summaryrefslogtreecommitdiffstats
path: root/module/plugins/internal/SimpleCrypter.py
diff options
context:
space:
mode:
Diffstat (limited to 'module/plugins/internal/SimpleCrypter.py')
-rw-r--r--module/plugins/internal/SimpleCrypter.py190
1 files changed, 121 insertions, 69 deletions
diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py
index dc93bef4d..b2622b5e0 100644
--- a/module/plugins/internal/SimpleCrypter.py
+++ b/module/plugins/internal/SimpleCrypter.py
@@ -2,117 +2,169 @@
import re
+from urlparse import urljoin, urlparse
+
from module.plugins.Crypter import Crypter
-from module.utils import html_unescape
-from module.plugins.internal.SimpleHoster import PluginParseError, replace_patterns, set_cookies
+from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo, replace_patterns, set_cookies
+from module.utils import fixup
-class SimpleCrypter(Crypter):
- __name__ = "SimpleCrypter"
- __version__ = "0.10"
- __type__ = "crypter"
+class SimpleCrypter(Crypter, SimpleHoster):
+ __name__ = "SimpleCrypter"
+ __type__ = "crypter"
+ __version__ = "0.42"
- __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"""
- __author_name__ = ("stickell", "zoidberg", "Walter Purcaro")
- __author_mail__ = ("l.stickell@yahoo.it", "zoidberg@mujmail.cz", "vuolter@gmail.com")
+ __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="(http://speedload.org/\w+)'
+ LINK_PATTERN: Download link or regex to catch links in group(1)
+ example: LINK_PATTERN = r'<div class="link"><a href="(.+?)"'
- TITLE_PATTERN: (optional) The group defined by 'title' should be the title
- example: TITLE_PATTERN = r'<title>Files of: (?P<title>[^<]+) folder</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'
- If it's impossible to extract the links using the LINK_PATTERN only you can override the getLinks method.
+ 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:
- If the links are disposed on multiple pages you need to define a pattern:
+ PAGES_PATTERN: (optional) group(1) should be the number of overall pages containing the links
+ example: PAGES_PATTERN = r'Pages: (\d+)'
- PAGES_PATTERN: The group defined by 'pages' must be the total number of pages
- example: PAGES_PATTERN = r'Pages: (?P<pages>\d+)'
+ and its loadPage method:
- and a function:
- loadPage(self, page_n):
- return the html of the page number 'page_n'
+ def loadPage(self, page_n):
+ return the html of the page number page_n
"""
- URL_REPLACEMENTS = []
+ LINK_PATTERN = None
- SH_COOKIES = True # or False or list of tuples [(domain, name, value)]
+ 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)]
- def setup(self):
- if isinstance(self.SH_COOKIES, list):
- set_cookies(self.req.cj, self.SH_COOKIES)
+ LOGIN_ACCOUNT = False
+ LOGIN_PREMIUM = False
- def decrypt(self, pyfile):
- pyfile.url = replace_patterns(pyfile.url, self.URL_REPLACEMENTS)
- self.html = self.load(pyfile.url, decode=True)
+ #@TODO: Remove in 0.4.10
+ def init(self):
+ account_name = (self.__name__ + ".py").replace("Folder.py", "").replace(".py", "")
+ account = self.pyfile.m.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):
+ self.pyfile.error = "" #@TODO: Remove in 0.4.10
+
+ 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):
+ set_cookies(self.req.cj, self.COOKIES)
+
+ self.pyfile.url = replace_patterns(self.pyfile.url, self.URL_REPLACEMENTS)
- self.checkOnline()
- package_name, folder_name = self.getPackageNameAndFolder()
+ def decrypt(self, pyfile):
+ self.prepare()
+
+ self.preload()
+ self.checkInfo()
- self.package_links = self.getLinks()
+ 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 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']
+ name = self.info['name']
+ if name and name != url:
+ self.pyfile.name = name
- self.logDebug('Package has %d links' % len(self.package_links))
+ except Exception:
+ pass
+
+ try:
+ folder = self.info['folder'] = self.pyfile.name
+
+ except Exception:
+ pass
+
+ self.logDebug("File name: %s" % self.pyfile.name,
+ "File folder: %s" % self.pyfile.name)
- 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:
+ 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 handlePages(self, pyfile):
+ try:
+ pages = int(re.search(self.PAGES_PATTERN, self.html).group(1))
+ except Exception:
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)
+ self.links += self.getLinks()
generated by cgit v1.2.3 (git 2.25.1) at 2025-02-01 03:02:36 +0100