From 3929dcdebfb3ab658e5b7b7a77f93df1dff5ccf1 Mon Sep 17 00:00:00 2001
From: itec78 <itec78@gmail.com>
Date: Mon, 27 Mar 2023 22:43:36 +0200
Subject: [PATCH] index fix

---
 oloturia2pdf.py | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/oloturia2pdf.py b/oloturia2pdf.py
index 0106cac..98952d6 100755
--- a/oloturia2pdf.py
+++ b/oloturia2pdf.py
@@ -10,6 +10,7 @@ import html2text
 import pdfkit
 import locale
 import PyPDF2
+import html
 
 locale.setlocale(locale.LC_TIME, 'it_IT.UTF-8')
 
@@ -161,9 +162,15 @@ def main():
 
         for vgo in all_vgos:
             vgo_num = html2text.html2text(vgo['content']).split(' ')[0]
-            vgo_name = os.linesep.join([s for s in html2text.html2text(vgo['content']).splitlines() if s]).splitlines()[-1]
-            if len(vgo_name) < 10:
-                vgo_name = [s for s in html2text.html2text(vgo['content']).split("\n\n") if s][-1].replace("\n"," ")
+            # vgo_name = os.linesep.join([s for s in html2text.html2text(vgo['content']).splitlines() if s]).splitlines()[-1]
+            # if len(vgo_name) < 10:
+            #     vgo_name = [s for s in html2text.html2text(vgo['content']).split("\n\n") if s][-1].replace("\n"," ")
+
+            vgo_name = vgo['content'].split("<p>")[-1].replace("</p>","")
+            vgo_name = vgo_name.split("<br />")[-1]
+            vgo_name = vgo_name.split("</a>")[-1]
+            vgo_name = html.unescape(vgo_name).strip()
+
             #print(vgo_num +' - '+ vgo_name)
             #print(str(vgo['id']) +' '+ vgo['uri'])
             vgo_dict[vgo_num] = vgo_name