From 27ac7d1eb78a038c1dff57cdab3f7173ddd1c8e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Gil=20Gon=C3=A7alves?= Date: Fri, 17 Jan 2014 23:53:41 +0000 Subject: [PATCH] Code naming and spacing improvement in converter --- converter.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/converter.py b/converter.py index af125f9..39e5ee6 100644 --- a/converter.py +++ b/converter.py @@ -5,9 +5,11 @@ import os import requests from html2text import html2text + _READABILITY_URL = 'https://www.readability.com/api/content/v1/parser' -def _readability(url): + +def _get_readability_html_and_title(url): token = os.environ.get('READABILITY_TOKEN') params = {'url': url, 'token': token} @@ -18,7 +20,8 @@ def _readability(url): ) return decoded_content -def _convert(html, title=None): + +def _convert_html_to_markdown(html, title=None): if title: title = '# {}'.format(title) html = '\n\n'.join([title, html]) @@ -26,13 +29,16 @@ def _convert(html, title=None): text_from_html = html2text(html) return text_from_html + def get_readable_content_from_url(url): try: - content, title = _readability(url) - return _convert(content, title=title) + content, title = _get_readability_html_and_title(url) + markdown = _convert_html_to_markdown(content, title=title) + return markdown except KeyError: return None if __name__ == '__main__': print get_readable_content_from_url('http://kennethreitz.org/') +