From 5806ed6e90d93d7b4871f950957b39cc97674a90 Mon Sep 17 00:00:00 2001
From: Michael Murtaugh <mm@automatist.org>
Date: Tue, 14 Apr 2020 12:48:35 +0200
Subject: [PATCH] use markdown + html5lib to structure the text

---
 readfrompad.py | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/readfrompad.py b/readfrompad.py
index 8158413..f4e803e 100644
--- a/readfrompad.py
+++ b/readfrompad.py
@@ -1,11 +1,14 @@
 from urllib.request import urlopen
+import markdown, html5lib
 
 
 pad_url = "https://pad.xpub.nl/p/boring_old_tomato_sandwiches"
 pad_text_url = pad_url + "/export/txt"
-
 f = urlopen(pad_text_url)
 pad_text = f.read().decode('utf-8')
-
-print (pad_text)
-
+# print (pad_text)
+html = markdown.markdown(pad_text)
+t = html5lib.parseFragment(html, namespaceHTMLElements=False)
+print (t)
+for elt in t:
+    print (elt)