From 58c69651d37af756caf40d30ddf8dd18b4703e93 Mon Sep 17 00:00:00 2001
From: Richard Harding <rharding@mitechie.com>
Date: Wed, 18 Apr 2012 21:31:42 -0400
Subject: [PATCH] Update README to be a rst file and clean up a little bit.

---
 README => README.rst                | 60 ++++++++++++++++++-----------
 src/readability_lxml/readability.py |  8 +---
 2 files changed, 39 insertions(+), 29 deletions(-)
 rename README => README.rst (52%)

diff --git a/README b/README.rst
similarity index 52%
rename from README
rename to README.rst
index 9e0471c..ee9aa66 100644
--- a/README
+++ b/README.rst
@@ -1,14 +1,14 @@
-This code is under the Apache License 2.0.  http://www.apache.org/licenses/LICENSE-2.0
+readability_lxml
+================
 
-This is a python port of a ruby port of arc90's readability project
+This is a python port of a ruby port of `arc90's readability`_ project
 
-http://lab.arc90.com/experiments/readability/
-
-In few words,
 Given a html document, it pulls out the main body text and cleans it up.
 It also can clean up title based on latest readability.js code.
 
-Based on:
+
+Inspiration
+-----------
  - Latest readability.js ( https://github.com/MHordecki/readability-redux/blob/master/readability/readability.js )
  - Ruby port by starrhorne and iterationlabs
  - Python port by gfxmonk ( https://github.com/gfxmonk/python-readability , based on BeautifulSoup )
@@ -16,13 +16,29 @@ Based on:
  - "BR to P" fix from readability.js which improves quality for smaller texts.
  - Github users contributions.
 
-Installation::
 
-    easy_install readability-lxml
-    or
-    pip install readability-lxml
+Installation
+-------------
+::
+
+    $ easy_install readability-lxml
+    # or
+    $ pip install readability-lxml
+
+
+Usage
+------
 
-Usage::
+Command Line Client
+~~~~~~~~~~~~~~~~~~~
+::
+
+    $ readability http://pypi.python.org/pypi/readability-lxml
+    $ readability /home/rharding/sampledoc.html
+
+As a Library
+~~~~~~~~~~~~
+::
 
     from readability.readability import Document
     import urllib
@@ -30,21 +46,19 @@ Usage::
     readable_article = Document(html).summary()
     readable_title = Document(html).short_title()
 
-Command-line usage::
-
-    python -m readability.readability -u http://pypi.python.org/pypi/readability-lxml
-
+Optional `Document` keyword argument:
 
-Document() kwarg options:
+- attributes:
+- debug: output debug messages
+- min_text_length:
+- retry_length:
+- url: will allow adjusting links to be absolute
 
- - attributes:
- - debug: output debug messages
- - min_text_length:
- - retry_length:
- - url: will allow adjusting links to be absolute
 
+History
+-------
 
-Updates
+ - `0.2.5`` Update setup.py for uploading .tar.gz to pypi
 
- - 0.2.5 Update setup.py for uploading .tar.gz to pypi
 
+.. _arc90's readability: http://lab.arc90.com/experiments/readability/
diff --git a/src/readability_lxml/readability.py b/src/readability_lxml/readability.py
index 2c8c630..c83b46f 100755
--- a/src/readability_lxml/readability.py
+++ b/src/readability_lxml/readability.py
@@ -102,11 +102,6 @@ class Document:
         self.options = options
         self.html = None
 
-    def _html(self, force=False):
-        if force or self.html is None:
-            self.html = self._parse(self.input_doc)
-        return self.html
-
     def _parse(self, input_doc):
         doc = build_doc(input_doc)
         doc = html_cleaner.clean_html(doc)
@@ -136,7 +131,8 @@ class Document:
         try:
             ruthless = True
             while True:
-                self._html(True)
+                self.html = self._parse(self.input_doc)
+
                 for i in self.tags(self.html, 'script', 'style'):
                     i.drop_tree()
                 for i in self.tags(self.html, 'body'):