diff options
Diffstat (limited to 'module/plugins/crypter/UlozToFolder.py')
| -rw-r--r-- | module/plugins/crypter/UlozToFolder.py | 42 |
1 files changed, 23 insertions, 19 deletions
diff --git a/module/plugins/crypter/UlozToFolder.py b/module/plugins/crypter/UlozToFolder.py index eebb14497..a1f3ed5ea 100644 --- a/module/plugins/crypter/UlozToFolder.py +++ b/module/plugins/crypter/UlozToFolder.py @@ -5,38 +5,42 @@ from module.plugins.Crypter import Crypter class UlozToFolder(Crypter): - __name__ = "UlozToFolder" - __type__ = "crypter" - __pattern__ = r'http://(?:www\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/(m|soubory)/.*' - __version__ = "0.2" + __name__ = "UlozToFolder" + __type__ = "crypter" + __version__ = "0.20" + + __pattern__ = r'http://(?:www\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj\.cz|zachowajto\.pl)/(m|soubory)/.+' + __config__ = [("use_subfolder", "bool", "Save package to subfolder", True), + ("subfolder_per_package", "bool", "Create a subfolder for each package", True)] + __description__ = """Uloz.to folder decrypter plugin""" - __author_name__ = "zoidberg" - __author_mail__ = "zoidberg@mujmail.cz" + __license__ = "GPLv3" + __authors__ = [("zoidberg", "zoidberg@mujmail.cz")] + FOLDER_PATTERN = r'<ul class="profile_files">(.*?)</ul>' LINK_PATTERN = r'<br /><a href="/([^"]+)">[^<]+</a>' NEXT_PAGE_PATTERN = r'<a class="next " href="/([^"]+)"> </a>' + def decrypt(self, pyfile): html = self.load(pyfile.url) new_links = [] for i in xrange(1, 100): - self.logInfo("Fetching links from page %i" % i) - found = re.search(self.FOLDER_PATTERN, html, re.DOTALL) - if found is None: - self.fail("Parse error (FOLDER)") - - new_links.extend(re.findall(self.LINK_PATTERN, found.group(1))) - found = re.search(self.NEXT_PAGE_PATTERN, html) - if found: - html = self.load("http://ulozto.net/" + found.group(1)) + self.logInfo(_("Fetching links from page %i") % i) + m = re.search(self.FOLDER_PATTERN, html, re.S) + if m is None: + self.error(_("FOLDER_PATTERN not found")) + + new_links.extend(re.findall(self.LINK_PATTERN, m.group(1))) + m = re.search(self.NEXT_PAGE_PATTERN, html) + if m: + html = self.load("http://ulozto.net/" + m.group(1)) else: break else: - self.logInfo("Limit of 99 pages reached, aborting") + self.logInfo(_("Limit of 99 pages reached, aborting")) if new_links: - self.core.files.addLinks(map(lambda s: "http://ulozto.net/%s" % s, new_links), pyfile.package().id) - else: - self.fail('Could not extract any links') + self.urls = [map(lambda s: "http://ulozto.net/%s" % s, new_links)] |