From 3e2254d676193ef6c628250617c675b9ff724b4c Mon Sep 17 00:00:00 2001
From: Laria Carolin Chabowski <laria@laria.me>
Date: Wed, 11 Mar 2020 22:35:27 +0100
Subject: Initial commit

falseknees-atom.lua is a simple scraper of falseknees.com/archive that
outputs an atom feed for consumption by newsboat or similar newsreaders
that can get a feed from some external command.
---
 falseknees-atom.lua | 120 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 120 insertions(+)
 create mode 100755 falseknees-atom.lua

(limited to 'falseknees-atom.lua')

diff --git a/falseknees-atom.lua b/falseknees-atom.lua
new file mode 100755
index 0000000..584617c
--- /dev/null
+++ b/falseknees-atom.lua
@@ -0,0 +1,120 @@
+#!/usr/bin/lua
+
+local string = require "string"
+local http = require "socket.http"
+
+local function must_get_page(url)
+  local data, status = http.request(url)
+  if status ~= 200 then
+    error("Failed getting '" .. url .. "': Got status " .. status .. "\n")
+  end
+  return data
+end
+
+local function xmlesc(text)
+  text = string.gsub(text, "&", "&amp;")
+  text = string.gsub(text, "<", "&lt;")
+  text = string.gsub(text, ">", "&gt;")
+  text = string.gsub(text, '"', "&quot;")
+  text = string.gsub(text, "'", "&apos;")
+  return text
+end
+
+local function unesc_html(s)
+  return string.gsub(s, '&([^;]+);', {
+    amp = "&",
+    lt = "<",
+    gt = ">",
+    quot = '"',
+    apos = "'",
+  })
+end
+
+local months = {
+  January = 1,
+  February = 2,
+  March = 3,
+  April = 4,
+  May = 5,
+  June = 6,
+  July = 7,
+  August = 8,
+  September = 9,
+  October = 10,
+  November = 11,
+  December = 12,
+}
+
+-- Get the permanent URL of the current comic (index.html)
+local function resolve_index()
+  local indexsrc = must_get_page("https://falseknees.com/index.html")
+  local url = string.match(indexsrc, '<meta%s+http%-equiv="refresh"%s+content="%d+;%s*URL=([^"]+)"%s*/?>')
+  return unesc_html(url)
+end
+
+local pagesrc = must_get_page("https://falseknees.com/archive.html")
+
+local maxdate
+local entries = {}
+
+local PATTERN = '<a href="([^"]+)">(%w+) (%d+)%w+, (%d+)%s*%-%s*([^<>]-)</a>'
+for url, monthname, day, year, title in string.gmatch(pagesrc, PATTERN) do
+  url = unesc_html(url)
+  monthname = unesc_html(monthname)
+  day = tonumber(unesc_html(day), 10)
+  year = tonumber(unesc_html(year), 10)
+  title = unesc_html(title)
+
+  if url == "index.html" then
+    url = resolve_index()
+  end
+
+  if not url then goto continue end
+
+  url = "https://falseknees.com/" .. url
+
+  local month = assert(months[monthname], "unknown month")
+
+  -- We fon't know the time, lets assume midnight at UTC+0
+  local date = string.format("%04d-%02d-%02dT00:00:00Z", year, month, day)
+
+  if not maxdate or date > maxdate then
+    maxdate = date
+  end
+
+  entries[#entries+1] = {
+    url = url,
+    title = title,
+    date = date
+  }
+
+  ::continue::
+end
+
+if not maxdate then
+  error("No entry successfully parsed")
+end
+
+-- A UUID URN with a UUID generated by `uuid -r`.
+local FEED_ID = "urn:uuid:7e86b012-c226-41b3-945e-bab3341c65e9"
+
+print(string.format([[<?xml version="1.0" encoding="utf-8"?>
+<feed xmlns="http://www.w3.org/2005/Atom">
+  <title>False Knees</title>
+  <link href="http://example.org/" />
+  <id>%s</id>
+  <author><name>Joshua Barkman</name></author>
+  <updated>%s</updated>]], xmlesc(FEED_ID), xmlesc(maxdate)))
+
+for _, entry in ipairs(entries) do
+  print(string.format([[
+    <entry>
+      <title>%s</title>
+      <link rel="alternate" type="text/html" href="%s" />
+      <id>%s</id>
+      <updated>%s</updated>
+    </entry>
+  ]], xmlesc(entry.title), xmlesc(entry.url), xmlesc(FEED_ID .. "#" .. entry.url), xmlesc(entry.date)))
+end
+
+print("</feed>")
-- 
cgit v1.2.3-54-g00ecf