setup.sh

@@ -9,10 +9,5 @@ elif [ ! -z "$1" ]; then
 fi
 
 # Installs prerequisites for some of the system scripts
-# Redundant package names are acceptable as this improves readability
 
-# General
 python -m pip install python-dotenv
-
-# Stasher
-python -m pip install requests lxml python-dotenv

stash.sh

@@ -0,0 +1,91 @@
+#!/bin/bash
+
+STASH_IMPORT_DIR=""
+STASH_API_KEY=""
+STASH_HOST=""
+STASH_PORT=0
+STASH_YTDLP_FORMAT="%(title)s [%(id)s].%(ext)s"  # https://github.com/yt-dlp/yt-dlp#output-template
+STASH_PRINT_PREFIX="Get: "
+STASH_URL_FIXERS=()
+
+source .env
+
+TARGET_DIR=$(readlink -m "$STASH_IMPORT_DIR/$(date +%Y%m)")
+mkdir -p $TARGET_DIR
+
+update_stash() {
+    echo "Running scan for new items in Stash..."
+    curl -S -s -o /dev/null -X POST -H "ApiKey: $STASH_API_KEY" -H "Content-Type: application/json" --data '{ "query": "mutation { metadataScan (input:{useFileMetadata: false})}" }' $STASH_HOST:$STASH_PORT/graphql
+}
+
+find_booru_artist() {
+    # TODO: Reduce html to just name
+    PAGE_URL="$1"
+    ARTIST_NAME=$(curl -s "$PAGE_URL" | xmllint --format --html -xpath "/html/body/div[1]/section/ul/li[1]/a/text()" - 2>/dev/null)
+    ARTIST_NAME=$(echo $ARTIST_NAME | tr -dc '[:alnum:]\n\r' | tr '[:upper:]' '[:lower:]' | tr ' ' '_')
+    echo $ARTIST_NAME__
+}
+
+download_file() {
+    FILE_URL="$1"
+
+    extensions="(jpg|JPG|jpeg|JPEG|png|PNG|gif|GIF|mp4|MP4)"
+    rgx_file="^.*\.$extensions$"
+    rgx_filename="[A-Za-z0-9_]*.$extensions"
+    rgx_booru='https?://[a-z.]+/(index\.php.*id=([0-9]+)|posts/([0-9]+))'
+    rgx_booru_v1='(https?://.*/original/([A-Za-z0-9/_]*\.(jpg|jpeg|png|gif|mp4))|https?://img[a-z0-9.]+\.[a-z]+\.com/(?:images|/samples)/.*/([_0-9a-z]*\.(jpg|jpeg|png|gif|mp4)))'
+    rgx_booru_v2='(https?://.*/original/([A-Za-z0-9/_]*\.(jpg|jpeg|png|gif|mp4))|https?://img[a-z0-9.]+\.[a-z]+\.com/images/([0-9a-z]+/)+([_0-9a-z]+\.(jpg|jpeg|png|gif|mp4)))'
+
+    if [[ $FILE_URL =~ $rgx_booru ]]; then
+        ARTIST=$(find_booru_artist "$FILE_URL")
+        echo "Artist is: $ARTIST"
+	FILE_URL=$(curl -s "$FILE_URL" | grep -Eo "$rgx_booru_v2" -m1 | head -1) #| grep '__' -m1)
+    fi
+
+    if [ -z "$FILE_URL" ]; then
+        return 1
+    fi
+
+    if [[ $FILE_URL =~ $rgx_file ]]; then
+	echo $STASH_PRINT_PREFIX $(echo $FILE_URL | grep -Eo "$rgx_filename")
+        curl -sO "$FILE_URL" --output-dir "$2/"
+        return $?
+    else
+        echo $STASH_PRINT_PREFIX $FILE_URL
+        yt-dlp $FILE_URL -o "$2/$3"
+        return $?
+    fi
+}
+
+if [ $1 == "--update" ]; then
+    update_stash
+    exit $?
+fi
+
+rgx_url='^http(s?):\/\/[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b[-a-zA-Z0-9@:%_\+.~#?&\/\/=]*$'
+
+if [[ $1 =~ $rgx_url ]]; then
+    # Download using yt-dlp
+    download_file "$1" "$TARGET_DIR" "$STASH_YTDLP_FORMAT"
+    if [ $? -ne 0 ]; then
+       echo "Stopped"
+       exit 1
+    fi
+else
+    isFile=$(file -0 "$1" | cut -d $'\0' -f2)
+    case "$isFile" in
+        (*text*)
+            # Download as multiple URLs from the provided source file
+            echo "Reading list of $(wc -l $1 | awk '{print $1}') URL(s)"
+            while read p; do
+                download_file "$p" "$TARGET_DIR" "$STASH_YTDLP_FORMAT"
+            done <$1
+            ;;
+        (*)
+            rsync "$1" "$TARGET_DIR/"
+            ;;
+    esac
+fi
+
+# Update stash
+update_stash