From 0ce9ba7932a2242d5850a01483a008a8eb9ee51a Mon Sep 17 00:00:00 2001
From: Michael Murtaugh <mm@automatist.org>
Date: Tue, 14 Apr 2020 12:56:40 +0200
Subject: [PATCH] use markdown + html5lib to structure the text

---
 readfrompad.py | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/readfrompad.py b/readfrompad.py
index f4e803e..3a61b66 100644
--- a/readfrompad.py
+++ b/readfrompad.py
@@ -2,12 +2,24 @@ from urllib.request import urlopen
 import markdown, html5lib
 
 
+sample_text = """
+# https://hub.xpub.nl/bootleglibrary/book/374
+This is an annotation of Mrs. Gersande's Binding Index
+"""
+
 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')
+pad_text = sample_text
+
 # print (pad_text)
+# Turn pad text into html text
 html = markdown.markdown(pad_text)
+print (html)
+
+# Turn html text in an elementtree
 t = html5lib.parseFragment(html, namespaceHTMLElements=False)
 print (t)
 for elt in t: