Some changes to run script

docs/index.rst

@@ -216,7 +216,7 @@ Extract using the rules in a JSON file (from *parslepy*'s ``examples/`` director
             "url": "a.item @href",
         }]
     }
-    $ python run_parslepy.py --script examples/engadget_css.let.json --url http://www.engadget.com
+    $ python run_parslepy.py examples/engadget_css.let.json http://www.engadget.com
     {u'sections': [{u'title': u'News', u'url': '/'},
                 {u'title': u'Reviews', u'url': '/reviews/'},
                 {u'title': u'Features', u'url': '/features/'},
@@ -228,6 +228,20 @@ Extract using the rules in a JSON file (from *parslepy*'s ``examples/`` director
                 {u'title': u'Engadget Show', u'url': '/videos/show/'},
                 {u'title': u'Topics', u'url': '#nav-topics'}]}
 
+You can also pass a local HTML file instead::
+
+    $ wget http://www.engadget.com -O page.html
+    $ python run_parslepy.py examples/engadget_css.let.json page.html
+    {u'sections': [{u'title': u'News', u'url': '/'},
+                {u'title': u'Reviews', u'url': '/reviews/'},
+                {u'title': u'Features', u'url': '/features/'},
+                {u'title': u'Galleries', u'url': '/galleries/'},
+                {u'title': u'Videos', u'url': '/videos/'},
+                {u'title': u'Events', u'url': '/events/'},
+                {u'title': u'Podcasts',
+                    u'url': '/podcasts/the-engadget-podcast/'},
+                {u'title': u'Engadget Show', u'url': '/videos/show/'},
+                {u'title': u'Topics', u'url': '#nav-topics'}]}
 
 You may want to check out the other examples given in the ``examples/`` directory.
 You can run them using the ``run_parslepy.py`` script like shown above.

run_parslepy.py

@@ -1,34 +1,24 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-import optparse
+import argparse
 import pprint
 import parslepy
-import lxml.html
 
-def main():
 
-    parser = optparse.OptionParser()
-    parser.add_option("--debug", dest="debug", action="store_true", help="debug mode", default=False)
-    parser.add_option("--url", dest="url", help="fetch this URL", default=None)
-    parser.add_option("--file", dest="inputfile", help="parse this HTML file", default=None)
-    parser.add_option("--script", dest="parselet", help="Parsley script filename", default=None)
-
-    (options, args) = parser.parse_args()
+def main(args):
+    with open(args.parselet) as fp:
+        extractor = parslepy.Parselet.from_jsonfile(fp, debug=args.debug)
+        output = extractor.parse(args.input)
+        pprint.pprint(output)
 
-    if not options.parselet:
-        print("You must provide a Parsley script")
-        return
-    if not options.url and not options.inputfile:
-        print("You must provide an URL")
-        return
 
-    with open(options.parselet) as fp:
-
-        extractor = parslepy.Parselet.from_jsonfile(fp, options.debug)
-        output = extractor.parse(options.url or options.inputfile)
-        pprint.pprint(output)
+def parse_args():
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument('parselet', help='Path to Parsley script')
+    parser.add_argument('input', help='URL or HTML file to scrape from')
+    parser.add_argument('--debug', action='store_true', help='Enable DEBUG mode')
+    return parser.parse_args()
 
 if __name__ == '__main__':
-	main()
-
+    main(parse_args())

setup.py

@@ -39,6 +39,7 @@
         "lxml >= 2.3",
         "cssselect",
       ],
+      scripts=['run_parslepy.py'],
       classifiers = [
         'Topic :: Software Development :: Libraries :: Python Modules',
         'Topic :: Text Processing :: Markup :: HTML',