diff options
Diffstat (limited to 'module/plugins/hoster/UlozTo.py')
| -rw-r--r-- | module/plugins/hoster/UlozTo.py | 155 |
1 files changed, 88 insertions, 67 deletions
diff --git a/module/plugins/hoster/UlozTo.py b/module/plugins/hoster/UlozTo.py index 6b699e39f..cf2f09311 100644 --- a/module/plugins/hoster/UlozTo.py +++ b/module/plugins/hoster/UlozTo.py @@ -21,116 +21,137 @@ from module.plugins.internal.SimpleHoster import SimpleHoster, create_getInfo def convertDecimalPrefix(m): # decimal prefixes used in filesize and traffic - return ("%%.%df" % {'k':3,'M':6,'G':9}[m.group(2)] % float(m.group(1))).replace('.','') + return ("%%.%df" % {'k':3,'M':6,'G':9}[m.group(2)] % float(m.group(1))).replace('.','') class UlozTo(SimpleHoster): __name__ = "UlozTo" __type__ = "hoster" - __pattern__ = r"http://(\w*\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/.*" - __version__ = "0.81" + __pattern__ = r"http://(\w*\.)?(uloz\.to|ulozto\.(cz|sk|net)|bagruj.cz|zachowajto.pl)/(?:live/)?(?P<id>\w+/[^/?]*)" + __version__ = "0.89" __description__ = """uloz.to""" __author_name__ = ("zoidberg") - FILE_NAME_PATTERN = r'<a share_url="[^&]*&t=(?P<N>[^"]+)"' - #FILE_NAME_PATTERN = r'<h2 class="nadpis" style="margin-left:196px;"><a href="[^"]+">(?P<N>[^<]+)</a></h2>' - FILE_SIZE_PATTERN = r'<div class="info_velikost" style="top:-55px;">\s*<div>[^<]*\s+(?P<S>[0-9.]+\s[kMG]B)\s*</div>\s*</div>' - FILE_SIZE_REPLACEMENTS = [('([0-9.]+)\s([kMG])B', convertDecimalPrefix)] - FILE_OFFLINE_PATTERN = r'http://www.uloz.to/(neexistujici|smazano|nenalezeno)' - - PASSWD_PATTERN = r'<input type="password" class="text" name="file_password" id="frmfilepasswordForm-file_password" />' - VIPLINK_PATTERN = r'<a href="[^"]*\?disclaimer=1" class="linkVip">' - FREE_URL_PATTERN = r'<form name="dwn" action="([^"]+)"' - PREMIUM_URL_PATTERN = r'<a onclick[^>]*href="([^"]+)[^>]*class="linkVip"' - CAPTCHA_PATTERN = r'<img style=".*src="([^"]+)" alt="Captcha" class="captcha"' - CAPTCHA_NB_PATTERN = r'<input class="captcha_nb" type="hidden" name="captcha_nb" value="([0-9]+)" >' + FILE_NAME_PATTERN = r'<a href="#download" class="jsShowDownload">(?P<N>[^<]+)</a>' + FILE_SIZE_PATTERN = r'<span id="fileSize">.*?(?P<S>[0-9.]+\s[kMG]B)</span>' + FILE_INFO_PATTERN = r'<p>File <strong>(?P<N>[^<]+)</strong> is password protected</p>' + FILE_OFFLINE_PATTERN = r'<title>404 - Page not found</title>|<h1 class="h1">File (has been deleted|was banned)</h1>' + FILE_SIZE_REPLACEMENTS = [('([0-9.]+)\s([kMG])B', convertDecimalPrefix)] + FILE_URL_REPLACEMENTS = [(r"(?<=http://)([^/]+)", "www.ulozto.net")] + + PASSWD_PATTERN = r'<div class="passwordProtectedFile">' + VIPLINK_PATTERN = r'<a href="[^"]*\?disclaimer=1" class="linkVip">' + FREE_URL_PATTERN = r'<div class="freeDownloadForm"><form action="([^"]+)"' + PREMIUM_URL_PATTERN = r'<div class="downloadForm"><form action="([^"]+)"' + + def setup(self): + self.multiDL = self.premium + self.resumeDownload = True def process(self, pyfile): - # check file online - header = self.load(pyfile.url, just_header=True) - if "location" in header: - self.logDebug('LOCATION: ' + header['location']) - if "utm_source=old" in header['location'] or re.search(self.FILE_OFFLINE_PATTERN, header['location']): - self.offline() - - self.html = self.load(pyfile.url, decode=True) - - # password protected links - passwords = self.getPassword().splitlines() + pyfile.url = re.sub(r"(?<=http://)([^/]+)", "www.ulozto.net", pyfile.url) + self.html = self.load(pyfile.url, decode = True, cookies = True) + + passwords = self.getPassword().splitlines() while self.PASSWD_PATTERN in self.html: if passwords: password = passwords.pop(0) self.logInfo("Password protected link, trying " + password) - self.html = self.load(pyfile.url, get = {"do": "filepasswordForm-submit"}, post={"file_password": password, "fpwdsend": 'Odeslat'}, cookies=True) + self.html = self.load(pyfile.url, get = {"do": "passwordProtectedForm-submit"}, + post={"password": password, "password_send": 'Send'}, cookies=True) else: self.fail("No or incorrect password") - - self.file_info = self.getFileInfo() - - # adult content + if re.search(self.VIPLINK_PATTERN, self.html): self.html = self.load(pyfile.url, get={"disclaimer": "1"}) - + + self.file_info = self.getFileInfo() + if self.premium and self.checkTrafficLeft(): self.handlePremium() - else: + else: self.handleFree() - def handleFree(self): - parsed_url = self.findDownloadURL(premium=False) + self.doCheckDownload() + def handleFree(self): + action, inputs = self.parseHtmlForm('id="frm-downloadDialog-freeDownloadForm"') + if not action or not inputs: + self.parseError("free download form") + # get and decrypt captcha - captcha = self.getStorage("captchaUser") - captcha_nb = self.getStorage("captchaNb") - captcha_url = "DUMMY" - - if not captcha or not captcha_nb: - found = re.search(self.CAPTCHA_PATTERN, self.html) - if not found: self.parseError("CAPTCHA") - captcha_url = found.group(1) - - found = re.search(self.CAPTCHA_NB_PATTERN, self.html) - if not found: self.parseError("CAPTCHA_NB") - captcha_nb = found.group(1) - - captcha = self.decryptCaptcha(captcha_url) + captcha_id_field = captcha_text_field = None + captcha_id = captcha_text = None - self.log.debug('CAPTCHA_URL:' + captcha_url + ' CAPTCHA:' + captcha + ' CAPTCHA_NB:' + captcha_nb) + for key in inputs.keys(): + found = re.match("captcha.*(id|text|value)", key) + if found: + if found.group(1) == "id": + captcha_id_field = key + else: + captcha_text_field = key + + if not captcha_id_field or not captcha_text_field: + self.parseError("CAPTCHA form changed") + + """ + captcha_id = self.getStorage("captcha_id") + captcha_text = self.getStorage("captcha_text") + + if not captcha_id or not captcha_text: + """ + captcha_id = inputs[captcha_id_field] + captcha_text = self.decryptCaptcha("http://img.uloz.to/captcha/%s.png" % captcha_id) - # download and check - self.download(parsed_url, post={"captcha_user": captcha, "captcha_nb": captcha_nb}, cookies=True) - self.doCheckDownload() + self.log.debug(' CAPTCHA ID:' + captcha_id + ' CAPTCHA TEXT:' + captcha_text) - self.setStorage("captchaUser", captcha) - self.setStorage("captchaNb", captcha_nb) - - def handlePremium(self): - parsed_url = self.findDownloadURL(premium=True) - self.download(parsed_url) - self.doCheckDownload() + """ + self.setStorage("captcha_id", captcha_id) + self.setStorage("captcha_text", captcha_text) + """ + self.multiDL = True + + inputs.update({captcha_id_field: captcha_id, captcha_text_field: captcha_text}) + self.download("http://www.ulozto.net" + action, post=inputs, cookies=True) + + def handlePremium(self): + self.download(self.pyfile.url + "?do=directDownload") + #parsed_url = self.findDownloadURL(premium=True) + #self.download(parsed_url, post={"download": "Download"}) + def findDownloadURL(self, premium=False): msg = "%s link" % ("Premium" if premium else "Free") found = re.search(self.PREMIUM_URL_PATTERN if premium else self.FREE_URL_PATTERN, self.html) if not found: self.parseError(msg) - parsed_url = found.group(1) + parsed_url = "http://www.ulozto.net" + found.group(1) self.logDebug("%s: %s" % (msg, parsed_url)) return parsed_url - + def doCheckDownload(self): check = self.checkDownload({ - "wrong_captcha": re.compile(self.CAPTCHA_PATTERN), + "wrong_captcha": re.compile(r'<ul class="error">\s*<li>Error rewriting the text.</li>'), "offline": re.compile(self.FILE_OFFLINE_PATTERN), - "passwd": self.PASSWD_PATTERN + "passwd": self.PASSWD_PATTERN, + "server_error": 'src="http://img.ulozto.cz/error403/vykricnik.jpg"', #paralell dl, server overload etc. + "not_found": "<title>Ulož.to</title>" }) if check == "wrong_captcha": - self.delStorage("captchaUser") - self.delStorage("captchaNb") + self.delStorage("captcha_id") + self.delStorage("captcha_text") self.invalidCaptcha() self.retry(reason="Wrong captcha code") elif check == "offline": self.offline() elif check == "passwd": self.fail("Wrong password") + elif check == "server_error": + self.logError("Server error, try downloading later") + self.multiDL = False + self.setWait(3600, True) + self.wait() + self.retry() + elif check == "not_found": + self.fail("Server error - file not downloadable") -getInfo = create_getInfo(UlozTo)
\ No newline at end of file +getInfo = create_getInfo(UlozTo)
\ No newline at end of file |