scraping the xerox printers

Gemfile

@@ -0,0 +1,5 @@
+source "https://rubygems.org"
+
+gem "mechanize", "~> 2.7"
+gem "open4"
+gem "influxdb", "~> 0.8"

Gemfile.lock

@@ -0,0 +1,44 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    connection_pool (2.2.2)
+    domain_name (0.5.20190701)
+      unf (>= 0.0.5, < 1.0.0)
+    http-cookie (1.0.3)
+      domain_name (~> 0.5)
+    influxdb (0.8.0)
+    mechanize (2.7.6)
+      domain_name (~> 0.5, >= 0.5.1)
+      http-cookie (~> 1.0)
+      mime-types (>= 1.17.2)
+      net-http-digest_auth (~> 1.1, >= 1.1.1)
+      net-http-persistent (>= 2.5.2)
+      nokogiri (~> 1.6)
+      ntlm-http (~> 0.1, >= 0.1.1)
+      webrobots (>= 0.0.9, < 0.2)
+    mime-types (3.3.1)
+      mime-types-data (~> 3.2015)
+    mime-types-data (3.2019.1009)
+    mini_portile2 (2.4.0)
+    net-http-digest_auth (1.4.1)
+    net-http-persistent (3.1.0)
+      connection_pool (~> 2.2)
+    nokogiri (1.10.9)
+      mini_portile2 (~> 2.4.0)
+    ntlm-http (0.1.1)
+    open4 (1.3.4)
+    unf (0.1.4)
+      unf_ext
+    unf_ext (0.0.7.7)
+    webrobots (0.1.2)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  influxdb (~> 0.8)
+  mechanize (~> 2.7)
+  open4
+
+BUNDLED WITH
+   1.17.3

default.nix

@@ -0,0 +1,27 @@
+{ pkgs ? import <nixpkgs> {} }:
+
+with pkgs;
+
+let
+  gems = bundlerEnv rec {
+    name = "scrapers";
+
+    inherit ruby;
+    # expects Gemfile, Gemfile.lock and gemset.nix in the same directory
+    # > nix-shell -p bundler --run 'bundle lock --update'
+    # > nix-shell -p bundix --run bundix
+    gemdir = ./.;
+  };
+  wrapScript = name: script:
+    stdenv.mkDerivation {
+      inherit name script;
+      buildInputs = [ gems.wrappedRuby ];
+
+      buildCommand = ''
+        install -D -m755 $script $out/bin/${name}
+        patchShebangs $out/bin/${name}
+      '';
+    };
+in {
+  xerox = wrapScript "xerox" ./xerox/scrape.rb;
+}

gemset.nix

@@ -0,0 +1,169 @@
+{
+  connection_pool = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "0lflx29mlznf1hn0nihkgllzbj8xp5qasn8j7h838465pi399k68";
+      type = "gem";
+    };
+    version = "2.2.2";
+  };
+  domain_name = {
+    dependencies = ["unf"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "0lcqjsmixjp52bnlgzh4lg9ppsk52x9hpwdjd53k8jnbah2602h0";
+      type = "gem";
+    };
+    version = "0.5.20190701";
+  };
+  http-cookie = {
+    dependencies = ["domain_name"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "004cgs4xg5n6byjs7qld0xhsjq3n6ydfh897myr2mibvh6fjc49g";
+      type = "gem";
+    };
+    version = "1.0.3";
+  };
+  influxdb = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "11q5pys13cp9rxhg1gihblqi597b6nfsfz3ghdij0zdf713pwwc3";
+      type = "gem";
+    };
+    version = "0.8.0";
+  };
+  mechanize = {
+    dependencies = ["domain_name" "http-cookie" "mime-types" "net-http-digest_auth" "net-http-persistent" "nokogiri" "ntlm-http" "webrobots"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "00834zv6s68g3x00s4kcgdry51s88qj0kjygnwhpg8k67kdihcrx";
+      type = "gem";
+    };
+    version = "2.7.6";
+  };
+  mime-types = {
+    dependencies = ["mime-types-data"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "1zj12l9qk62anvk9bjvandpa6vy4xslil15wl6wlivyf51z773vh";
+      type = "gem";
+    };
+    version = "3.3.1";
+  };
+  mime-types-data = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "18x61fc36951vw7f74gq8cyybdpxvyg5d0azvqhrs82ddw3v16xh";
+      type = "gem";
+    };
+    version = "3.2019.1009";
+  };
+  mini_portile2 = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "15zplpfw3knqifj9bpf604rb3wc1vhq6363pd6lvhayng8wql5vy";
+      type = "gem";
+    };
+    version = "2.4.0";
+  };
+  net-http-digest_auth = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "1nq859b0gh2vjhvl1qh1zrk09pc7p54r9i6nnn6sb06iv07db2jb";
+      type = "gem";
+    };
+    version = "1.4.1";
+  };
+  net-http-persistent = {
+    dependencies = ["connection_pool"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "1bink2g0a94zh9kmb96rrh48rkbkdpimljy2370z5liixvy3gdpa";
+      type = "gem";
+    };
+    version = "3.1.0";
+  };
+  nokogiri = {
+    dependencies = ["mini_portile2"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "12j76d0bp608932xkzmfi638c7aqah57l437q8494znzbj610qnm";
+      type = "gem";
+    };
+    version = "1.10.9";
+  };
+  ntlm-http = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "0yx01ffrw87wya1syivqzf8hz02axk7jdpw6aw221xwvib767d36";
+      type = "gem";
+    };
+    version = "0.1.1";
+  };
+  open4 = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "1cgls3f9dlrpil846q0w7h66vsc33jqn84nql4gcqkk221rh7px1";
+      type = "gem";
+    };
+    version = "1.3.4";
+  };
+  unf = {
+    dependencies = ["unf_ext"];
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "0bh2cf73i2ffh4fcpdn9ir4mhq8zi50ik0zqa1braahzadx536a9";
+      type = "gem";
+    };
+    version = "0.1.4";
+  };
+  unf_ext = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "0wc47r23h063l8ysws8sy24gzh74mks81cak3lkzlrw4qkqb3sg4";
+      type = "gem";
+    };
+    version = "0.0.7.7";
+  };
+  webrobots = {
+    groups = ["default"];
+    platforms = [];
+    source = {
+      remotes = ["https://rubygems.org"];
+      sha256 = "19ndcbba8s8m62hhxxfwn83nax34rg2k5x066awa23wknhnamg7b";
+      type = "gem";
+    };
+    version = "0.1.2";
+  };
+}

xerox/scrape.rb

@@ -0,0 +1,65 @@
+#!/usr/bin/env ruby
+
+require 'open-uri'
+require 'influxdb'
+
+HOST = ARGV[0]
+USER = ARGV[1]
+PASSWORD = ARGV[2]
+
+def scrape_paper_supply
+  results = {}
+
+  open("http://#{HOST}/sttray.htm", :http_basic_authentication => [USER, PASSWORD])
+    .read()
+    .scan(/\['Tray (.+?)',\d+,(\d+),/) do |m|
+
+    results[m[0]] = m[1].to_i
+  end
+
+  results
+end
+
+def scrape_consumables
+  results = {}
+
+  doc = open("http://#{HOST}/stsply.htm", :http_basic_authentication => [USER, PASSWORD])
+          .read()
+          .force_encoding("ISO-8859-1")
+          .encode("utf-8", replace: nil)
+
+  doc.scan(/info.concat\(\[\[(.+?)\);/) do |m|
+    m[0].scan(/\['(.+?)',(\d+),(\d+)\]/) do |m|
+      results[m[0]] = {
+        :status => m[1].to_i,
+        :life => m[2].to_i,
+      }
+    end
+  end
+
+  results
+end
+
+paper_supply = scrape_paper_supply
+consumables = scrape_consumables
+
+db = InfluxDB::Client.new(url: "http://grafana.hq.c3d2.de:8086/drucker")
+db.write_points [ {
+  series: "paper_supply",
+  tags: { host: HOST },
+  values: paper_supply,
+}, {
+  series: "consumables_status",
+  tags: { host: HOST },
+  values: consumables.inject({}) do |status, consumable|
+    status[consumable[0]] = consumable[1][:status]
+    status
+  end,
+}, {
+  series: "consumables_life",
+  tags: { host: HOST },
+  values: consumables.inject({}) do |life, consumable|
+    life[consumable[0]] = consumable[1][:life]
+    life
+  end,
+} ], 'm'