morss/morss.py

@@ -18,7 +18,6 @@ from . import readabilite
 
 import wsgiref.simple_server
 import wsgiref.handlers
-import cgitb
 
 
 try:
@@ -45,7 +44,7 @@ THREADS = 10  # number of threads (1 for single-threaded)
 DEBUG = False
 PORT = 8080
 
-PROTOCOL = ['http', 'https']
+PROTOCOL = ['http', 'https', 'ftp']
 
 
 def filterOptions(options):
@@ -67,7 +66,6 @@ def log(txt, force=False):
     if DEBUG or force:
         if 'REQUEST_URI' in os.environ:
             open('morss.log', 'a').write("%s\n" % repr(txt))
-
         else:
             print(repr(txt))
 
@@ -75,7 +73,6 @@ def log(txt, force=False):
 def len_html(txt):
     if len(txt):
         return len(lxml.html.fromstring(txt).text_content())
-
     else:
         return 0
 
@@ -83,7 +80,6 @@ def len_html(txt):
 def count_words(txt):
     if len(txt):
         return len(lxml.html.fromstring(txt).text_content().split())
-
     return 0
 
 
@@ -92,14 +88,12 @@ class Options:
         if len(args):
             self.options = args
             self.options.update(options or {})
-
         else:
             self.options = options or {}
 
     def __getattr__(self, key):
         if key in self.options:
             return self.options[key]
-
         else:
             return False
 
@@ -113,23 +107,17 @@ class Options:
 def parseOptions(options):
     """ Turns ['md=True'] into {'md':True} """
     out = {}
-
     for option in options:
         split = option.split('=', 1)
-
         if len(split) > 1:
             if split[0].lower() == 'true':
                 out[split[0]] = True
-
             elif split[0].lower() == 'false':
                 out[split[0]] = False
-
             else:
                 out[split[0]] = split[1]
-
         else:
             out[split[0]] = True
-
     return out
 
 
@@ -220,7 +208,6 @@ def ItemFill(item, options, feedurl='/', fast=False):
         if len(match):
             link = match[0]
             log(link)
-
         else:
             link = None
 
@@ -230,7 +217,6 @@ def ItemFill(item, options, feedurl='/', fast=False):
         if len(match) and urlparse(match[0]).netloc != 'www.facebook.com':
             link = match[0]
             log(link)
-
         else:
             link = None
 
@@ -313,7 +299,6 @@ def UrlFix(url):
 
     return url
 
-
 def FeedFetch(url, options):
     # allow for code execution for feedify
     pre = feedify.pre_worker(url)
@@ -342,6 +327,7 @@ def FeedFetch(url, options):
     if options.items:
         # using custom rules
         rss = feeds.FeedHTML(xml)
+        feed.rule
 
         rss.rules['items'] = options.items
 
@@ -354,8 +340,6 @@ def FeedFetch(url, options):
         if options.item_time:
             rss.rules['item_time'] = options.item_time
 
-        rss = rss.convert(feeds.FeedXML)
-
     else:
         try:
             rss = feeds.parse(xml, url, contenttype)
@@ -393,7 +377,6 @@ def FeedGather(rss, url, options):
             value = queue.get()
             try:
                 worker(*value)
-
             except Exception as e:
                 log('Thread Error: %s' % e.message)
             queue.task_done()
@@ -433,7 +416,6 @@ def FeedGather(rss, url, options):
     for i, item in enumerate(list(rss.items)):
         if threads == 1:
             worker(*[i, item])
-
         else:
             queue.put([i, item])
 
@@ -453,38 +435,37 @@ def FeedGather(rss, url, options):
     return rss
 
 
-def FeedFormat(rss, options, encoding='utf-8'):
+def FeedFormat(rss, options):
     if options.callback:
         if re.match(r'^[a-zA-Z0-9\.]+$', options.callback) is not None:
-            out = '%s(%s)' % (options.callback, rss.tojson(encoding='unicode'))
+            return '%s(%s)' % (options.callback, rss.tojson())
-            return out if encoding == 'unicode' else out.encode(encoding)
 
         else:
             raise MorssException('Invalid callback var name')
 
     elif options.json:
         if options.indent:
-            return rss.tojson(encoding=encoding, indent=4)
+            return rss.tojson(encoding='UTF-8', indent=4)
 
         else:
-            return rss.tojson(encoding=encoding)
+            return rss.tojson(encoding='UTF-8')
 
     elif options.csv:
-        return rss.tocsv(encoding=encoding)
+        return rss.tocsv(encoding='UTF-8')
 
     elif options.reader:
         if options.indent:
-            return rss.tohtml(encoding=encoding, pretty_print=True)
+            return rss.tohtml(encoding='UTF-8', pretty_print=True)
 
         else:
-            return rss.tohtml(encoding=encoding)
+            return rss.tohtml(encoding='UTF-8')
 
     else:
         if options.indent:
-            return rss.torss(xml_declaration=True, encoding=encoding, pretty_print=True)
+            return rss.torss(xml_declaration=True, encoding='UTF-8', pretty_print=True)
 
         else:
-            return rss.torss(xml_declaration=True, encoding=encoding)
+            return rss.torss(xml_declaration=True, encoding='UTF-8')
 
 
 def process(url, cache=None, options=None):
@@ -518,7 +499,7 @@ def cgi_app(environ, start_response):
     if url.startswith(':'):
         split = url.split('/', 1)
 
-        raw_options = split[0].replace('|', '/').replace('\\\'', '\'').split(':')[1:]
+        options = split[0].replace('|', '/').replace('\\\'', '\'').split(':')[1:]
 
         if len(split) > 1:
             url = split[1]
@@ -526,10 +507,10 @@ def cgi_app(environ, start_response):
             url = ''
 
     else:
-        raw_options = []
+        options = []
 
     # init
-    options = Options(filterOptions(parseOptions(raw_options)))
+    options = Options(filterOptions(parseOptions(options)))
     headers = {}
 
     global DEBUG
@@ -570,42 +551,18 @@ def cgi_app(environ, start_response):
     rss = FeedGather(rss, url, options)
     out = FeedFormat(rss, options)
 
-    if options.silent:
+    if not options.silent:
-        return ['']
+        return out
-
-    else:
-        return [out]
 
 
-def middleware(func):
+def cgi_wrapper(environ, start_response):
-    " Decorator to turn a function into a wsgi middleware "
+    # simple http server for html and css
-    # This is called when parsing the code
-
-    def app_builder(app):
-        # This is called when doing app = cgi_wrapper(app)
-
-        def app_wrap(environ, start_response):
-            # This is called when a http request is being processed
-
-            return func(environ, start_response, app)
-
-        return app_wrap
-
-    return app_builder
-
-
-@middleware
-def cgi_file_handler(environ, start_response, app):
-    " Simple HTTP server to serve static files (.html, .css, etc.) "
-
     files = {
         '': 'text/html',
-        'index.html': 'text/html',
+        'index.html': 'text/html'}
-        'sheet.xsl': 'text/xsl'}
 
     if 'REQUEST_URI' in environ:
         url = environ['REQUEST_URI'][1:]
-
     else:
         url = environ['PATH_INFO'][1:]
 
@@ -634,29 +591,16 @@ def cgi_file_handler(environ, start_response, app):
             start_response(headers['status'], list(headers.items()))
             return ['Error %s' % headers['status']]
 
-    else:
+    # actual morss use
-        return app(environ, start_response)
-
-
-@middleware
-def cgi_error_handler(environ, start_response, app):
     try:
-        return app(environ, start_response)
+        return [cgi_app(environ, start_response) or '(empty)']
-
     except (KeyboardInterrupt, SystemExit):
         raise
-
     except Exception as e:
-        headers = {'status': '500 Oops', 'content-type': 'text/html'}
+        headers = {'status': '500 Oops', 'content-type': 'text/plain'}
         start_response(headers['status'], list(headers.items()), sys.exc_info())
-        log('ERROR: %s' % repr(e), force=True)
+        log('ERROR <%s>: %s' % (url, e.message), force=True)
-        return [cgitb.html(sys.exc_info())]
+        return ['An error happened:\n%s' % e.message]
-
-
-@middleware
-def cgi_encode(environ, start_response, app):
-    out = app(environ, start_response)
-    return [x if isinstance(x, bytes) else x.encode('utf-8') for x in out]
 
 
 def cli_app():
@@ -683,7 +627,6 @@ def isInt(string):
     try:
         int(string)
         return True
-
     except ValueError:
         return False
 
@@ -691,12 +634,7 @@ def isInt(string):
 def main():
     if 'REQUEST_URI' in os.environ:
         # mod_cgi
-
+        wsgiref.handlers.CGIHandler().run(cgi_wrapper)
-        app = cgi_app
-        app = cgi_error_handler(app)
-        app = cgi_encode(app)
-
-        wsgiref.handlers.CGIHandler().run(app)
 
     elif len(sys.argv) <= 1 or isInt(sys.argv[1]) or '--root' in sys.argv[1:]:
         # start internal (basic) http server
@@ -705,30 +643,22 @@ def main():
             argPort = int(sys.argv[1])
             if argPort > 0:
                 port = argPort
-
             else:
                 raise MorssException('Port must be positive integer')
 
         else:
             port = PORT
 
-        app = cgi_app
+        print('Serving http://localhost:%s/'%port)
-        app = cgi_file_handler(app)
+        httpd = wsgiref.simple_server.make_server('', port, cgi_wrapper)
-        app = cgi_error_handler(app)
-        app = cgi_encode(app)
-
-        print('Serving http://localhost:%s/' % port)
-        httpd = wsgiref.simple_server.make_server('', port, app)
         httpd.serve_forever()
 
     else:
         # as a CLI app
         try:
             cli_app()
-
         except (KeyboardInterrupt, SystemExit):
             raise
-
         except Exception as e:
             print('ERROR: %s' % e.message)