diff options
Diffstat (limited to 'module/plugins/internal/SimpleCrypter.py')
| -rw-r--r-- | module/plugins/internal/SimpleCrypter.py | 77 |
1 files changed, 41 insertions, 36 deletions
diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py index 5115692ad..dc34f864f 100644 --- a/module/plugins/internal/SimpleCrypter.py +++ b/module/plugins/internal/SimpleCrypter.py @@ -2,7 +2,7 @@ import re -from urlparse import urlparse +from urlparse import urljoin, urlparse from pyload.plugin.Crypter import Crypter from pyload.plugin.internal.SimpleHoster import SimpleHoster, create_getInfo, replace_patterns, set_cookies @@ -12,7 +12,7 @@ from pyload.utils import fixup class SimpleCrypter(Crypter, SimpleHoster): __name__ = "SimpleCrypter" __type__ = "crypter" - __version__ = "0.32" + __version__ = "0.43" __pattern__ = r'^unmatchable$' __config__ = [("use_subfolder", "bool", "Save package to subfolder", True), #: Overrides core.config['general']['folder_per_package'] @@ -28,16 +28,16 @@ class SimpleCrypter(Crypter, SimpleHoster): """ Following patterns should be defined by each crypter: - LINK_PATTERN: group(1) must be a download link or a regex to catch more links + LINK_PATTERN: Download link or regex to catch links in group(1) example: LINK_PATTERN = r'<div class="link"><a href="(.+?)"' - NAME_PATTERN: (optional) folder name or webpage title + NAME_PATTERN: (optional) folder name or page title example: NAME_PATTERN = r'<title>Files of: (?P<N>[^<]+) folder</title>' - OFFLINE_PATTERN: (optional) Checks if the file is yet available online + OFFLINE_PATTERN: (optional) Checks if the page is unreachable example: OFFLINE_PATTERN = r'File (deleted|not found)' - TEMP_OFFLINE_PATTERN: (optional) Checks if the file is temporarily offline + TEMP_OFFLINE_PATTERN: (optional) Checks if the page is temporarily unreachable example: TEMP_OFFLINE_PATTERN = r'Server maintainance' @@ -69,15 +69,18 @@ class SimpleCrypter(Crypter, SimpleHoster): def prepare(self): - self.info = {} - self.links = [] + self.pyfile.error = "" #@TODO: Remove in 0.4.10 - if self.LOGIN_ACCOUNT and not self.account: - self.fail(_("Required account not found")) + self.info = {} + self.html = "" + self.links = [] #@TODO: Move to hoster class in 0.4.10 if self.LOGIN_PREMIUM and not self.premium: self.fail(_("Required premium account not found")) + if self.LOGIN_ACCOUNT and not self.account: + self.fail(_("Required account not found")) + self.req.setOption("timeout", 120) if isinstance(self.COOKIES, list): @@ -90,46 +93,45 @@ class SimpleCrypter(Crypter, SimpleHoster): self.prepare() self.preload() - - if self.html is None: - self.fail(_("No html retrieved")) - self.checkInfo() self.links = self.getLinks() if hasattr(self, 'PAGES_PATTERN') and hasattr(self, 'loadPage'): - self.handleMultiPages() + self.handlePages(pyfile) self.logDebug("Package has %d links" % len(self.links)) if self.links: self.packages = [(self.info['name'], self.links, self.info['folder'])] + elif not self.urls and not self.packages: #@TODO: Remove in 0.4.10 + self.fail(_("No link grabbed")) - def checkStatus(self): - status = self.info['status'] - - if status is 1: - self.offline() - elif status is 6: - self.tempOffline() + def checkNameSize(self, getinfo=True): + if not self.info or getinfo: + self.logDebug("File info (BEFORE): %s" % self.info) + self.info.update(self.getInfo(self.pyfile.url, self.html)) + self.logDebug("File info (AFTER): %s" % self.info) + try: + url = self.info['url'].strip() + name = self.info['name'].strip() + if name and name != url: + self.pyfile.name = name - def checkNameSize(self): - name = self.info['name'] - url = self.info['url'] + except Exception: + pass - if name and name != url: - self.pyfile.name = name - else: - self.pyfile.name = name = self.info['name'] = urlparse(name).path.split('/')[-1] + try: + folder = self.info['folder'] = self.pyfile.name - folder = self.info['folder'] = name + except Exception: + pass - self.logDebug("File name: %s" % name, - "File folder: %s" % folder) + self.logDebug("File name: %s" % self.pyfile.name, + "File folder: %s" % self.pyfile.name) def getLinks(self): @@ -137,13 +139,16 @@ class SimpleCrypter(Crypter, SimpleHoster): Returns the links extracted from self.html You should override this only if it's impossible to extract links using only the LINK_PATTERN. """ - return re.findall(self.LINK_PATTERN, self.html) + url_p = urlparse(self.pyfile.url) + baseurl = "%s://%s" % (url_p.scheme, url_p.netloc) + + return [urljoin(baseurl, link) if not urlparse(link).scheme else link \ + for link in re.findall(self.LINK_PATTERN, self.html)] - def handleMultiPages(self): + def handlePages(self, pyfile): try: - m = re.search(self.PAGES_PATTERN, self.html) - pages = int(m.group(1)) + pages = int(re.search(self.PAGES_PATTERN, self.html).group(1)) except Exception: pages = 1 |