diff options
author | zoidberg10 <zoidberg@mujmail.cz> | 2011-09-20 17:10:52 +0200 |
---|---|---|
committer | zoidberg10 <zoidberg@mujmail.cz> | 2011-09-20 17:10:52 +0200 |
commit | 924b9e2e7e0d651662b4bd00936b7f4675e7947f (patch) | |
tree | 8b723b917a95fbb0ab26253e32cdd963cc7f5c44 /module/plugins/hoster/CzshareCom.py | |
parent | general JSON API, url parser (diff) | |
download | pyload-924b9e2e7e0d651662b4bd00936b7f4675e7947f.tar.xz |
New plugins: HellspyCz, LetitbitNet, FreevideoCz, StreamCz, UlozToFolder
Diffstat (limited to 'module/plugins/hoster/CzshareCom.py')
-rw-r--r-- | module/plugins/hoster/CzshareCom.py | 122 |
1 files changed, 38 insertions, 84 deletions
diff --git a/module/plugins/hoster/CzshareCom.py b/module/plugins/hoster/CzshareCom.py index 8cab02317..74c582dae 100644 --- a/module/plugins/hoster/CzshareCom.py +++ b/module/plugins/hoster/CzshareCom.py @@ -24,6 +24,7 @@ def getInfo(urls): result = [] for url in urls: + html = getURL(url, decode=True) if re.search(CzshareCom.FILE_OFFLINE_PATTERN, html): # File offline @@ -33,36 +34,40 @@ def getInfo(urls): found = re.search(CzshareCom.FILE_NAME_PATTERN, html) if found is not None: name = found.group(1) - result.append((name, 0, 2, url)) + + found = re.search(CzshareCom.FILE_SIZE_PATTERN, html) + if found is not None: + size = float(found.group(1).replace(',','.')) + units = found.group(2) + pow = {'KiB': 1, 'MiB': 2, 'GiB': 3}[units] + size = int(size * 1024 ** pow) + result.append((name, size, 2, url)) + else: + result.append((name, 0, 2, url)) yield result - class CzshareCom(Hoster): __name__ = "CzshareCom" __type__ = "hoster" - __pattern__ = r"http://.*czshare\.(com|cz)/.*" - __version__ = "0.6" + __pattern__ = r"http://(\w*\.)*czshare\.(com|cz)/.*" + __version__ = "0.7" __description__ = """CZshare.com""" __author_name__ = ("zoidberg") + __author_mail__ = ("zoidberg@mujmail.cz") - #FILE_URL_PATTERN = r'<a href="http://czshare.com/([^/]+)/([^/]+)/[^"]*">([^<]+)</a>' FILE_URL_PATTERN = r'<a href="([^"]+)" class="page-download">[^>]*alt="([^"]+)" /></a>' - FORM_PATTERN = r'<form action="download.php" method="post">' - ID_PATTERN = r'<input type="hidden" name="id" value="([^"]+)" />' - FILE_PATTERN = r'<input type="hidden" name="file" value="([^"]+)" />' - #TICKET_PATTERN = r'<input type="hidden" name="ticket" value="([^"]+)" />' - SUBMIT_PATTERN = r'<input type="submit" name="freedown" value="([^"]+)" class="button" />' - SIZE_PATTERN = r'<input type="hidden" name="size" value="([^"]+)" />' - SERVER_PATTERN = r'<input type="hidden" name="server" value="([^"]+)" />' - FILE_OFFLINE_PATTERN = r'<h2 class="red">Soubor nenalezen<span> </span></h2>' + FORM_PATTERN = r'<form action="download.php" method="post">\s*<img src="captcha.php" id="captcha" />(.*?)</form>' + FORM_INPUT_PATTERN = r'<input[^>]* name="([^"]+)" value="([^"]+)"[^>]*/>' + FILE_OFFLINE_PATTERN = r'<h2 class="red">[^<]*[Ss]oubor (nenalezen|expiroval|je po.kozen)[^<]*<span> </span></h2>' MULTIDL_PATTERN = r"<p><font color='red'>Z[^<]*PROFI.</font></p>" FILE_NAME_PATTERN = r'<h1>([^<]+)<span> </span></h1>' + FILE_SIZE_PATTERN = r'<div class="tab" id="category">\s*Velikost:\s*([0-9.,]+)(KiB|MiB|GiB)\s*</div>' def setup(self): self.multiDL = False def process(self, pyfile): - self.html = self.load(pyfile.url, decode=True) + self.html = self.load(pyfile.url, cookies=True, decode=True) #marks the file as "offline" when the pattern was found on the html-page if re.search(self.FILE_OFFLINE_PATTERN, self.html) is not None: @@ -71,93 +76,42 @@ class CzshareCom(Hoster): # parse the name from the site and set attribute in pyfile found = re.search(self.FILE_URL_PATTERN, self.html) if found is None: - self.fail("Parse error (URL)") + self.fail("Parse error (URL)") pyfile.name = found.group(2) parsed_url = "http://czshare.com" + found.group(1) - # get download ticket and parse html + # get download ticket and parse html self.logDebug("PARSED_URL:" + parsed_url) self.logDebug("NAME:" + pyfile.name) - self.html = self.load(parsed_url) + self.html = self.load(parsed_url, cookies=True) #if not re.search(self.FORM_PATTERN, self.html): if re.search(self.MULTIDL_PATTERN, self.html): - self.waitForFreeSlot() - - parse_err = False - - found = re.search(self.SERVER_PATTERN, self.html) - if found is None: - parse_err = True - server = "" - else: - server = found.group(1) - - found = re.search(self.ID_PATTERN, self.html) - if found is None: - parse_err = True - file_id = "" - else: - file_id = found.group(1) - - found = re.search(self.FILE_PATTERN, self.html) - if found is None: - parse_err = True - long_id = "" - else: - long_id = found.group(1) - - found = re.search(self.SIZE_PATTERN, self.html) - if found is None: - parse_err = True - size = "" - else: - size = found.group(1) - - self.logDebug("ID:" + file_id + " F:" + long_id + " B:" + size + " S:" + server) - - if parse_err: - self.fail("Parse error") - - found = re.search(self.SUBMIT_PATTERN, self.html) - if found is None: - self.fail("Parse error (SUBMIT)") - else: - submit = found.group(1) - - # get and decrypt captcha + self.waitForFreeSlot() + + try: + form = re.search(self.FORM_PATTERN, self.html, re.DOTALL).group(1) + inputs = dict(re.findall(self.FORM_INPUT_PATTERN, form)) + pyfile.size = float(inputs['size'])/1024 + except Exception, e: + self.logError(e) + self.fail("Parse error (FORM)") + + # get and decrypt captcha captcha_url = 'http://czshare.com/captcha.php' - """ - if self.getConfig("randomCaptcha") == True: - captcha = ''.join(random.choice('abcdefghijklmnopqrstuvwxyz') for i in range(5)) - else: - """ - captcha = self.decryptCaptcha(captcha_url) - self.logDebug('CAPTCHA_URL:' + captcha_url + ' CAPTCHA:' + captcha) - - """ - self.setWait(self.getConfig("multiWait"), True) - self.wait() - """ + inputs['captchastring2'] = self.decryptCaptcha(captcha_url) + self.logDebug('CAPTCHA_URL:' + captcha_url + ' CAPTCHA:' + inputs['captchastring2']) # download the file, destination is determined by pyLoad - #download_url = 'http://czshare.com/free.php' - self.download(parsed_url, post={ - "id": file_id, - "file": long_id, - "size": size, - "server": server, - "captchastring2": captcha, - "freedown": submit - }) + self.download(parsed_url, cookies=True, post=inputs) # check download check = self.checkDownload({ "tempoffline": re.compile(r"^Soubor je do.asn. nedostupn.$"), "multi_dl": re.compile(self.MULTIDL_PATTERN), - "captcha_err": re.compile(self.SUBMIT_PATTERN) - }) + "captcha_err": re.compile(self.FORM_PATTERN) + }) if check == "tempoffline": self.fail("File not available - try later") |