lain-ipfs-scraper/index.pyhtml

57 lines
2.6 KiB
Plaintext

<%!
import BTEdb, time
%>
<%
db = BTEdb.Database("/dev/shm/lainchan-scraper.json")
dumped = db.Dump("table")
dumped.sort(key = lambda x: x["time"])
%>
<!doctype html>
<html>
<head>
<title>Lainchan scraper for IPFS IDs</title>
<link rel="stylesheet" href="/style.css" />
<link rel="stylesheet" href="https://lainchan.org/stylesheets/code/dark.css" />
<script type="text/javascript" src="https://lainchan.org/js/jquery.min.js"></script>
<script type="text/javascript" src="https://lainchan.org/js/prettify.js"></script>
<script type="text/javascript" src="https://lainchan.org/js/hilight.js"></script>
<script>
$( document ).ready(function() {
// On document ready, find all date elements
var s = document.getElementsByClassName("date");
for (var i = 0; i < s.length; i++) {
// Foreach el in document.find(".date")
var el = s[i];
d = new Date(parseInt(el.innerHTML + "000")); // uses milliseconds, hence the extra 000
// change the html of el from an epoch to the formatted local time and date of that epoch
el.innerHTML = d.toLocaleTimeString() + " " + d.toLocaleDateString();
}
});
</script>
</head>
<body>
<h1>IPFS Scraper</h1>
<div id="status">${open("/dev/shm/lainchan-scraper-status", "r").read()}</div>
<div id="content">
<!-- reverse dumped -->
% for post in dumped[::-1]:
<div class="post">
<!-- Generate a link back to the lainchan thread, as well as links to download the ipfs hash from multiple sources, and print the hash itself. -->
<a class="postlink" href="https://lainchan.org/${post["board"]}/res/${post["parent_thread_id"]}.html#q${post["post"]}" target="_blank">Post</a> -
<a class="ipfslink-public" href="https://ipfs.io/ipfs/${post["match"]}">public</a>
<a class="ipfslink-local" href="http://localhost:8080/ipfs/${post["match"]}">local</a> -
${post["match"]}
<span class="date">${post["time"]}</span>
<!-- We must escape the lambda because either mako, mako-server or paste refuses to print unicode characters -->
<div class="embedded">${post["text"].replace(u"\u03bb", "lam").replace('href="/' + post["board"], 'href="https://lainchan.org/' + post["board"])}</div>
</div>
% endfor
<br />
Note that only /tech/ and /&lambda;/ are scraped at this time.<br />
The source can be found on <a href="https://gitla.in/nilesrogoff/lain-ipfs-scraper/">gitla.in/nilesrogoff/lain-ipfs-scraper</a><br />
Hypothetically it should be compatable with any vichan compatable bbs.
</div>
<div id="footer">Niles Rogoff 2016<br /><a href="https://pgp.mit.edu/pks/lookup?op=vindex&search=0xB78B908F23430F80">2048R/23430F80</a></div>
</body>
</html>