re.search(attr, html).groupdict()) + except AttributeError: + continue + else: + online = True + + if online: + info['status'] = 2 + + if 'N' in info: + info['name'] = replace_patterns(info['N'].strip(), cls.NAME_REPLACEMENTS) + + if 'S' in info: + size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'], cls.SIZE_REPLACEMENTS) + info['size'] = parseFileSize(size) + + elif isinstance(info['size'], basestring): + unit = info['units'] if 'units' in info else None + info['size'] = parseFileSize(info['size'], unit) + + return info def init(self): - self.info = {} + self.link = "" #@TODO: Move to hoster class in 0.4.10 def setup(self): @@ -231,90 +221,117 @@ class SimpleHoster(Hoster): def prepare(self): - if isinstance(self.COOKIES, list): - set_cookies(self.req.cj, self.COOKIES) + if self.CHECK_DIRECT_LINK is None: + self.CHECK_DIRECT_LINK = bool(self.account) self.req.setOption("timeout", 120) + 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.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 = self.load(self.pyfile.url, decode=not self.TEXT_ENCODING, cookies=bool(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 process(self, pyfile): - direct_link = self.prepare() + self.prepare() - if isinstance(direct_link, basestring): - self.logInfo(_("Direct download link detected")) - self.download(direct_link, ref=True, cookies=True, disposition=True) + if self.CHECK_DIRECT_LINK: + self.logDebug("Looking for direct download link...") + self.handleDirect() - elif self.html is None: - self.fail(_("No html retrieved")) + if not self.link: + self.preload() + + #@TODO: Remove in 0.4.10 + if self.html is None: + self.fail(_("No html retrieved")) + + info = self.getInfo(pyfile.url, self.html) + self._updateInfo(info) + + self.checkNameSize() - else: 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 any file information - self.getFileInfo() + self.checkStatus() if self.premium and (not self.FORCE_CHECK_TRAFFIC or self.checkTrafficLeft()): - self.logDebug("Handle as premium download") + self.logDebug("Handled 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.logDebug("Handled as free download") self.handleFree() + if self.link: + self.download(self.link, disposition=self.CONTENT_DISPOSITION) - def getDirectLink(self, url): - self.req.http.c.setopt(FOLLOWLOCATION, 0) - html = self.load(url, ref=True, decode=True) + def checkStatus(self): + status = self.info['status'] - self.req.http.c.setopt(FOLLOWLOCATION, 1) + if status is 1: + self.offline() - 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) - except: - pass + elif status is 6: + self.tempOffline() + + elif status is not 2: + self.error(_("File status: %s") % filter(lambda key, val: val == status, statusMap.iteritems())[0], + _("File info: %s") % self.info) - def getFileInfo(self): - name, size, status, url = parseFileInfo(self, html=self.html) + def checkNameSize(self): + name = self.info['name'] + size = self.info['size'] + url = self.info['url'] if name and name != url: self.pyfile.name = name else: - self.pyfile.name = self.info['name'] = urlparse(html_unescape(name)).path.split("/")[-1] + self.pyfile.name = self.info['name'] = urlparse(html_unescape(name)).path.split('/')[-1] - if status is 1: - self.offline() + if size > 0: + self.pyfile.size = size + else: + self.logError(_("File size not found")) - elif status is 6: - self.tempOffline() + self.logDebug("File name: %s" % self.pyfile.name, "File size: %s" % self.pyfile.size or _("Unknown")) - 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")) + def checkInfo(self): + self._updateInfo(self.getInfo(self.pyfile.url, self.html or "")) + self.checkNameSize() + self.checkStatus() + + + def _updateInfo(self, info) + self.logDebug(_("File info (previous): %s") % self.info) + self.info.update(info) + self.logDebug(_("File info (current): %s") % self.info) + + + def handleDirect(self): + self.link = _getDirectLink(self, self.pyfile.url) + + if self.link: + self.logInfo(_("Direct download link detected")) + + self._updateInfo(self.getInfo(self.pyfile.url)) + self.checkNameSize() - self.logDebug("FILE NAME: %s" % self.pyfile.name, "FILE SIZE: %d" % self.pyfile.size or _("Unknown")) - return self.info + else: + self.logDebug(_("Direct download link not found")) def handleFree(self): @@ -326,11 +343,10 @@ class SimpleHoster(Hoster): if m is None: self.error(_("Free download link not found")) - link = m.group(1) + self.link = m.group(1) + except Exception, e: self.fail(str(e)) - else: - self.download(link, ref=True, cookies=True, disposition=True) def handlePremium(self): @@ -342,19 +358,18 @@ class SimpleHoster(Hoster): if m is None: self.error(_("Premium download link not found")) - link = m.group(1) + self.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) + time_str = "%dh %dm" % divmod(wait_time / 60, 60) else: wait_time = 900 - time_str = _("(unknown time)") + time_str = _("(unknown time)") max_tries = 100 self.logInfo(_("Download limit reached, reconnect or wait %s") % time_str) diff --git a/pyload/plugins/internal/XFSHoster.py b/pyload/plugins/internal/XFSHoster.py index 87ddfab3f..a9fe2d0ad 100644 --- a/pyload/plugins/internal/XFSHoster.py +++ b/pyload/plugins/internal/XFSHoster.py @@ -16,7 +16,7 @@ from pyload.utils import html_unescape class XFSHoster(SimpleHoster): __name__ = "XFSHoster" __type__ = "hoster" - __version__ = "0.15" + __version__ = "0.17" __pattern__ = r'^unmatchable$' @@ -41,7 +41,7 @@ class XFSHoster(SimpleHoster): OFFLINE_PATTERN = r'>\s*\w+ (Not Found|file (was|has been) removed)' TEMP_OFFLINE_PATTERN = r'>\s*\w+ server (is in )?(maintenance|maintainance)' - WAIT_PATTERN = r'<span id="countdown_str">.*?>(\d+)</span>' + WAIT_PATTERN = r'<span id="countdown_str">.*?>(\d+)</span>|id="countdown" value=".*?(\d+).*?"' OVR_LINK_PATTERN = r'<h2>Download Link</h2>\s*<textarea[^>]*>([^<]+)' LINK_PATTERN = None #: final download url pattern @@ -71,6 +71,9 @@ class XFSHoster(SimpleHoster): pattern = r'(https?://(www\.)?([^/]*?%s|\d+\.\d+\.\d+\.\d+)(\:\d+)?(/d/|(/files)?/\d+/\w+/).+?)["\'<]' self.LINK_PATTERN = pattern % self.HOSTER_DOMAIN.replace('.', '\.') + if self.CHECK_DIRECT_LINK is None: + self.CHECK_DIRECT_LINK = bool(self.premium) + self.captcha = None self.errmsg = None self.passwords = self.getPassword().splitlines() @@ -122,8 +125,6 @@ class XFSHoster(SimpleHoster): data = self.getPostParameters() - # sleep(10) - self.req.http.c.setopt(FOLLOWLOCATION, 0) self.html = self.load(self.pyfile.url, post=data, ref=True, decode=True) @@ -266,7 +267,7 @@ class XFSHoster(SimpleHoster): self.logDebug(inputs) - if 'op' in inputs and inputs['op'] in ("download2", "download3"): + if 'op' in inputs and inputs['op'] in ("download1", "download2", "download3"): if "password" in inputs: if self.passwords: inputs['password'] = self.passwords.pop(0) |