SimpleHoster: new PREMIUM_ONLY_PATTERN (see #350).

+ cosmetics

1 files changed, 48 insertions, 26 deletions

diff --git a/module/plugins/internal/SimpleHoster.py b/module/plugins/internal/SimpleHoster.py
index 53f2e9f19..856d3fde6 100644
--- a/module/plugins/internal/SimpleHoster.py
+++ b/module/plugins/internal/SimpleHoster.py
@@ -25,6 +25,7 @@ from module.utils import html_unescape, fixup, parseFileSize
 from module.network.RequestFactory import getURL
 from module.network.CookieJar import CookieJar
 
+
 def replace_patterns(string, ruleslist):
     for r in ruleslist:
         rf, rt = r
@@ -32,18 +33,22 @@ def replace_patterns(string, ruleslist):
         #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)
-        return m.group(2) if m else None
+    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, 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):
+    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 inputtag in re.finditer(r'(<(input|textarea)[^>]*>)([^<]*(?=</\2)|)', form.group('content'), re.S | re.I):
@@ -65,19 +70,20 @@ def parseHtmlForm(attr_str, html, input_names=None):
                         continue
                     elif hasattr(val, "search") and re.match(val, inputs[key]):
                         continue
-                    break # attibute value does not match
+                    break  # attibute value does not match
                 else:
-                    break # attibute name does not match
+                    break  # attibute name does not match
             else:
-                return action, inputs # passed attribute check
+                return action, inputs  # passed attribute check
         else:
             # no attribute check
             return action, inputs
 
-    return {}, None # no matching form found
+    return {}, None  # no matching form found
+
 
-def parseFileInfo(self, url = '', html = ''):
-    info = {"name" : url, "size" : 0, "status" : 3}
+def parseFileInfo(self, url='', html=''):
+    info = {"name": url, "size": 0, "status": 3}
 
     if hasattr(self, "pyfile"):
         url = self.pyfile.url
@@ -85,10 +91,12 @@ def parseFileInfo(self, url = '', html = ''):
     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 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, "html"):
+                self.html = html
 
         if hasattr(self, "FILE_OFFLINE_PATTERN") and re.search(self.FILE_OFFLINE_PATTERN, html):
             # File offline
@@ -113,10 +121,12 @@ def parseFileInfo(self, url = '', html = ''):
                 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)
+                    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']
+                    if 'units' in info:
+                        info['size'] += info['units']
                     info['size'] = parseFileSize(info['size'])
 
     if hasattr(self, "file_info"):
@@ -124,34 +134,41 @@ def parseFileInfo(self, url = '', html = ''):
 
     return info['name'], info['size'], info['status'], url
 
+
 def create_getInfo(plugin):
     def getInfo(urls):
         for url in urls:
             cj = CookieJar(plugin.__name__)
-            if isinstance(plugin.SH_COOKIES, list): set_cookies(cj, plugin.SH_COOKIES)
+            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))
+                                                          decode=not plugin.SH_BROKEN_ENCODING, cookies=cj))
             yield file_info
+
     return getInfo
 
+
 def timestamp():
-    return int(time()*1000)
+    return int(time() * 1000)
+
 
 class PluginParseError(Exception):
     def __init__(self, msg):
         Exception.__init__(self)
         self.value = 'Parse error (%s) - plugin may be out of date' % msg
+
     def __str__(self):
         return repr(self.value)
 
+
 class SimpleHoster(Hoster):
     __name__ = "SimpleHoster"
-    __version__ = "0.30"
+    __version__ = "0.31"
     __pattern__ = None
     __type__ = "hoster"
     __description__ = """Base hoster plugin"""
-    __author_name__ = ("zoidberg")
-    __author_mail__ = ("zoidberg@mujmail.cz")
+    __author_name__ = ("zoidberg", "stickell")
+    __author_mail__ = ("zoidberg@mujmail.cz", "l.stickell@yahoo.it")
     """
     These patterns should be defined by each hoster:
     FILE_INFO_PATTERN = r'(?P<N>file_name) (?P<S>file_size) (?P<U>units)'
@@ -159,15 +176,17 @@ class SimpleHoster(Hoster):
     and FILE_SIZE_PATTERN = r'(?P<S>file_size) (?P<U>units)'
     FILE_OFFLINE_PATTERN = r'File (deleted|not found)'
     TEMP_OFFLINE_PATTERN = r'Server maintainance'
+
+    You can also define a PREMIUM_ONLY_PATTERN to detect links that can be downloaded only with a premium account.
     """
 
     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
+    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 = {}
@@ -189,11 +208,14 @@ class SimpleHoster(Hoster):
         else:
             # This line is required due to the getURL workaround. Can be removed in 0.5
             self.html = self.load(pyfile.url, decode=not self.SH_BROKEN_ENCODING, cookies=self.SH_COOKIES)
+            if hasattr(self, 'PREMIUM_ONLY_PATTERN') and re.search(self.PREMIUM_ONLY_PATTERN, self.html):
+                self.fail("This link require a premium account")
             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)
+        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)
@@ -230,7 +252,7 @@ class SimpleHoster(Hoster):
     def parseError(self, msg):
         raise PluginParseError(msg)
 
-    def longWait(self, wait_time = None, max_tries = 3):
+    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:
@@ -242,7 +264,7 @@ class SimpleHoster(Hoster):
 
         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)
@@ -253,4 +275,4 @@ class SimpleHoster(Hoster):
             return True
         size = self.pyfile.size / 1024
         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
+        return size <= traffic