Created
November 9, 2022 21:00
-
-
Save skuro/cd8556772f9223273816f822fbb5b0a4 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
(ns io.codehopper.fun-with-redis | |
(:require [taoensso.carmine :as car :refer (wcar)] | |
[skyscraper.core :as sky] | |
[skyscraper.cache :as sky.cache] | |
[reaver])) | |
(def seed | |
[{:url "https://clojuredays.org", | |
:processor :page | |
:page 2022}]) | |
(def redis {:pool {} :spec {:uri "redis://127.0.0.1:6379"}}) | |
(defn redis-cache | |
[redis-conn] | |
(reify | |
sky.cache/CacheBackend | |
(save-blob [_ key blob metadata] | |
(car/wcar redis-conn | |
(car/set key {:blob blob | |
:meta metadata}))) | |
(load-blob [_ key] | |
(car/wcar redis-conn | |
(car/get key))) | |
java.io.Closeable | |
(close [_] | |
nil))) | |
(sky/defprocessor :page | |
:cache-template "dcd/:page" | |
:skyscraper.db/columns [:sponsor :year] | |
:process-fn (fn [doc ctx] | |
(concat | |
(reaver/extract-from doc | |
"#sponsors a" | |
[:sponsor :year] | |
".sponsor" (reaver/attr :href) | |
".sponsor" (constantly (str (:page ctx)))) | |
))) | |
(defn run [cache] | |
(sky/scrape! seed | |
:html-cache cache | |
:db-file "/tmp/dcd.db" | |
:parse-fn sky/parse-reaver)) | |
(comment | |
(def _x (redis-cache redis)) | |
(sky.cache/save-blob _x :cache-key "I'm a blob" {:meta "too-meta"}) | |
(sky.cache/load-blob _x :cache-key) | |
(car/wcar redis | |
(car/get "dcd/1")) | |
(car/wcar redis | |
(car/keys "*")) | |
(run (redis-cache redis))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment