Add basic single URL scraping

scrape-all.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+update_cache() {
+	cache=$(curl "$1" -s)
+}
+
+get_main_ingredients() {
+	if [[ -z "$1" ]]; then
+	  local data=$cache
+	else
+	  local data=$1
+	fi
+	
+	echo "$data" | htmlq -p | grep '<a class="link link--styled" data-component="Link" href="/glossary/.*">.*</a>' | sed 's/^.*<a class="link link--styled" data-component="Link" href=".*">//' | sed 's/<\/a>.*//'
+	echo "$data" | htmlq -p | grep '<!-- -->.*<!-- -->' | sed 's/<!-- -->/@/g' | awk -F@ '{print $2}'
+}
+
+get_json() {
+	if [[ -z "$1" ]]; then
+	  local data=$cache
+	else
+	  local data=$1
+	fi
+	
+	echo "$data" | htmlq -p | grep '<script data-testid="page-schema" type="application/ld+json">' -A1 | tail -n1 | sed 's/<\/script>//' | jq
+}
+
+update_cache "https://www.bbcgoodfood.com/recipes/vegan-banana-bread"
+get_json
+get_main_ingredients