batch_anki_import tags

README.md

@@ -66,8 +66,8 @@ Most scripts assume:
 ### Usage:
 
 ```bash
-./extract_anki_audio.py jp [--concat] [--outdir DIR] [--copy-only-new]
-./extract_anki_audio.py es [--concat] [--outdir DIR] [--copy-only-new]
+./audio_extractor.py jp [--concat] [--outdir DIR] [--copy-only-new]
+./audio_extractor.py es [--concat] [--outdir DIR] [--copy-only-new]
 ```
 
 Outputs:
@@ -86,11 +86,20 @@ Outputs:
 ### Usage
 
 ```bash
-./batch_anki_import.sh [jp|es] [--concat] [--outdir DIR]
+./batch_anki_import.sh [jp|es] [--tags TAG1,TAG2,...]
 ```
 
-- Keeps all individual MP3s.
-- If `--concat` is passed, also writes one combined MP3 for the run.
+| Option                     | Description                                                                                      |
+| -------------------------- | ------------------------------------------------------------------------------------------------ |
+| `--tags TAG1,TAG2,...`     | Comma-separated list of tags. `text-to-speech` is always included. Default: `AI-generated`       |
+
+### Tag behavior
+- By default, cards are tagged with `text-to-speech` and `AI-generated`
+- When `--tags` is specified, `text-to-speech` is always included, and `AI-generated` is replaced by the custom tags
+- Examples:
+  - `./batch_anki_import.sh jp` → tags: `text-to-speech`, `AI-generated`
+  - `./batch_anki_import.sh jp --tags manual` → tags: `text-to-speech`, `manual`
+  - `./batch_anki_import.sh es --tags "youtube,media"` → tags: `text-to-speech`, `youtube`, `media`
 
 ### Requirements
 - Anki + AnkiConnect
@@ -100,6 +109,9 @@ Outputs:
 - Japanese: `~/Languages/Anki/sentences_jp.txt`
 - Spanish: `~/Languages/Anki/sentences_es.txt`
 
+### Notes
+- Audio files are generated in a temporary directory and cleaned up after import. No local audio files are retained.
+
 ## word-scraper
 
 Extract frequent words from Anki notes using **AnkiConnect** and **spaCy**.

batch_anki_import.sh

@@ -4,29 +4,32 @@ prog="$(basename "$0")"
 
 print_help() {
   cat <<EOF
-usage: $prog [-h] {es,jp}
+usage: $prog [-h] [--tags TAG1,TAG2,...] {es,jp}
 
 positional arguments:
   {es,jp}
 
 options:
   -h, --help            show this help message and exit
+  --tags TAG1,TAG2,...  comma-separated list of additional tags (default: AI-generated)
+                        text-to-speech is always included
 EOF
 }
 
 arg_error_missing_lang() {
-  echo "usage: $prog [-h] {es,jp}" >&2
+  echo "usage: $prog [-h] [--tags TAG1,TAG2,...] {es,jp}" >&2
   echo "$prog: error: the following arguments are required: lang" >&2
   exit 2
 }
 
 arg_error_unknown() {
-  echo "usage: $prog [-h] {es,jp}" >&2
+  echo "usage: $prog [-h] [--tags TAG1,TAG2,...] {es,jp}" >&2
   echo "$prog: error: unrecognized arguments: $*" >&2
   exit 2
 }
 
 lang=""
+custom_tags=""
 
 while [[ $# -gt 0 ]]; do
   case "$1" in
@@ -34,6 +37,14 @@ while [[ $# -gt 0 ]]; do
       print_help
       exit 0
       ;;
+    --tags)
+      if [[ -z "$2" || "$2" == -* ]]; then
+        echo "$prog: error: --tags requires an argument" >&2
+        exit 2
+      fi
+      custom_tags="$2"
+      shift 2
+      ;;
     jp|es)
       if [[ -n "$lang" ]]; then
         arg_error_unknown "$1"
@@ -49,6 +60,20 @@ done
 
 [[ -z "$lang" ]] && arg_error_missing_lang
 
+# Build tags JSON array - text-to-speech is always included
+TAGS='["text-to-speech"'
+if [[ -n "$custom_tags" ]]; then
+  IFS=',' read -ra tag_array <<< "$custom_tags"
+  for tag in "${tag_array[@]}"; do
+    # Trim whitespace
+    tag="$(echo -e "$tag" | sed 's/^[[:space:]]*//;s/[[:space:]]*$//')"
+    TAGS+=", \"$tag\""
+  done
+else
+  TAGS+=', "AI-generated"'
+fi
+TAGS+=']'
+
 case "$lang" in
   jp)
     DECK_NAME="日本語"
@@ -66,8 +91,6 @@ case "$lang" in
     ;;
 esac
 
-
-TAGS='["AI-generated", "text-to-speech"]'
 count=0
 
 # Use a temporary directory to handle processing