{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "import requests\n",
    "import json\n",
    "import vlc\n",
    "import re\n",
    "import random\n",
    "from IPython.display import Audio\n",
    "\n",
    "def load_json_database(url):\n",
    "    records = []\n",
    "    try:\n",
    "        response = requests.get(url)\n",
    "        response.raise_for_status()  # Raise an error for bad status codes\n",
    "        for line in response.iter_lines(decode_unicode=True):\n",
    "            if line:\n",
    "                try:\n",
    "                    record = json.loads(line)\n",
    "                    records.append(record)\n",
    "                except json.JSONDecodeError as e:\n",
    "                    print(f\"Error parsing JSON: {e}\")\n",
    "    except requests.exceptions.RequestException as e:\n",
    "        print(f\"Error fetching data from URL: {e}\")\n",
    "    return records\n",
    "\n",
    "def search_in_json_database(database, search_word, region):\n",
    "    for record in database:\n",
    "        # 检查 word 字段是否匹配\n",
    "        if record.get('word') == search_word:\n",
    "            # 找到匹配项后，获取美式发音信息\n",
    "            pos_items = record.get('pos_items', [])\n",
    "            for pos_item in pos_items:\n",
    "                pronunciations = pos_item.get('pronunciations', [])\n",
    "                for pronunciation in pronunciations:\n",
    "                    if pronunciation.get('region') == region:\n",
    "                        # 找到美式发音，返回相关信息\n",
    "                        return {\n",
    "                            'pronunciation': pronunciation.get('pronunciation'),\n",
    "                            'audio': pronunciation.get('audio')\n",
    "                        }\n",
    "    # 如果没有找到匹配的 word 字段，返回 'not exist'\n",
    "    return 'not exist'\n",
    "\n",
    "url = \"https://raw.githubusercontent.com/zelic91/camdict/main/cam_dict.refined.json\"\n",
    "\n",
    "json_database = load_json_database(url)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "text =\"\"\"\n",
    "### `w`\n",
    "\n",
    "* \"w\" - week, weird, wife\n",
    "* \"wh\" - white, what, why\n",
    "\n",
    "### `j`\n",
    "\n",
    "* \"y\" - yes, yet, yoke\n",
    "* \"i\" - onion, million\n",
    "* \"j\" - jager, hallelujah\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "words = \"\"\n",
    "phonetics_not_exist = ''\n",
    "lines = text.split(\"\\n\")\n",
    "for line in lines:\n",
    "    line = line.replace(\" `\", \" <span class=\\\"pho\\\">\")\n",
    "    line = line.replace(\"`\", \"</span>\")\n",
    "    if '*' in line:\n",
    "        line = line.replace('\"', \"**\")\n",
    "        examples = line.split(\"-\")[1].split(\",\")\n",
    "        examples = [x.strip() for x in examples]\n",
    "        line = line.replace(\" - \", \"\\n\")\n",
    "        # print(examples)\n",
    "        # wrap examples in span,\n",
    "        for e in examples:\n",
    "            # join e in words with ','\n",
    "            words += e + \",\"\n",
    "            entry_us = search_in_json_database(json_database, e, 'us')\n",
    "            if entry_us == 'not exist':\n",
    "                phonetics = entry_us\n",
    "                phonetics_not_exist += f'{e},'\n",
    "            else:\n",
    "                phonetics = entry_us['pronunciation']    \n",
    "            wrapped_e = f'\\t- {e} <span class=\"pho alt\">{phonetics}</span> <span class=\"speak-word-inline\" data-audio-us-male=\"/audios/us/{e}-us-male.mp3\" data-audio-us-female=\"/audios/us/{e}-us-female.mp3\"></span>\\n'\n",
    "            line = line.replace(e, wrapped_e).replace(',', '').strip()\n",
    "            \n",
    "\n",
    "    print(line)\n",
    "print(f'phonetics_not_exist: {phonetics_not_exist}')\n",
    "print('\\n'+words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import asyncio\n",
    "import edge_tts\n",
    "import pygame\n",
    "text = words.rstrip(\",\")\n",
    "Wordlist = text.split(\",\")\n",
    "\n",
    "print(Wordlist)\n",
    "for w in Wordlist:\n",
    "  # for VOICE in ['en-US-GuyNeural', 'en-US-JennyNeural', 'en-GB-RyanNeural', 'en-GB-SoniaNeural']:\n",
    "  for VOICE in ['en-US-GuyNeural', 'en-US-MichelleNeural']:\n",
    "    w = w.strip()\n",
    "    # OUTPUT_FILE = f\"{w}-{VOICE.replace('EricNeural', 'Guy-Male').replace('JennyNeural', 'Jenny-Female').replace('RyanNeural', 'Ryan-Male').replace('SoniaNeural', 'Sonia-Female').lower()}.mp3\"\n",
    "    OUTPUT_FILE = f\"{w}-{VOICE.replace('GuyNeural', 'Male').replace('MichelleNeural', 'Female').replace('en-', '').lower()}.mp3\"\n",
    "    communicate = edge_tts.Communicate(w, VOICE)\n",
    "    await communicate.save(OUTPUT_FILE) \n",
    "  print(w)\n",
    "print(\"Files created!\") "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}