convert script to python

Makefile

@@ -1,8 +1,9 @@
 install:
-	cp notes2web /usr/local/bin
+	cp notes2web.py /usr/local/bin
+	pip install -r requirement.txt
 	mkdir -p /opt/notes2web
 	cp -r templates /opt/notes2web
 	cp styles.css /opt/notes2web
 
 uninstall:
-	rm -rf /usr/local/bin/notes2web/opt/notes2web
+	rm -rf /usr/local/bin/notes2web.py /opt/notes2web

notes2web

@@ -1,137 +0,0 @@
-#!/usr/bin/env bash
-
-
-# set default config values, load user config, export config variables
-name=""
-output="web"
-article_template="/opt/notes2web/templates/article.html"
-textarticlehead_template="/opt/notes2web/templates/textarticlehead.html"
-textarticlefoot_template="/opt/notes2web/templates/textarticlefoot.html"
-listitem_template="/opt/notes2web/templates/listitem.html"
-index_template="/opt/notes2web/templates/index.html"
-stylesheet="/opt/notes2web/styles.css"
-
-for configpath in "$HOME/.notes2web.conf" "$HOME/.config/notes2web/config" ".notes2web.conf"
-do
-	[[ -f "$configpath" ]] && source "$configpath"
-done
-
-export name
-export output
-export article_template
-export textarticlehead_template
-export textarticlefoot_template
-export listitem_template
-export index_template
-export stylesheet
-
-
-[[ "$1" == "--help" ]] && echo "USAGE: $0 [NOTES_DIRECTORY_1 [NOTES_DIRECTORY_2 [...]]]" && exit 0
-[[ "$1" == "--clean" ]] && {
-	find -name ".2web" -exec rm {} \;
-	rm -rf "$output"
-	exit 0
-}
-
-
-mkdir -p "$output"
-
-
-function _renderarticle {
-	echo "rendering $1"
-	mkdir -p "$(dirname "$output/${1}.html")"
-	pandoc\
-		--toc\
-		--standalone\
-		-t html\
-		--template "$article_template"\
-		-o "$output/${1}.html"\
-		"$1"\
-		--mathjax
-}
-
-
-function _rendertextarticle {
-	[[ "$(file -b "$1")" == "ASCII text" ]] || exit
-	echo "rendering text file $1"
-	mkdir -p "$(dirname "$output/${1}.html")"
-	sed -e "s#\\\$title\\\$#$1#" "$textarticlehead_template"\
-		> "$output/${1}.html"
-	cat "$1" >> "$output/${1}.html"
-	cat "$textarticlefoot_template" >> "$output/${1}.html"
-}
-
-
-function _adddirtoindex {
-	dir="$(dirname "$1")"
-	echo "<h2>$(basename "$dir") notes</h2>" >> $output/index.md
-	find "$dir" -name '*.md' -exec bash -c "_addarticletoindex '{}'" \;
-	find "$dir" -not -path '**/.git/**' -not -name '*.md' -type f -exec bash -c "_addtextarticletoindex '{}'" \;
-}
-
-
-function _addtextarticletoindex {
-	[[ "$(file -b "$1")" == "ASCII text" ]] || exit
-	pandoc\
-		-t html\
-		-V "filepath=${1}.html"\
-		-V "title=$1"\
-		--template "$listitem_template"\
-		"$1"\
-		>> $output/index.md
-}
-
-
-function _addarticletoindex {
-	echo "adding $1 to list of notes"
-	pandoc\
-		-t html\
-		-V "filepath=${1}.html"\
-		--template "$listitem_template"\
-		"$1"\
-		>> $output/index.md
-}
-
-
-export -f _renderarticle
-export -f _rendertextarticle
-export -f _adddirtoindex
-export -f _addarticletoindex
-export -f _addtextarticletoindex
-
-
-#render each markdown file in every folder passed in args
-for dir in "$@"
-do
-	find "$dir" -name '*.md' -exec bash -c "_renderarticle '{}'" \;
-	find "$dir" -not -path '**/.git/**' -not -name '*.md' -type f -exec bash -c "_rendertextarticle '{}'" \;
-done
-
-
-# create an intermediate markdown file of links to each article
-echo "---" > $output/index.md
-[[ -z "$name" ]] && echo "title: notes" >> $output/index.md || echo "title: ${name}'s notes" >> $output/index.md
-echo "---" >> $output/index.md
-
-
-# mark folders to be included in notes2web's index
-for file in "$@"
-do
-	[[ ! -f "$file" ]] && echo "the presence of this files tells notes2web that it should be added to the notes2web index" > "$file/.2web"
-done
-
-
-# add articles to index and render
-find -name '.2web' -exec bash -c "_adddirtoindex '{}'" \;
-
-
-echo "copying styles.css to current directory"
-cp "$stylesheet" "$output/styles.css"
-
-
-echo "rendering index.md"
-pandoc\
-	-t html\
-	--template "$index_template"\
-	-o "$output/index.html"\
-	"$output/index.md"

notes2web.py

@@ -0,0 +1,169 @@
+#!/usr/bin/env python3
+
+
+from bs4 import BeautifulSoup as bs
+import magic
+import sys
+import pathlib
+import pypandoc
+import shutil
+import os
+import re
+
+TEXT_ARTICLE_TEMPLATE_FOOT = None
+TEXT_ARTICLE_TEMPLATE_HEAD = None
+INDEX_TEMPLATE_FOOT = None
+INDEX_TEMPLATE_HEAD = None
+
+def get_files(folder):
+    markdown = []
+    plaintext = []
+    other = []
+
+    for root, folders, files in os.walk(folder):
+        for filename in files:
+            name = os.path.join(root, filename)
+            if os.path.splitext(name)[1] == '.md':
+                markdown.append(name)
+            elif re.match(r'^text/', magic.from_file(name, mime=True)):
+                plaintext.append(name)
+                other.append(name)
+            else:
+                other.append(name)
+
+    return markdown, plaintext, other
+
+def get_dirs(folder):
+    r = []
+
+    for root, folders, files in os.walk(folder):
+        [r.append(os.path.join(root, folder)) for folder in folders]
+
+    return r
+
+
+def get_args():
+    """ Get command line arguments """
+
+    import argparse
+    parser = argparse.ArgumentParser()
+    parser.add_argument('notes', type=pathlib.Path)
+    parser.add_argument('-o', '--output-dir', type=pathlib.Path, default='web')
+    parser.add_argument('-t', '--template', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/templates/article.html'))
+    parser.add_argument('-H', '--template-text-head', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/templates/textarticlehead.html'))
+    parser.add_argument('-f', '--template-text-foot', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/templates/textarticlefoot.html'))
+    parser.add_argument('-i', '--template-index-head', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/templates/indexhead.html'))
+    parser.add_argument('-I', '--template-index-foot', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/templates/indexfoot.html'))
+    parser.add_argument('-s', '--stylesheet', type=pathlib.Path, default=pathlib.Path('/opt/notes2web/styles.css'))
+    return parser.parse_args()
+
+
+def main(args):
+    """ Entry point for script """
+
+    with open(args.template_text_foot) as fp:
+        TEXT_ARTICLE_TEMPLATE_FOOT = fp.read()
+
+    with open(args.template_text_head) as fp:
+        TEXT_ARTICLE_TEMPLATE_HEAD = fp.read()
+
+    with open(args.template_index_foot) as fp:
+        INDEX_TEMPLATE_FOOT = fp.read()
+
+    with open(args.template_index_head) as fp:
+        INDEX_TEMPLATE_HEAD = fp.read()
+
+    if not os.path.exists(args.output_dir):
+        os.makedirs(args.output_dir, exist_ok=True)
+
+    if os.path.isfile(args.output_dir):
+        print("Output directory ({output_dir}) cannot be a file.")
+
+
+    markdown_files, plaintext_files, other_files = get_files(args.notes)
+
+    print(f"{markdown_files=}")
+    for filename in markdown_files:
+        html = pypandoc.convert_file(filename, 'html', extra_args=[f'--template={args.template}'])
+        output_filename = os.path.splitext(re.sub(f"^{args.notes.name}", args.output_dir.name, filename))[0] + '.html'
+        os.makedirs(os.path.dirname(output_filename), exist_ok=True)
+
+        with open(output_filename, 'w+') as fp:
+            fp.write(html)
+
+    print(f"{plaintext_files=}")
+    for filename in plaintext_files:
+        output_filename = re.sub(f"^{args.notes.name}", args.output_dir.name, filename) + '.html'
+        os.makedirs(os.path.dirname(output_filename), exist_ok=True)
+        title = os.path.basename(output_filename)
+        html = re.sub(r'\$title\$', title, TEXT_ARTICLE_TEMPLATE_HEAD)
+        html = re.sub(r'\$raw\$', os.path.basename(filename), html)
+        with open(filename) as fp:
+            html += fp.read()
+        html += TEXT_ARTICLE_TEMPLATE_FOOT
+
+        with open(output_filename, 'w+') as fp:
+            fp.write(html)
+
+    print(f"{other_files=}")
+    for filename in other_files:
+        output_filename = re.sub(f"^{args.notes.name}", args.output_dir.name, filename)
+        os.makedirs(os.path.dirname(output_filename), exist_ok=True)
+        shutil.copyfile(filename, output_filename)
+
+
+    dirs_to_index = [args.output_dir.name] + get_dirs(args.output_dir)
+    print(f"{dirs_to_index=}")
+    for directory in dirs_to_index:
+        paths = os.listdir(directory)
+        print(f"{paths=}")
+
+        indexentries = []
+        
+        for path in paths:
+            if path == 'index.html':
+                continue
+
+            fullpath = os.path.join(directory, path)
+            print(fullpath)
+            if os.path.splitext(path)[1] == '.html':
+                with open(fullpath) as fp:
+                    soup = bs(fp.read(), 'html.parser')
+
+                try:
+                    title = soup.find('title').get_text()
+                except AttributeError:
+                    title = path
+            else:
+                title = path
+
+            if title.strip() == '':
+                title = path
+
+            indexentries.append({
+                'title': title,
+                'path': path,
+                'isdirectory': os.path.isdir(fullpath)
+                })
+
+        indexentries.sort(key=lambda entry: entry['title'])
+        indexentries.sort(key=lambda entry: entry['isdirectory'], reverse=True)
+        
+        html = re.sub(r'\$title\$', directory, INDEX_TEMPLATE_HEAD)
+        for entry in indexentries:
+            html += f"<div class=\"article\"><a href=\"{entry['path']}\">{entry['title']}{'/' if entry['isdirectory'] else ''}</a></div>"
+        html += INDEX_TEMPLATE_FOOT
+
+        with open(os.path.join(directory, 'index.html'), 'w+') as fp:
+            fp.write(html)
+
+    shutil.copyfile(args.stylesheet, os.path.join(args.output_dir.name, 'styles.css'))
+
+    return 0
+
+
+if __name__ == '__main__':
+    try:
+        sys.exit(main(get_args()))
+    except KeyboardInterrupt:
+        sys.exit(0)

readme.md

@@ -18,7 +18,7 @@ View your notes as a static html site.
 ## Usage
 
 ```
-$ notes2web NOTES_DIRECTORY_1 [NOTES_DIRECTORY_2 [...]]
+$ notes2web.py NOTES_DIRECTORY_1 [NOTES_DIRECTORY_2 [...]]
 ```
 
 The command will generate a website in the `$output` directory (`./web` by default).
@@ -28,6 +28,8 @@ Then you just have to point a webserver at `$output`.
 
 ## Config
 
+NOT CURRENTLY IMPLEMENTED
+
 `notes2web` looks for a config file called `.notes2web.conf` in your current directory and your home
 directory.
 Default config values:

requirements.txt

@@ -0,0 +1,3 @@
+beautifulsoup4==4.9.3
+pypandoc==1.5
+soupsieve==2.2.1

templates/indexfoot.html

@@ -0,0 +1,2 @@
+	<p style="font-size: 0.7em;"> page generated by <a href="https://github.com/alvierahman90/notes2web">notes2web</a></p>
+</body>

templates/indexhead.html

@@ -0,0 +1,11 @@
+<head>
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<meta charset="utf-8"> 
+<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=Open+Sans&display=swap" />
+<link rel="stylesheet" type="text/css" href="/styles.css" />
+<title>$title$</title>
+</head>
+
+<body>
+	<h1>$title$</h1>
+	<div class="article"><a href="..">../</a></div>

templates/textarticlehead.html

@@ -10,6 +10,7 @@
 	<h1>$title$</h1>
 	<p> This file was not rendered by notes2web because it is a plaintext file, not a markdown
 	file.
+	You access the raw file <a href="$raw$">here</a>.
 	Below is an unformatted representation of the file:
 	</p>
 	<pre>