diff options
Diffstat (limited to 'module/plugins/internal')
| -rw-r--r-- | module/plugins/internal/SimpleHoster.py | 172 | ||||
| -rw-r--r-- | module/plugins/internal/UnRar.py | 4 | ||||
| -rw-r--r-- | module/plugins/internal/XFSPAccount.py | 79 |
3 files changed, 193 insertions, 62 deletions
diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py index 20263064a..5056b22b2 100644 --- a/module/plugins/internal/SimpleHoster.py +++ b/module/plugins/internal/SimpleHoster.py @@ -23,59 +23,97 @@ from time import time from module.plugins.Hoster import Hoster from module.utils import html_unescape, fixup, parseFileSize from module.network.RequestFactory import getURL +from module.network.CookieJar import CookieJar -def reSub(string, ruleslist): +def replace_patterns(string, ruleslist): for r in ruleslist: rf, rt = r string = re.sub(rf, rt, string) #self.logDebug(rf, rt, string) return string +def set_cookies(cj, cookies): + for cookie in cookies: + if isinstance(cookie, tuple) and len(cookie) == 3: + domain, name, value = cookie + cj.setCookie(domain, name, value) + def parseHtmlTagAttrValue(attr_name, tag): m = re.search(r"%s\s*=\s*([\"']?)((?<=\")[^\"]+|(?<=')[^']+|[^\s\"'][^>\s]+)\1" % attr_name, tag) - return m.group(2) if m else '' - -def parseFileInfo(self, url = '', html = '', infomode = False): - if not html and hasattr(self, "html"): html = self.html - + return m.group(2) if m else None + +def parseHtmlForm(attr_str, html): + inputs = {} + action = None + form = re.search(r"(?P<tag><form[^>]*%s[^>]*>)(?P<content>.*?)</(form|body|html)[^>]*>" % attr_str, html, re.S | re.I) + if form: + action = parseHtmlTagAttrValue("action", form.group('tag')) + for input in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('content'), re.S | re.I): + name = parseHtmlTagAttrValue("name", input.group(1)) + if name: + value = parseHtmlTagAttrValue("value", input.group(1)) + if value is None: + inputs[name] = input.group(3) or '' + else: + inputs[name] = value + + return action, inputs + +def parseFileInfo(self, url = '', html = ''): info = {"name" : url, "size" : 0, "status" : 3} - online = False + + if hasattr(self, "pyfile"): + url = self.pyfile.url if hasattr(self, "req") and self.req.http.code == '404': info['status'] = 1 - elif hasattr(self, "FILE_OFFLINE_PATTERN") and re.search(self.FILE_OFFLINE_PATTERN, html): - # File offline - info['status'] = 1 else: - for pattern in ("FILE_INFO_PATTERN", "FILE_NAME_PATTERN", "FILE_SIZE_PATTERN"): + if not html and hasattr(self, "html"): html = self.html + if isinstance(self.SH_BROKEN_ENCODING, (str, unicode)): + html = unicode(html, self.SH_BROKEN_ENCODING) + if hasattr(self, "html"): self.html = html + + if hasattr(self, "FILE_OFFLINE_PATTERN") and re.search(self.FILE_OFFLINE_PATTERN, html): + # File offline + info['status'] = 1 + else: + online = False try: - info = dict(info, **re.search(getattr(self, pattern), html).groupdict()) - online = True - except AttributeError: - continue - - if online: - # File online, return name and size - info['status'] = 2 - if 'N' in info: - info['name'] = reSub(info['N'], self.FILE_NAME_REPLACEMENTS) - if 'S' in info: - size = reSub(info['S'] + info['U'] if 'U' in info else info['S'], self.FILE_SIZE_REPLACEMENTS) - info['size'] = parseFileSize(size) - elif isinstance(info['size'], (str, unicode)): - if 'units' in info: info['size'] += info['units'] - info['size'] = parseFileSize(info['size']) - - if infomode: - return info - else: - return info['name'], info['size'], info['status'], url + info.update(re.match(self.__pattern__, url).groupdict()) + except: + pass + + for pattern in ("FILE_INFO_PATTERN", "FILE_NAME_PATTERN", "FILE_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 + if 'N' in info: + info['name'] = replace_patterns(info['N'], self.FILE_NAME_REPLACEMENTS) + if 'S' in info: + size = replace_patterns(info['S'] + info['U'] if 'U' in info else info['S'], self.FILE_SIZE_REPLACEMENTS) + info['size'] = parseFileSize(size) + elif isinstance(info['size'], (str, unicode)): + if 'units' in info: info['size'] += info['units'] + info['size'] = parseFileSize(info['size']) + + if hasattr(self, "file_info"): + self.file_info = info + + return info['name'], info['size'], info['status'], url def create_getInfo(plugin): def getInfo(urls): for url in urls: - file_info = parseFileInfo(plugin, url, getURL(reSub(url, plugin.FILE_URL_REPLACEMENTS), \ - decode = False if plugin.HTML_BROKEN_ENCODING else True)) + cj = CookieJar(plugin.__name__) + if isinstance(plugin.SH_COOKIES, list): set_cookies(cj, plugin.SH_COOKIES) + file_info = parseFileInfo(plugin, url, getURL(replace_patterns(url, plugin.FILE_URL_REPLACEMENTS), \ + decode = not plugin.SH_BROKEN_ENCODING, cookies = cj)) yield file_info return getInfo @@ -91,7 +129,7 @@ class PluginParseError(Exception): class SimpleHoster(Hoster): __name__ = "SimpleHoster" - __version__ = "0.17" + __version__ = "0.25" __pattern__ = None __type__ = "hoster" __description__ = """Base hoster plugin""" @@ -110,16 +148,22 @@ class SimpleHoster(Hoster): FILE_NAME_REPLACEMENTS = [("&#?\w+;", fixup)] FILE_URL_REPLACEMENTS = [] - HTML_BROKEN_ENCODING = False + SH_BROKEN_ENCODING = False # Set to True or encoding name if encoding in http header is not correct + SH_COOKIES = True # or False or list of tuples [(domain, name, value)] + SH_CHECK_TRAFFIC = False # True = force check traffic left for a premium account + + def init(self): + self.file_info = {} def setup(self): - self.resumeDownload = self.multiDL = True if self.account else False + self.resumeDownload = self.multiDL = True if self.premium else False + if isinstance(self.SH_COOKIES, list): set_cookies(self.req.cj, self.SH_COOKIES) def process(self, pyfile): - pyfile.url = reSub(pyfile.url, self.FILE_URL_REPLACEMENTS) - self.html = self.load(pyfile.url, decode = False if self.HTML_BROKEN_ENCODING else True) - self.file_info = self.getFileInfo() - if self.premium: + pyfile.url = replace_patterns(pyfile.url, self.FILE_URL_REPLACEMENTS) + self.html = self.load(pyfile.url, decode = not self.SH_BROKEN_ENCODING, cookies = self.SH_COOKIES) + self.getFileInfo() + if self.premium and (not self.SH_CHECK_TRAFFIC or self.checkTrafficLeft()): self.handlePremium() else: self.handleFree() @@ -129,25 +173,26 @@ class SimpleHoster(Hoster): if hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, self.html): self.tempOffline() - file_info = parseFileInfo(self, infomode = True) - if file_info['status'] == 1: + name, size, status = parseFileInfo(self)[:3] + + if status == 1: self.offline() - elif file_info['status'] != 2: - self.logDebug(file_info) + elif status != 2: + self.logDebug(self.file_info) self.parseError('File info') - if file_info['name']: - self.pyfile.name = file_info['name'] + if name: + self.pyfile.name = name else: self.pyfile.name = html_unescape(urlparse(self.pyfile.url).path.split("/")[-1]) - if file_info['size']: - self.pyfile.size = file_info['size'] + if size: + self.pyfile.size = size else: self.logError("File size not parsed") self.logDebug("FILE NAME: %s FILE SIZE: %s" % (self.pyfile.name, self.pyfile.size)) - return file_info + return self.file_info def handleFree(self): self.fail("Free download not implemented") @@ -156,19 +201,24 @@ class SimpleHoster(Hoster): self.fail("Premium download not implemented") def parseError(self, msg): - raise PluginParseError(msg) + raise PluginParseError(msg) + + 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) + else: + wait_time = 900 + time_str = "(unknown time)" + max_tries = 100 + + self.logInfo("Download limit reached, reconnect or wait %s" % time_str) + + self.setWait(wait_time, True) + self.wait() + self.retry(max_tries = max_tries, reason="Download limit reached") def parseHtmlForm(self, attr_str): - inputs = {} - action = None - form = re.search(r"(?P<tag><form[^>]*%s[^>]*>)(?P<content>.*?)</form[^>]*>" % attr_str, self.html, re.S) - if form: - action = parseHtmlTagAttrValue("action", form.group('tag')) - for input in re.finditer(r'(<(?:input|textarea)[^>]*>)', form.group('content')): - name = parseHtmlTagAttrValue("name", input.group(1)) - if name: - inputs[name] = parseHtmlTagAttrValue("value", input.group(1)) - return action, inputs + return parseHtmlForm(attr_str, self.html) def checkTrafficLeft(self): traffic = self.account.getAccountInfo(self.user, True)["trafficleft"] diff --git a/module/plugins/internal/UnRar.py b/module/plugins/internal/UnRar.py index a315fbea3..53995a083 100644 --- a/module/plugins/internal/UnRar.py +++ b/module/plugins/internal/UnRar.py @@ -27,7 +27,7 @@ from module.plugins.internal.AbstractExtractor import AbtractExtractor, WrongPas class UnRar(AbtractExtractor): __name__ = "UnRar" - __version__ = "0.1" + __version__ = "0.11" # there are some more uncovered rar formats re_splitfile = re.compile(r"(.*)\.part(\d+)\.rar$") @@ -127,6 +127,8 @@ class UnRar(AbtractExtractor): raise WrongPassword if err.strip(): #raise error if anything is on stderr raise ArchiveError(err.strip()) + if p.returncode: + raise ArchiveError("Process terminated") if not self.files: self.password = password diff --git a/module/plugins/internal/XFSPAccount.py b/module/plugins/internal/XFSPAccount.py new file mode 100644 index 000000000..ad25ad2c8 --- /dev/null +++ b/module/plugins/internal/XFSPAccount.py @@ -0,0 +1,79 @@ +# -*- coding: utf-8 -*- + +""" + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3 of the License, + or (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. + See the GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program; if not, see <http://www.gnu.org/licenses/>. + + @author: zoidberg +""" + +import re +from time import mktime, strptime +from module.plugins.Account import Account +from module.plugins.internal.SimpleHoster import parseHtmlForm +from module.utils import parseFileSize + +class XFSPAccount(Account): + __name__ = "XFSPAccount" + __version__ = "0.05" + __type__ = "account" + __description__ = """XFileSharingPro account base""" + __author_name__ = ("zoidberg") + __author_mail__ = ("zoidberg@mujmail.cz") + + MAIN_PAGE = None + + VALID_UNTIL_PATTERN = r'>Premium account expire:</TD><TD><b>([^<]+)</b>' + TRAFFIC_LEFT_PATTERN = r'>Traffic available today:</TD><TD><b>([^<]+)</b>' + + def loadAccountInfo(self, user, req): + html = req.load(self.MAIN_PAGE + "?op=my_account", decode = True) + + validuntil = trafficleft = None + premium = True if '>Renew premium<' in html else False + + found = re.search(self.VALID_UNTIL_PATTERN, html) + if found: + premium = True + trafficleft = -1 + try: + self.logDebug(found.group(1)) + validuntil = mktime(strptime(found.group(1), "%d %B %Y")) + except Exception, e: + self.logError(e) + else: + found = re.search(self.TRAFFIC_LEFT_PATTERN, html) + if found: + trafficleft = found.group(1) + if "Unlimited" in trafficleft: + premium = True + else: + trafficleft = parseFileSize(trafficleft) / 1024 + + return ({"validuntil": validuntil, "trafficleft": trafficleft, "premium": premium}) + + def login(self, user, data, req): + html = req.load('%slogin.html' % self.MAIN_PAGE, decode = True) + + action, inputs = parseHtmlForm('name="FL"', html) + if not inputs: + inputs = {"op": "login", + "redirect": self.MAIN_PAGE} + + inputs.update({"login": user, + "password": data['password']}) + + html = req.load(self.MAIN_PAGE, post = inputs, decode = True) + + if 'Incorrect Login or Password' in html or '>Error<' in html: + self.wrongPassword()
\ No newline at end of file |