From fc3c0b8be63efc19ede332132e755f0569d1587c Mon Sep 17 00:00:00 2001
From: octospacc <octo@tutamail.com>
Date: Wed, 29 Jun 2022 00:17:52 +0200
Subject: [PATCH] First work on HTML to Gemtext

---
 Source/Build.py          | 15 +++++++++++----
 Source/Modules/Gemini.py | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 4 deletions(-)
 create mode 100644 Source/Modules/Gemini.py

diff --git a/Source/Build.py b/Source/Build.py
index 3cfda04..93414a3 100755
--- a/Source/Build.py
+++ b/Source/Build.py
@@ -19,16 +19,18 @@ from Libs.markdown import Markdown
 from Libs.markdown import markdown
 from pathlib import Path
 from Modules.Feed import *
+from Modules.Gemini import *
 from Modules.Utils import *
 
 Extensions = {
 	'Pages': ('md', 'pug')}
 
 def ResetPublic():
-	try:
-		shutil.rmtree('public')
-	except FileNotFoundError:
-		pass
+	for i in ('public', 'public.gmi'):
+		try:
+			shutil.rmtree(i)
+		except FileNotFoundError:
+			pass
 
 def GetLevels(Path, AsNum=False, Add=0, Sub=0):
 	n = Path.count('/') + Add - Sub
@@ -473,6 +475,11 @@ def Main(Args):
 			Lang=SiteLang,
 			Minify=True if Args.Minify and Args.Minify not in ('False', 'None') else False)
 
+	#HTML2Gemtext(
+	#	Pages=Pages,
+	#	SiteName=SiteName,
+	#	SiteTagline=SiteTagline)
+
 	DelTmp()
 	os.system("cp -R Assets/* public/")
 
diff --git a/Source/Modules/Gemini.py b/Source/Modules/Gemini.py
new file mode 100644
index 0000000..c4e3b7e
--- /dev/null
+++ b/Source/Modules/Gemini.py
@@ -0,0 +1,35 @@
+""" ================================= |
+| This file is part of                |
+|   staticoso                         |
+| Just a simple Static Site Generator |
+|                                     |
+| Licensed under the AGPLv3 license   |
+|   Copyright (C) 2022, OctoSpacc     |
+| ================================= """
+
+from Libs.bs4 import BeautifulSoup
+from Modules.Utils import *
+
+def HTML2Gemtext(Pages, SiteName, SiteTagline):
+	os.mkdir('public.gmi')
+	for File, Content, Titles, Meta, HTMLContent, Description, Image in Pages:
+		Parse = BeautifulSoup(HTMLContent, 'html.parser')
+		# We should first get the most basic HTML elements, convert them to Gemtext, then replace the Gemtext in the original full HTML, and then removing <p> tags?
+		#print(File, Parse.find_all('p'), Parse.find_all('li'))
+
+""" Gemtext:
+# h1
+## h2
+### h3
+
+* li
+* li
+
+=> [protocol://]URL Link Description
+
+> Quote
+
+```
+Preformatted
+```
+"""