diff options
author | RaNaN <Mast3rRaNaN@hotmail.de> | 2013-03-24 17:16:34 +0100 |
---|---|---|
committer | RaNaN <Mast3rRaNaN@hotmail.de> | 2013-03-24 17:16:34 +0100 |
commit | 3ae2fbb170ad0f2bfe1ebf7f59e76d3645861f0a (patch) | |
tree | b01e2c881aaf744aaab0af613a7a26e7129f2028 /module/plugins/internal | |
parent | enter captchas on webui (diff) | |
parent | Rapidgator: fixed bug #47 (diff) | |
download | pyload-3ae2fbb170ad0f2bfe1ebf7f59e76d3645861f0a.tar.xz |
Merge remote-tracking branch 'origin/stable'
Conflicts:
module/plugins/accounts/FilesonicCom.py
module/plugins/accounts/OronCom.py
module/plugins/accounts/ShareonlineBiz.py
module/plugins/addons/UpdateManager.py
module/plugins/crypter/FilesonicComFolder.py
module/plugins/hoster/BezvadataCz.py
module/plugins/hoster/EuroshareEu.py
module/plugins/hoster/FilesonicCom.py
module/plugins/hoster/MegauploadCom.py
module/plugins/hoster/Premium4Me.py
module/plugins/hoster/YoutubeCom.py
module/plugins/internal/MultiHoster.py
module/utils.py
Diffstat (limited to 'module/plugins/internal')
-rw-r--r-- | module/plugins/internal/CaptchaService.py | 77 | ||||
-rw-r--r-- | module/plugins/internal/SimpleCrypter.py | 49 | ||||
-rw-r--r-- | module/plugins/internal/SimpleHoster.py | 98 | ||||
-rw-r--r-- | module/plugins/internal/XFSPAccount.py | 2 |
4 files changed, 174 insertions, 52 deletions
diff --git a/module/plugins/internal/CaptchaService.py b/module/plugins/internal/CaptchaService.py new file mode 100644 index 000000000..b912436a7 --- /dev/null +++ b/module/plugins/internal/CaptchaService.py @@ -0,0 +1,77 @@ +# -*- 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 + +class CaptchaService(): + __version__ = "0.02" + + def __init__(self, plugin): + self.plugin = plugin + +class ReCaptcha(): + def __init__(self, plugin): + self.plugin = plugin + + def challenge(self, id): + js = self.plugin.req.load("http://www.google.com/recaptcha/api/challenge", get={"k":id}, cookies=True) + + try: + challenge = re.search("challenge : '(.*?)',", js).group(1) + server = re.search("server : '(.*?)',", js).group(1) + except: + self.plugin.fail("recaptcha error") + result = self.result(server,challenge) + + return challenge, result + + def result(self, server, challenge): + return self.plugin.decryptCaptcha("%simage"%server, get={"c":challenge}, cookies=True, forceUser=True, imgtype="jpg") + +class AdsCaptcha(CaptchaService): + def challenge(self, src): + js = self.plugin.req.load(src, cookies=True) + + try: + challenge = re.search("challenge: '(.*?)',", js).group(1) + server = re.search("server: '(.*?)',", js).group(1) + except: + self.plugin.fail("adscaptcha error") + result = self.result(server,challenge) + + return challenge, result + + def result(self, server, challenge): + return self.plugin.decryptCaptcha("%sChallenge.aspx" % server, get={"cid": challenge, "dummy": random()}, cookies=True, imgtype="jpg") + +class SolveMedia(CaptchaService): + def __init__(self,plugin): + self.plugin = plugin + + def challenge(self, src): + html = self.plugin.req.load("http://api.solvemedia.com/papi/challenge.noscript?k=%s" % src, cookies=True) + try: + challenge = re.search(r'<input type=hidden name="adcopy_challenge" id="adcopy_challenge" value="([^"]+)">', html).group(1) + except: + self.plugin.fail("solvmedia error") + result = self.result(challenge) + + return challenge, result + + def result(self,challenge): + return self.plugin.decryptCaptcha("http://api.solvemedia.com/papi/media?c=%s" % challenge,imgtype="gif")
\ No newline at end of file diff --git a/module/plugins/internal/SimpleCrypter.py b/module/plugins/internal/SimpleCrypter.py index 69798bc0a..b8942c724 100644 --- a/module/plugins/internal/SimpleCrypter.py +++ b/module/plugins/internal/SimpleCrypter.py @@ -13,32 +13,53 @@ 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 """ -from re import findall +import re from module.plugins.Crypter import Crypter class SimpleCrypter(Crypter): __name__ = "SimpleCrypter" - __version__ = "0.01" + __version__ = "0.03" __pattern__ = None __type__ = "crypter" __description__ = """Base crypter plugin""" - __author_name__ = ("zoidberg") - __author_mail__ = ("zoidberg@mujmail.cz") + __author_name__ = ("stickell", "zoidberg") + __author_mail__ = ("l.stickell@yahoo.it", "zoidberg@mujmail.cz") + """ + These patterns should be defined by each hoster: + + LINK_PATTERN: group(1) must be a download link + example: <div class="link"><a href="(http://speedload.org/\w+) + + TITLE_PATTERN: (optional) the group defined by 'title' should be the title + example: <title>Files of: (?P<title>[^<]+) folder</title> + """ - def init(self): - self.url = self.pyfile.url - def decrypt(self, pyfile): - self.html = self.load(self.url) + self.html = self.load(pyfile.url) - new_links = [] - new_links.extend(findall(self.LINK_PATTERN, self.html)) + package_name, folder_name = self.getPackageNameAndFolder() - if new_links: - self.core.files.addLinks(new_links, self.pyfile.package().id) + package_links = re.findall(self.LINK_PATTERN, self.html) + self.logDebug('Package has %d links' % len(package_links)) + + if package_links: + self.packages = [(package_name, package_links, folder_name)] else: - self.fail('Could not extract any links')
\ No newline at end of file + self.fail('Could not extract any links') + + def getPackageNameAndFolder(self): + if hasattr(self, 'TITLE_PATTERN'): + m = re.search(self.TITLE_PATTERN, self.html) + if m: + name = folder = m.group('title') + 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 diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py index a2e246d44..666374a22 100644 --- a/module/plugins/internal/SimpleHoster.py +++ b/module/plugins/internal/SimpleHoster.py @@ -31,48 +31,65 @@ def replace_patterns(string, ruleslist): 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, re.I) + m = re.search(r"%s\s*=\s*([\"']?)((?<=\")[^\"]+|(?<=')[^']+|[^>\s\"'][^>\s]*)\1" % attr_name, tag, re.I) 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: + +def parseHtmlForm(attr_str, html, input_names=None): + for form in re.finditer(r"(?P<tag><form[^>]*%s[^>]*>)(?P<content>.*?)</?(form|body|html)[^>]*>" % attr_str, html, re.S | re.I): + inputs = {} 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)) + for inputtag in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('content'), re.S | re.I): + name = parseHtmlTagAttrValue("name", inputtag.group(1)) if name: - value = parseHtmlTagAttrValue("value", input.group(1)) + value = parseHtmlTagAttrValue("value", inputtag.group(1)) if value is None: - inputs[name] = input.group(3) or '' + inputs[name] = inputtag.group(3) or '' else: inputs[name] = value - - return action, inputs -def parseFileInfo(self, url = '', html = ''): + if isinstance(input_names, dict): + # check input attributes + for key, val in input_names.items(): + if key in inputs: + if isinstance(val, basestring) and inputs[key] == val: + continue + elif isinstance(val, tuple) and inputs[key] in val: + continue + elif hasattr(val, "search") and re.match(val, inputs[key]): + continue + break # attibute value does not match + else: + break # attibute name does not match + else: + return action, inputs # passed attribute check + else: + # no attribute check + return action, inputs + + return {}, None # no matching form found + +def parseFileInfo(self, url = '', html = ''): info = {"name" : url, "size" : 0, "status" : 3} - - if hasattr(self, "pyfile"): - url = self.pyfile.url + + if hasattr(self, "pyfile"): + url = self.pyfile.url if hasattr(self, "req") and self.req.http.code == '404': info['status'] = 1 else: if not html and hasattr(self, "html"): html = self.html - if isinstance(self.SH_BROKEN_ENCODING, (str, unicode)): + 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 @@ -82,7 +99,7 @@ def parseFileInfo(self, url = '', html = ''): 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()) @@ -129,7 +146,7 @@ class PluginParseError(Exception): class SimpleHoster(Hoster): __name__ = "SimpleHoster" - __version__ = "0.26" + __version__ = "0.28" __pattern__ = None __type__ = "hoster" __description__ = """Base hoster plugin""" @@ -147,13 +164,13 @@ class SimpleHoster(Hoster): FILE_SIZE_REPLACEMENTS = [] FILE_NAME_REPLACEMENTS = [("&#?\w+;", fixup)] FILE_URL_REPLACEMENTS = [] - + 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 = {} + self.file_info = {} def setup(self): self.resumeDownload = self.multiDL = True if self.premium else False @@ -161,6 +178,7 @@ class SimpleHoster(Hoster): def process(self, pyfile): pyfile.url = replace_patterns(pyfile.url, self.FILE_URL_REPLACEMENTS) + self.req.setOption("timeout", 120) 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()): @@ -168,13 +186,17 @@ class SimpleHoster(Hoster): else: self.handleFree() + def load(self, url, get={}, post={}, ref=True, cookies=True, just_header=False, decode=False): + if type(url) == unicode: url = url.encode('utf8') + return Hoster.load(self, url=url, get=get, post=post, ref=ref, cookies=cookies, just_header=just_header, decode=decode) + def getFileInfo(self): self.logDebug("URL: %s" % self.pyfile.url) if hasattr(self, "TEMP_OFFLINE_PATTERN") and re.search(self.TEMP_OFFLINE_PATTERN, self.html): self.tempOffline() name, size, status = parseFileInfo(self)[:3] - + if status == 1: self.offline() elif status != 2: @@ -202,26 +224,28 @@ class SimpleHoster(Hoster): def parseError(self, 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 - + 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") + self.retry(max_tries = max_tries, reason="Download limit reached") + + def parseHtmlForm(self, attr_str='', input_names=None): + return parseHtmlForm(attr_str, self.html, input_names) - def parseHtmlForm(self, attr_str): - return parseHtmlForm(attr_str, self.html) - - def checkTrafficLeft(self): + def checkTrafficLeft(self): traffic = self.account.getAccountInfo(self.user, True)["trafficleft"] + if traffic == -1: + return True size = self.pyfile.size / 1024 - self.logInfo("Filesize: %i KiB, Traffic left for user %s: %i KiB" % (size, self.user, traffic)) + self.logInfo("Filesize: %i KiB, Traffic left for user %s: %i KiB" % (size, self.user, traffic)) return size <= traffic
\ No newline at end of file diff --git a/module/plugins/internal/XFSPAccount.py b/module/plugins/internal/XFSPAccount.py index ad25ad2c8..8333c7265 100644 --- a/module/plugins/internal/XFSPAccount.py +++ b/module/plugins/internal/XFSPAccount.py @@ -33,7 +33,7 @@ class XFSPAccount(Account): MAIN_PAGE = None - VALID_UNTIL_PATTERN = r'>Premium account expire:</TD><TD><b>([^<]+)</b>' + VALID_UNTIL_PATTERN = r'>Premium.[Aa]ccount expire:</TD><TD><b>([^<]+)</b>' TRAFFIC_LEFT_PATTERN = r'>Traffic available today:</TD><TD><b>([^<]+)</b>' def loadAccountInfo(self, user, req): |