Wikinaut · December 19, 2022 12:10
diff --git a/patch-parsed-twitter-archive.sh b/patch-parsed-twitter-archive.sh
 #!/usr/bin/bash

 # Patch parsed Twitter Archiv Parser

 # To clarify: the script does not patch the parser, but the twitter-archive-parser-parsed archive
 # It is not modifying the parsed files themselves, but creating copies with the extension .body

 # Postprocessor for files generated by https://github.com/timhutton/twitter-archive-parser
 # init 18.12.2022

 # Usage: in the parsed twitter-archive directory with the numerous *.html, run
 # ./patch-parsed-twitter-archive-sh

 # It creates:
 # for each existing monthly (or so) *.html it creates one new *.html.body file
 # patches and strips several html tags
 # adds jQuery and the lazy-images loader
 # adds links to the images to facilitate the original view, opens the original image in a new tab 
 # concatenates all *.html.body files into a single all.html file

 # TODO:
 # the sorting order in each monthly block is downwards (most recent tweet: at the end)
 # where as the concatenated monthly files are added with the "most recent on top"
 # Example: NOV 1, 2, ... 30, OCT 1, 2, ... 31

 # License: WTFPL

 IFSsave=$IFS
 IFS='' # to preserve html page code layout

 { header=$(cat) ; } << 'EOF'
 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
 <html>
 <head>

 <meta http-equiv="Content-Type" content="text/html; charset=utf-8">
 <meta name="viewport" content="initial-scale=1.0, user-scalable=no" />

 <script type="text/javascript" src="https://code.jquery.com/jquery-3.6.2.min.js"></script>
 <script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/jquery.lazy/1.7.9/jquery.lazy.min.js"></script>

 <style>

 .container {
 	position: relative;
 	padding-left: 33%;
 	width: 33%;
 	font-size: small;
 	font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Helvetica,Arial,sans-serif;
 	font-size: 15px;
 }

 blockquote {
 }

 img.lazy {
        max-height: 33vh; /* percentage of viewport height */
        display: flex;
        margin-right: auto;
        margin-left: auto;
 }

 video {
        display: flex;
        margin-right: auto;
        margin-left: auto;
        max-height: 33vh;
 }

 </
 </style>

 </head>

 <body>

 <script>

 $(function($) {
 	$("img.lazy").Lazy();
 	$("img.lazy").each( function() {
 		$(this).wrap("<a href='"+$(this).attr("data-src")+"' target='_blank'></a>");
 	});
 });

 </script>
 EOF

 { footer=$(cat) ; } << 'EOF'
 </body>
 </html>
 EOF

 for f in *Tweet-Archive*.html ; do
 	sed "1,/<body*/d;/<\/body/,//d;/<main class=\"container\">/d;
 		s/^ *<h1>Your twitter archive<\/h1>/<main class=\"container\">\n<h3>$f<\/h3>\n<hr>\n/g; \
 		s/<img src=\"media/<img class='lazy' data-src=\"media/g; \
 		s/\/><br><img/\/><img/g" \
 		"$f" > "$f.body"
 done

 outfile="all.html"
 echo $header | cat > "$outfile"

 IFS=$IFSsave
 cat $(ls -r *Tweet-Archive*.html.body) >> "$outfile"

 # cleaning up
 rm *Tweet-Archive*.html.body 

 IFS=''
 echo $footer |cat >> "$outfile"
	#!/usr/bin/bash

	# Patch parsed Twitter Archiv Parser

	# To clarify: the script does not patch the parser, but the twitter-archive-parser-parsed archive
	# It is not modifying the parsed files themselves, but creating copies with the extension .body

	# Postprocessor for files generated by https://github.com/timhutton/twitter-archive-parser
	# init 18.12.2022

	# Usage: in the parsed twitter-archive directory with the numerous *.html, run
	# ./patch-parsed-twitter-archive-sh

	# It creates:
	# for each existing monthly (or so) .html it creates one new .html.body file
	# patches and strips several html tags
	# adds jQuery and the lazy-images loader
	# adds links to the images to facilitate the original view, opens the original image in a new tab
	# concatenates all *.html.body files into a single all.html file

	# TODO:
	# the sorting order in each monthly block is downwards (most recent tweet: at the end)
	# where as the concatenated monthly files are added with the "most recent on top"
	# Example: NOV 1, 2, ... 30, OCT 1, 2, ... 31

	# License: WTFPL

	IFSsave=$IFS
	IFS='' # to preserve html page code layout

	{ header=$(cat) ; } << 'EOF'
	<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
	<html>
	<head>

	<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
	<meta name="viewport" content="initial-scale=1.0, user-scalable=no" />

	<script type="text/javascript" src="https://code.jquery.com/jquery-3.6.2.min.js"></script>
	<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/jquery.lazy/1.7.9/jquery.lazy.min.js"></script>

	<style>

	.container {
	position: relative;
	padding-left: 33%;
	width: 33%;
	font-size: small;
	font-family: -apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Helvetica,Arial,sans-serif;
	font-size: 15px;
	}

	blockquote {
	}

	img.lazy {
	max-height: 33vh; /* percentage of viewport height */
	display: flex;
	margin-right: auto;
	margin-left: auto;
	}

	video {
	display: flex;
	margin-right: auto;
	margin-left: auto;
	max-height: 33vh;
	}

	</
	</style>

	</head>

	<body>

	<script>

	$(function($) {
	$("img.lazy").Lazy();
	$("img.lazy").each( function() {
	$(this).wrap("<a href='"+$(this).attr("data-src")+"' target='_blank'></a>");
	});
	});

	</script>
	EOF

	{ footer=$(cat) ; } << 'EOF'
	</body>
	</html>
	EOF

	for f in Tweet-Archive.html ; do
	sed "1,/<body*/d;/<\/body/,//d;/<main class=\"container\">/d;
	s/^ *<h1>Your twitter archive<\/h1>/<main class=\"container\">\n<h3>$f<\/h3>\n<hr>\n/g; \
	s/<img src=\"media/<img class='lazy' data-src=\"media/g; \
	s/\/><br><img/\/><img/g" \
	"$f" > "$f.body"
	done

	outfile="all.html"
	echo $header \| cat > "$outfile"

	IFS=$IFSsave
	cat $(ls -r Tweet-Archive.html.body) >> "$outfile"

	# cleaning up
	rm Tweet-Archive.html.body

	IFS=''
	echo $footer \|cat >> "$outfile"