From 00e4620c819920ea386724be21fd984ccb28b82e Mon Sep 17 00:00:00 2001
From: Flinner <flinner.hlqn@aleeas.com>
Date: Wed, 18 Aug 2021 17:57:52 +0300
Subject: [PATCH] feat: scrape paul's site

---
 bin/bin/paul.sh | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100755 bin/bin/paul.sh

diff --git a/bin/bin/paul.sh b/bin/bin/paul.sh
new file mode 100755
index 0000000..701d2c4
--- /dev/null
+++ b/bin/bin/paul.sh
@@ -0,0 +1,48 @@
+#!/bin/sh
+
+
+exit_m() {
+  echo "$1"
+  exit 1
+}
+
+# curl with cache! (in "/tmp")
+curl_cache(){
+  local cache_path=`echo $1 |  sed 's|/|_|g'`
+  local cache_path="/tmp/$cache_path"
+
+  [ -f "$cache_path" ] || curl -s "$1" -o "$cache_path"
+
+  echo "$cache_path"
+}
+
+
+domain="https://tutorial.math.lamar.edu/"
+file=`curl_cache "$1"` # main file, that has all questions
+q_num=$(( $2 - 1 )) #numbering starts at 1
+
+# naive method to check for only args!
+[ -n "$file" ]  || exit_m  "No Files Given"
+[ -n "$q_num" ] || exit_m  "No Questoin Number Given!"
+[ ! -n "$3" ]   || exit_m  "Incorrect number of args :("
+
+
+# get all practice questions
+question_text=`cat $file | pup 'body .practice-problems li json{}' |
+  jq ".[${q_num}].text"  | tr -d '"'`
+
+# get all solution *links*
+solution_path=`cat $file | pup 'body .practice-problems li json{}' |
+  jq -r ".[${q_num}].children[0].href"`
+solution_url="$domain/$solution_path"
+
+
+# ====  get solution =========
+# download if not already downloaded
+solution_path=`curl_cache "$solution_url"`
+
+echo "$question_text"
+echo "\n"
+cat "$solution_path" | pup 'body .soln-content p text{}'
+
+