diff options
Diffstat (limited to 'pyload/plugins/internal/SimpleCrypter.py')
| -rw-r--r-- | pyload/plugins/internal/SimpleCrypter.py | 43 |
1 files changed, 25 insertions, 18 deletions
diff --git a/pyload/plugins/internal/SimpleCrypter.py b/pyload/plugins/internal/SimpleCrypter.py index 454a95e84..6c5c9593f 100644 --- a/pyload/plugins/internal/SimpleCrypter.py +++ b/pyload/plugins/internal/SimpleCrypter.py @@ -2,30 +2,32 @@ import re -from pyload.plugins.base.Crypter import Crypter +from pyload.plugins.Crypter import Crypter from pyload.plugins.internal.SimpleHoster import PluginParseError, replace_patterns, set_cookies -from pyload.utils import html_unescape +from pyload.utils import fixup, html_unescape class SimpleCrypter(Crypter): __name__ = "SimpleCrypter" __type__ = "crypter" - __version__ = "0.12" + __version__ = "0.13" __pattern__ = None __description__ = """Simple decrypter plugin""" - __author_name__ = ("stickell", "zoidberg", "Walter Purcaro") - __author_mail__ = ("l.stickell@yahoo.it", "zoidberg@mujmail.cz", "vuolter@gmail.com") + __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+)' + example: LINK_PATTERN = r'<div class="link"><a href="(.+?)"' - TITLE_PATTERN: (optional) The group defined by 'title' should be the folder name or the webpage title - example: TITLE_PATTERN = r'<title>Files of: (?P<title>[^<]+) folder</title>' + TITLE_PATTERN: (optional) group(1) should be the folder name or the webpage title + example: TITLE_PATTERN = r'<title>Files of: ([^<]+) folder</title>' OFFLINE_PATTERN: (optional) Checks if the file is yet available online example: OFFLINE_PATTERN = r'File (deleted|not found)' @@ -39,8 +41,8 @@ class SimpleCrypter(Crypter): If the links are splitted on multiple pages you can define the PAGES_PATTERN regex: - PAGES_PATTERN: (optional) The group defined by 'pages' should be the number of overall pages containing the links - example: PAGES_PATTERN = r'Pages: (?P<pages>\d+)' + 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: @@ -48,7 +50,7 @@ class SimpleCrypter(Crypter): return the html of the page number page_n """ - + TITLE_REPLACEMENTS = [("&#?\w+;", fixup)] URL_REPLACEMENTS = [] TEXT_ENCODING = False #: Set to True or encoding name if encoding in http header is not correct @@ -110,23 +112,28 @@ class SimpleCrypter(Crypter): 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()) + 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 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: + try: + m = re.search(self.PAGES_PATTERN, self.html) + pages = int(m.group(1)) + except: pages = 1 for p in xrange(2, pages + 1): |