{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import ast\n",
    "import glob\n",
    "import json\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import labelbox as lb\n",
    "\n",
    "\n",
    "from langdetect import detect\n",
    "from bs4 import BeautifulSoup\n",
    "from better_profanity import profanity\n",
    "from suno_utils.utils.s3 import check_s3_file_exists\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_3393705/1278973186.py:3: DtypeWarning: Columns (76,91) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df = pd.read_csv(\"/home/tony/Data/Preference/30b_v1/interesting_clips_v4_t_2_20240827_slice.csv\")\n"
     ]
    }
   ],
   "source": [
    "# read csv file\n",
    "#df = pd.read_csv(\"/home/tony/Data/Preference/30b_v1/interesting_clips_v4_t_1_20240808_slice.csv\")\n",
    "df = pd.read_csv(\"/home/tony/Data/Preference/30b_v1/interesting_clips_v4_t_2_20240827_slice.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "22723.0\n"
     ]
    }
   ],
   "source": [
    "print(len(df)/2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "def is_english(text):\n",
    "    try:\n",
    "        return True if detect(text) == \"en\" else False\n",
    "    except:\n",
    "        return False\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Basic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a dataset\n",
    "client = lb.Client(api_key=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VySWQiOiJjbHppbmJnY2wwMDYyMDd5bWg2enhiMTd6Iiwib3JnYW5pemF0aW9uSWQiOiJjbHppbmJnY2QwMDYxMDd5bWM4cjM5cHdzIiwiYXBpS2V5SWQiOiJjbHp3cmU3ZnQwYjFzMDd6aWRrNTFnb21mIiwic2VjcmV0IjoiMGU5M2MwNmU4ZWI1Y2Y3NTlmNTk5YTk5MzIwOTU5MzQiLCJpYXQiOjE3MjM4MTU3NTcsImV4cCI6MjM1NDk2Nzc1N30.Z6gZwlzQ85KrqGOydqCdo1RVmUhOEntpev2HhNso4PU\")\n",
    "dataset = client.create_dataset(name=\"ab-preference-test\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_clip_details(clip_item):\n",
    "    s3_id = clip_item[\"s3_id\"]\n",
    "    string_data = clip_item[\"metadata\"]\n",
    "    dict_data = ast.literal_eval(string_data)\n",
    "    lyrics = dict_data[\"prompt\"]\n",
    "    tags = dict_data[\"tags\"]\n",
    "\n",
    "    return s3_id, lyrics, tags"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 1\n",
      "0001b51e-bb6c-46b0-b491-fc2422bfe866\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0001b51e-bb6c-46b0-b491-fc2422bfe866.html\n",
      "upload: ../outputs/html-20270823/0001b51e-bb6c-46b0-b491-fc2422bfe866.html to s3://suno-annotation-public/preference-20270823/0001b51e-bb6c-46b0-b491-fc2422bfe866.html\n",
      "2 3\n",
      "00042143-14ea-43f0-89d7-a4814fe00c47\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00042143-14ea-43f0-89d7-a4814fe00c47.html\n",
      "upload: ../outputs/html-20270823/00042143-14ea-43f0-89d7-a4814fe00c47.html to s3://suno-annotation-public/preference-20270823/00042143-14ea-43f0-89d7-a4814fe00c47.html\n",
      "4 5\n",
      "0006ff4c-3623-4ac7-8285-c2292abdfefb\n",
      "Skipping 0006ff4c-3623-4ac7-8285-c2292abdfefb because it is not in English\n",
      "6 7\n",
      "0007bf87-3ca9-4406-9e45-fa70a31165d5\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0007bf87-3ca9-4406-9e45-fa70a31165d5.html\n",
      "upload: ../outputs/html-20270823/0007bf87-3ca9-4406-9e45-fa70a31165d5.html to s3://suno-annotation-public/preference-20270823/0007bf87-3ca9-4406-9e45-fa70a31165d5.html\n",
      "8 9\n",
      "0009c697-f880-405a-abc4-cb7a5d44af68\n",
      "Skipping 0009c697-f880-405a-abc4-cb7a5d44af68 because it is not in English\n",
      "10 11\n",
      "000ff6df-da91-49c6-ba02-22a2bf677857\n",
      "Skipping 000ff6df-da91-49c6-ba02-22a2bf677857 because it contains profanity\n",
      "12 13\n",
      "001b7be8-0b08-4d98-9514-4eca0be01648\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/001b7be8-0b08-4d98-9514-4eca0be01648.html\n",
      "upload: ../outputs/html-20270823/001b7be8-0b08-4d98-9514-4eca0be01648.html to s3://suno-annotation-public/preference-20270823/001b7be8-0b08-4d98-9514-4eca0be01648.html\n",
      "14 15\n",
      "001c6edd-e892-48e5-9e86-32905b62e8d6\n",
      "Skipping 001c6edd-e892-48e5-9e86-32905b62e8d6 because it is not in English\n",
      "16 17\n",
      "001c8a9a-8967-4dc4-9a30-fb263942575f\n",
      "Skipping 001c8a9a-8967-4dc4-9a30-fb263942575f because it is not in English\n",
      "18 19\n",
      "001da941-e77d-4952-9d42-2617fc36dde4\n",
      "Skipping 001da941-e77d-4952-9d42-2617fc36dde4 because it contains profanity\n",
      "20 21\n",
      "001db825-7aef-43ae-94ee-3ee6c0887cb6\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/001db825-7aef-43ae-94ee-3ee6c0887cb6.html\n",
      "upload: ../outputs/html-20270823/001db825-7aef-43ae-94ee-3ee6c0887cb6.html to s3://suno-annotation-public/preference-20270823/001db825-7aef-43ae-94ee-3ee6c0887cb6.html\n",
      "22 23\n",
      "001ed20c-3e74-47d8-84f6-60b3d7c98fc6\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/001ed20c-3e74-47d8-84f6-60b3d7c98fc6.html\n",
      "upload: ../outputs/html-20270823/001ed20c-3e74-47d8-84f6-60b3d7c98fc6.html to s3://suno-annotation-public/preference-20270823/001ed20c-3e74-47d8-84f6-60b3d7c98fc6.html\n",
      "24 25\n",
      "001f8f83-6502-4186-973a-0910c89e4bfd\n",
      "Skipping 001f8f83-6502-4186-973a-0910c89e4bfd because it contains profanity\n",
      "26 27\n",
      "0023ae27-9eb7-460f-908d-8120cc0aaa3c\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0023ae27-9eb7-460f-908d-8120cc0aaa3c.html\n",
      "upload: ../outputs/html-20270823/0023ae27-9eb7-460f-908d-8120cc0aaa3c.html to s3://suno-annotation-public/preference-20270823/0023ae27-9eb7-460f-908d-8120cc0aaa3c.html\n",
      "28 29\n",
      "0023f9dd-9a69-4f92-b7fc-55fb44e0ffee\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0023f9dd-9a69-4f92-b7fc-55fb44e0ffee.html\n",
      "upload: ../outputs/html-20270823/0023f9dd-9a69-4f92-b7fc-55fb44e0ffee.html to s3://suno-annotation-public/preference-20270823/0023f9dd-9a69-4f92-b7fc-55fb44e0ffee.html\n",
      "30 31\n",
      "0029d47a-4917-47de-bc9f-579d8593de78\n",
      "Skipping 0029d47a-4917-47de-bc9f-579d8593de78 because it is not in English\n",
      "32 33\n",
      "002d20d4-c61f-49ee-a96a-f5a202afc641\n",
      "Skipping 002d20d4-c61f-49ee-a96a-f5a202afc641 because it contains profanity\n",
      "34 35\n",
      "00319ef9-bbbf-4cc2-822a-69cf89d9b8d9\n",
      "Skipping 00319ef9-bbbf-4cc2-822a-69cf89d9b8d9 because it contains profanity\n",
      "36 37\n",
      "003381e8-4e5b-452c-a0e5-20b94e81dc6f\n",
      "Skipping 003381e8-4e5b-452c-a0e5-20b94e81dc6f because it is not in English\n",
      "38 39\n",
      "0036af11-33fb-4661-b5a7-347d3d85f87d\n",
      "Skipping 0036af11-33fb-4661-b5a7-347d3d85f87d because it is not in English\n",
      "40 41\n",
      "0036cea8-9680-45f2-b2b7-f9c90b8bea6a\n",
      "Skipping 0036cea8-9680-45f2-b2b7-f9c90b8bea6a because it is not in English\n",
      "42 43\n",
      "00389653-7e29-48d7-a938-5429fa052a5d\n",
      "Skipping 00389653-7e29-48d7-a938-5429fa052a5d because it is not in English\n",
      "44 45\n",
      "003b4ab1-cc25-4ae0-b4c1-8dfb681188e6\n",
      "Skipping 003b4ab1-cc25-4ae0-b4c1-8dfb681188e6 because it is not in English\n",
      "46 47\n",
      "003d6841-e03f-468e-8f31-d0be737b0f84\n",
      "Skipping 003d6841-e03f-468e-8f31-d0be737b0f84 because it contains profanity\n",
      "48 49\n",
      "0040069e-ac46-4bf0-a984-d5b7c66debb8\n",
      "Skipping 0040069e-ac46-4bf0-a984-d5b7c66debb8 because it is not in English\n",
      "50 51\n",
      "0045d8ea-9556-4091-8d64-385f726d90f7\n",
      "Skipping 0045d8ea-9556-4091-8d64-385f726d90f7 because it is not in English\n",
      "52 53\n",
      "0047c838-2bcd-4b0d-ad1f-754c0507a6fb\n",
      "Skipping 0047c838-2bcd-4b0d-ad1f-754c0507a6fb because it contains profanity\n",
      "54 55\n",
      "004a2290-0060-4045-acce-8e191c03a37b\n",
      "Skipping 004a2290-0060-4045-acce-8e191c03a37b because it is not in English\n",
      "56 57\n",
      "004a6f97-b337-497b-8967-5e9ca1507aa6\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/004a6f97-b337-497b-8967-5e9ca1507aa6.html\n",
      "upload: ../outputs/html-20270823/004a6f97-b337-497b-8967-5e9ca1507aa6.html to s3://suno-annotation-public/preference-20270823/004a6f97-b337-497b-8967-5e9ca1507aa6.html\n",
      "58 59\n",
      "004ce7fe-83a0-4987-b8c3-4172b16238d9\n",
      "Skipping 004ce7fe-83a0-4987-b8c3-4172b16238d9 because it is not in English\n",
      "60 61\n",
      "0051065f-14f0-4822-95a9-74507345a446\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0051065f-14f0-4822-95a9-74507345a446.html\n",
      "upload: ../outputs/html-20270823/0051065f-14f0-4822-95a9-74507345a446.html to s3://suno-annotation-public/preference-20270823/0051065f-14f0-4822-95a9-74507345a446.html\n",
      "62 63\n",
      "0051d439-525e-4ba5-9e52-81f526637f9c\n",
      "Skipping 0051d439-525e-4ba5-9e52-81f526637f9c because it is not in English\n",
      "64 65\n",
      "0055791d-30d2-4c88-930b-3ba648c9c58e\n",
      "Skipping 0055791d-30d2-4c88-930b-3ba648c9c58e because it is not in English\n",
      "66 67\n",
      "0056cdb3-7689-42ef-b8c0-dcf5597f3952\n",
      "Skipping 0056cdb3-7689-42ef-b8c0-dcf5597f3952 because it is not in English\n",
      "68 69\n",
      "00581ba4-ca5c-4a42-b125-a2918012d5b4\n",
      "Skipping 00581ba4-ca5c-4a42-b125-a2918012d5b4 because it is not in English\n",
      "70 71\n",
      "005a93a2-f4fe-46af-89eb-cc7b7eb51f08\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/005a93a2-f4fe-46af-89eb-cc7b7eb51f08.html\n",
      "upload: ../outputs/html-20270823/005a93a2-f4fe-46af-89eb-cc7b7eb51f08.html to s3://suno-annotation-public/preference-20270823/005a93a2-f4fe-46af-89eb-cc7b7eb51f08.html\n",
      "72 73\n",
      "005da623-01ee-4e63-9445-ad51fdfd8f21\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/005da623-01ee-4e63-9445-ad51fdfd8f21.html\n",
      "upload: ../outputs/html-20270823/005da623-01ee-4e63-9445-ad51fdfd8f21.html to s3://suno-annotation-public/preference-20270823/005da623-01ee-4e63-9445-ad51fdfd8f21.html\n",
      "74 75\n",
      "005ef189-a18a-466a-b8b2-8c6e3a5a8e97\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/005ef189-a18a-466a-b8b2-8c6e3a5a8e97.html\n",
      "upload: ../outputs/html-20270823/005ef189-a18a-466a-b8b2-8c6e3a5a8e97.html to s3://suno-annotation-public/preference-20270823/005ef189-a18a-466a-b8b2-8c6e3a5a8e97.html\n",
      "76 77\n",
      "0062d8e4-5b47-486b-9bc0-fcfe39308a77\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0062d8e4-5b47-486b-9bc0-fcfe39308a77.html\n",
      "upload: ../outputs/html-20270823/0062d8e4-5b47-486b-9bc0-fcfe39308a77.html to s3://suno-annotation-public/preference-20270823/0062d8e4-5b47-486b-9bc0-fcfe39308a77.html\n",
      "78 79\n",
      "0064466a-2c85-45a7-b6c4-6463cd7973da\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0064466a-2c85-45a7-b6c4-6463cd7973da.html\n",
      "upload: ../outputs/html-20270823/0064466a-2c85-45a7-b6c4-6463cd7973da.html to s3://suno-annotation-public/preference-20270823/0064466a-2c85-45a7-b6c4-6463cd7973da.html\n",
      "80 81\n",
      "00705382-4ae9-4dd3-b8c9-1a248cd1fcb9\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00705382-4ae9-4dd3-b8c9-1a248cd1fcb9.html\n",
      "upload: ../outputs/html-20270823/00705382-4ae9-4dd3-b8c9-1a248cd1fcb9.html to s3://suno-annotation-public/preference-20270823/00705382-4ae9-4dd3-b8c9-1a248cd1fcb9.html\n",
      "82 83\n",
      "007403b2-8eb4-44f1-8fb7-9213afa134d8\n",
      "Skipping 007403b2-8eb4-44f1-8fb7-9213afa134d8 because it is not in English\n",
      "84 85\n",
      "0074ee97-e041-40df-81e5-32b2aa7bf68c\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0074ee97-e041-40df-81e5-32b2aa7bf68c.html\n",
      "upload: ../outputs/html-20270823/0074ee97-e041-40df-81e5-32b2aa7bf68c.html to s3://suno-annotation-public/preference-20270823/0074ee97-e041-40df-81e5-32b2aa7bf68c.html\n",
      "86 87\n",
      "007bc0c3-3e63-4577-9a60-7cdd701ada9d\n",
      "Skipping 007bc0c3-3e63-4577-9a60-7cdd701ada9d because it contains profanity\n",
      "88 89\n",
      "0081c21e-dd06-415b-a11d-6cb5e5dc927a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0081c21e-dd06-415b-a11d-6cb5e5dc927a.html\n",
      "upload: ../outputs/html-20270823/0081c21e-dd06-415b-a11d-6cb5e5dc927a.html to s3://suno-annotation-public/preference-20270823/0081c21e-dd06-415b-a11d-6cb5e5dc927a.html\n",
      "90 91\n",
      "0087d10f-c3bf-47f4-aacd-9501cdab03ae\n",
      "Skipping 0087d10f-c3bf-47f4-aacd-9501cdab03ae because it is not in English\n",
      "92 93\n",
      "008d4ccc-46c6-4ef8-a7d2-0c1708cb2a49\n",
      "Skipping 008d4ccc-46c6-4ef8-a7d2-0c1708cb2a49 because it is not in English\n",
      "94 95\n",
      "008dd45e-5921-43eb-8255-caa7e52d5810\n",
      "Skipping 008dd45e-5921-43eb-8255-caa7e52d5810 because it is not in English\n",
      "96 97\n",
      "008df58a-3b6d-4376-a7e0-6d7cad9ed377\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/008df58a-3b6d-4376-a7e0-6d7cad9ed377.html\n",
      "upload: ../outputs/html-20270823/008df58a-3b6d-4376-a7e0-6d7cad9ed377.html to s3://suno-annotation-public/preference-20270823/008df58a-3b6d-4376-a7e0-6d7cad9ed377.html\n",
      "98 99\n",
      "0092645b-1fad-4a81-9e88-e99c3204e00a\n",
      "Skipping 0092645b-1fad-4a81-9e88-e99c3204e00a because it is not in English\n",
      "100 101\n",
      "0097e68a-aaaa-4e44-abc3-9d57d6a2e459\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0097e68a-aaaa-4e44-abc3-9d57d6a2e459.html\n",
      "upload: ../outputs/html-20270823/0097e68a-aaaa-4e44-abc3-9d57d6a2e459.html to s3://suno-annotation-public/preference-20270823/0097e68a-aaaa-4e44-abc3-9d57d6a2e459.html\n",
      "102 103\n",
      "009bc7df-0434-40b5-91c1-8238085bb15e\n",
      "Skipping 009bc7df-0434-40b5-91c1-8238085bb15e because it is not in English\n",
      "104 105\n",
      "009e2ca9-f0b7-43e3-8567-5c19e3c67df8\n",
      "Skipping 009e2ca9-f0b7-43e3-8567-5c19e3c67df8 because it contains profanity\n",
      "106 107\n",
      "00a29ed2-20dd-4786-8bf7-cc85b64cb092\n",
      "Skipping 00a29ed2-20dd-4786-8bf7-cc85b64cb092 because it is not in English\n",
      "108 109\n",
      "00a45d7f-c565-4459-94a7-32df6d721a8c\n",
      "Skipping 00a45d7f-c565-4459-94a7-32df6d721a8c because it is not in English\n",
      "110 111\n",
      "00a5356e-9441-4273-8844-a483b3519f3c\n",
      "Skipping 00a5356e-9441-4273-8844-a483b3519f3c because it is not in English\n",
      "112 113\n",
      "00a5596a-5948-4106-b4f3-e02d94eaf895\n",
      "Skipping 00a5596a-5948-4106-b4f3-e02d94eaf895 because it is not in English\n",
      "114 115\n",
      "00a5aa75-b684-4b64-8678-78f2633c9bea\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00a5aa75-b684-4b64-8678-78f2633c9bea.html\n",
      "upload: ../outputs/html-20270823/00a5aa75-b684-4b64-8678-78f2633c9bea.html to s3://suno-annotation-public/preference-20270823/00a5aa75-b684-4b64-8678-78f2633c9bea.html\n",
      "116 117\n",
      "00a85cff-0e3b-4adb-bae3-4d82d88a80d7\n",
      "Skipping 00a85cff-0e3b-4adb-bae3-4d82d88a80d7 because it is not in English\n",
      "118 119\n",
      "00a9a5b4-3eb8-4aab-a6db-60ea1b0765c6\n",
      "Skipping 00a9a5b4-3eb8-4aab-a6db-60ea1b0765c6 because it is not in English\n",
      "120 121\n",
      "00a9f65f-6d09-4148-8427-dc99b9e6f2c3\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00a9f65f-6d09-4148-8427-dc99b9e6f2c3.html\n",
      "upload: ../outputs/html-20270823/00a9f65f-6d09-4148-8427-dc99b9e6f2c3.html to s3://suno-annotation-public/preference-20270823/00a9f65f-6d09-4148-8427-dc99b9e6f2c3.html\n",
      "122 123\n",
      "00aa8090-7b96-4e56-b02f-c472fb907fb5\n",
      "Skipping 00aa8090-7b96-4e56-b02f-c472fb907fb5 because it contains profanity\n",
      "124 125\n",
      "00ab83e6-61b1-4b26-bfcf-570208ad69e1\n",
      "Skipping 00ab83e6-61b1-4b26-bfcf-570208ad69e1 because it contains profanity\n",
      "126 127\n",
      "00abb327-5237-431d-9f7d-0bde4cc717ab\n",
      "Skipping 00abb327-5237-431d-9f7d-0bde4cc717ab because it is not in English\n",
      "128 129\n",
      "00abd4bf-78fd-4d2a-8d14-252be60d8322\n",
      "Skipping 00abd4bf-78fd-4d2a-8d14-252be60d8322 because it is not in English\n",
      "130 131\n",
      "00af81b0-1e45-44ef-8dab-6e26cf77cc21\n",
      "Skipping 00af81b0-1e45-44ef-8dab-6e26cf77cc21 because it is not in English\n",
      "132 133\n",
      "00b1e2aa-e9ac-41f0-8b2e-9803321e8b85\n",
      "Skipping 00b1e2aa-e9ac-41f0-8b2e-9803321e8b85 because it is not in English\n",
      "134 135\n",
      "00b2455f-a177-4ecc-93eb-2847b1b6fa67\n",
      "Skipping 00b2455f-a177-4ecc-93eb-2847b1b6fa67 because it is not in English\n",
      "136 137\n",
      "00b43de6-ca29-4d5a-984a-9a45d43f860f\n",
      "Skipping 00b43de6-ca29-4d5a-984a-9a45d43f860f because it is not in English\n",
      "138 139\n",
      "00b6c7e8-5e29-4585-a344-5c3b272da1b2\n",
      "Skipping 00b6c7e8-5e29-4585-a344-5c3b272da1b2 because it is not in English\n",
      "140 141\n",
      "00b93045-671e-4920-9386-254279799e0b\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00b93045-671e-4920-9386-254279799e0b.html\n",
      "upload: ../outputs/html-20270823/00b93045-671e-4920-9386-254279799e0b.html to s3://suno-annotation-public/preference-20270823/00b93045-671e-4920-9386-254279799e0b.html\n",
      "142 143\n",
      "00bfec57-10cf-4f73-a75b-7da9962e568e\n",
      "Skipping 00bfec57-10cf-4f73-a75b-7da9962e568e because it is not in English\n",
      "144 145\n",
      "00c3d555-8daa-4095-9c11-4b12176def0f\n",
      "Skipping 00c3d555-8daa-4095-9c11-4b12176def0f because it is not in English\n",
      "146 147\n",
      "00c3db6c-a189-45ac-92b7-4516e1f0fc19\n",
      "Skipping 00c3db6c-a189-45ac-92b7-4516e1f0fc19 because it contains profanity\n",
      "148 149\n",
      "00ca0b73-f8f4-4fdd-85b5-723a5b74962e\n",
      "Skipping 00ca0b73-f8f4-4fdd-85b5-723a5b74962e because it is not in English\n",
      "150 151\n",
      "00cad5a8-06f7-4863-9389-05c584609977\n",
      "Skipping 00cad5a8-06f7-4863-9389-05c584609977 because it is not in English\n",
      "152 153\n",
      "00caf3f4-7b11-4868-badd-34238e822c24\n",
      "Skipping 00caf3f4-7b11-4868-badd-34238e822c24 because it is not in English\n",
      "154 155\n",
      "00cc98ba-2dd2-495e-9e56-5c088e2bbb16\n",
      "Skipping 00cc98ba-2dd2-495e-9e56-5c088e2bbb16 because it is not in English\n",
      "156 157\n",
      "00cd6fe5-cfcb-404c-9469-032653ef8913\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00cd6fe5-cfcb-404c-9469-032653ef8913.html\n",
      "upload: ../outputs/html-20270823/00cd6fe5-cfcb-404c-9469-032653ef8913.html to s3://suno-annotation-public/preference-20270823/00cd6fe5-cfcb-404c-9469-032653ef8913.html\n",
      "158 159\n",
      "00cf3539-af07-4f61-9c5b-c16282b353d6\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00cf3539-af07-4f61-9c5b-c16282b353d6.html\n",
      "upload: ../outputs/html-20270823/00cf3539-af07-4f61-9c5b-c16282b353d6.html to s3://suno-annotation-public/preference-20270823/00cf3539-af07-4f61-9c5b-c16282b353d6.html\n",
      "160 161\n",
      "00d247e1-d34a-40f5-be76-89d0246b3b97\n",
      "Skipping 00d247e1-d34a-40f5-be76-89d0246b3b97 because it is not in English\n",
      "162 163\n",
      "00d5b0e0-8175-4d82-bc1e-d5852df029ac\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00d5b0e0-8175-4d82-bc1e-d5852df029ac.html\n",
      "upload: ../outputs/html-20270823/00d5b0e0-8175-4d82-bc1e-d5852df029ac.html to s3://suno-annotation-public/preference-20270823/00d5b0e0-8175-4d82-bc1e-d5852df029ac.html\n",
      "164 165\n",
      "00d682e4-a622-479e-b0c6-f209b6fd717a\n",
      "Skipping 00d682e4-a622-479e-b0c6-f209b6fd717a because it is not in English\n",
      "166 167\n",
      "00d76159-0161-46e3-8667-1e0e848c8921\n",
      "Skipping 00d76159-0161-46e3-8667-1e0e848c8921 because it is not in English\n",
      "168 169\n",
      "00d9e4f0-921f-4cc6-b924-9b0c0e3ab222\n",
      "Skipping 00d9e4f0-921f-4cc6-b924-9b0c0e3ab222 because it is not in English\n",
      "170 171\n",
      "00dcbd61-add4-4ea9-b659-d711080a66cf\n",
      "Skipping 00dcbd61-add4-4ea9-b659-d711080a66cf because it is not in English\n",
      "172 173\n",
      "00de9399-9b45-4b53-a9fe-76118a6c7969\n",
      "Skipping 00de9399-9b45-4b53-a9fe-76118a6c7969 because it is not in English\n",
      "174 175\n",
      "00e35bb1-4be0-47de-ae62-2aab8704afc6\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00e35bb1-4be0-47de-ae62-2aab8704afc6.html\n",
      "upload: ../outputs/html-20270823/00e35bb1-4be0-47de-ae62-2aab8704afc6.html to s3://suno-annotation-public/preference-20270823/00e35bb1-4be0-47de-ae62-2aab8704afc6.html\n",
      "176 177\n",
      "00e5786e-3f16-4b89-aad2-96ee1c9adf74\n",
      "Skipping 00e5786e-3f16-4b89-aad2-96ee1c9adf74 because it contains profanity\n",
      "178 179\n",
      "00eb70a9-e190-432d-bfd1-520428e733aa\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00eb70a9-e190-432d-bfd1-520428e733aa.html\n",
      "upload: ../outputs/html-20270823/00eb70a9-e190-432d-bfd1-520428e733aa.html to s3://suno-annotation-public/preference-20270823/00eb70a9-e190-432d-bfd1-520428e733aa.html\n",
      "180 181\n",
      "00edb46e-0973-483d-b876-346c23ca5c5c\n",
      "Skipping 00edb46e-0973-483d-b876-346c23ca5c5c because it is not in English\n",
      "182 183\n",
      "00f04dc1-2122-4ae1-a3d4-43e326da0f7a\n",
      "Skipping 00f04dc1-2122-4ae1-a3d4-43e326da0f7a because it is not in English\n",
      "184 185\n",
      "00f1bb3d-c33a-4ec8-b506-ee8816f500a0\n",
      "Skipping 00f1bb3d-c33a-4ec8-b506-ee8816f500a0 because it is not in English\n",
      "186 187\n",
      "00f59f38-16b2-4fe7-ba5e-3dee628ef4a3\n",
      "Skipping 00f59f38-16b2-4fe7-ba5e-3dee628ef4a3 because it is not in English\n",
      "188 189\n",
      "00f5a549-1989-4765-9208-aefe2ea6c053\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00f5a549-1989-4765-9208-aefe2ea6c053.html\n",
      "upload: ../outputs/html-20270823/00f5a549-1989-4765-9208-aefe2ea6c053.html to s3://suno-annotation-public/preference-20270823/00f5a549-1989-4765-9208-aefe2ea6c053.html\n",
      "190 191\n",
      "00fa6002-cc69-48b4-a961-e1354e1f2a19\n",
      "Skipping 00fa6002-cc69-48b4-a961-e1354e1f2a19 because it is not in English\n",
      "192 193\n",
      "00fad7a3-e8b3-4777-a161-238cda0bdaba\n",
      "Skipping 00fad7a3-e8b3-4777-a161-238cda0bdaba because it is not in English\n",
      "194 195\n",
      "00fcce48-a80d-4bbc-b07a-cfa9c97f4241\n",
      "Skipping 00fcce48-a80d-4bbc-b07a-cfa9c97f4241 because it is not in English\n",
      "196 197\n",
      "00fdc177-e822-4da5-8d46-0ba8324ebb3b\n",
      "Skipping 00fdc177-e822-4da5-8d46-0ba8324ebb3b because it is not in English\n",
      "198 199\n",
      "00ffda18-50e4-47af-a6de-a16abe2ec302\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/00ffda18-50e4-47af-a6de-a16abe2ec302.html\n",
      "upload: ../outputs/html-20270823/00ffda18-50e4-47af-a6de-a16abe2ec302.html to s3://suno-annotation-public/preference-20270823/00ffda18-50e4-47af-a6de-a16abe2ec302.html\n",
      "200 201\n",
      "01015733-68de-4403-9ed9-506ad6c97d76\n",
      "Skipping 01015733-68de-4403-9ed9-506ad6c97d76 because it is not in English\n",
      "202 203\n",
      "010383c2-ab4d-46a9-99d1-842b2fe6453b\n",
      "Skipping 010383c2-ab4d-46a9-99d1-842b2fe6453b because it is not in English\n",
      "204 205\n",
      "01058fb0-1b58-4b70-bd74-05d4db26b10c\n",
      "Skipping 01058fb0-1b58-4b70-bd74-05d4db26b10c because it is not in English\n",
      "206 207\n",
      "0106abcb-1acf-4608-9c2c-7f387e013eda\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0106abcb-1acf-4608-9c2c-7f387e013eda.html\n",
      "upload: ../outputs/html-20270823/0106abcb-1acf-4608-9c2c-7f387e013eda.html to s3://suno-annotation-public/preference-20270823/0106abcb-1acf-4608-9c2c-7f387e013eda.html\n",
      "208 209\n",
      "010a94e5-3821-4a82-bb6b-0285f7e92e7b\n",
      "Skipping 010a94e5-3821-4a82-bb6b-0285f7e92e7b because it is not in English\n",
      "210 211\n",
      "010e2e07-889d-44a3-a6bf-221b41b8e07f\n",
      "Skipping 010e2e07-889d-44a3-a6bf-221b41b8e07f because it is not in English\n",
      "212 213\n",
      "010f76e1-e95c-4298-9f62-0c0a9f98c188\n",
      "Skipping 010f76e1-e95c-4298-9f62-0c0a9f98c188 because it is not in English\n",
      "214 215\n",
      "01116b61-eb84-41b4-9c75-426ad1b72091\n",
      "Skipping 01116b61-eb84-41b4-9c75-426ad1b72091 because it is not in English\n",
      "216 217\n",
      "0111f8fd-9a1c-4e30-81fc-208d1854bdc5\n",
      "Skipping 0111f8fd-9a1c-4e30-81fc-208d1854bdc5 because it is not in English\n",
      "218 219\n",
      "0114c7c4-e099-4433-b9b4-3f72d2cfbec5\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0114c7c4-e099-4433-b9b4-3f72d2cfbec5.html\n",
      "upload: ../outputs/html-20270823/0114c7c4-e099-4433-b9b4-3f72d2cfbec5.html to s3://suno-annotation-public/preference-20270823/0114c7c4-e099-4433-b9b4-3f72d2cfbec5.html\n",
      "220 221\n",
      "011ae299-e651-4b32-94b1-b8b0ccb95560\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/011ae299-e651-4b32-94b1-b8b0ccb95560.html\n",
      "upload: ../outputs/html-20270823/011ae299-e651-4b32-94b1-b8b0ccb95560.html to s3://suno-annotation-public/preference-20270823/011ae299-e651-4b32-94b1-b8b0ccb95560.html\n",
      "222 223\n",
      "011b2aeb-dcbb-4fca-8a82-577e4347ad66\n",
      "Skipping 011b2aeb-dcbb-4fca-8a82-577e4347ad66 because it is not in English\n",
      "224 225\n",
      "011b6779-82f3-40e4-bd9e-9afb65b13930\n",
      "Skipping 011b6779-82f3-40e4-bd9e-9afb65b13930 because it contains profanity\n",
      "226 227\n",
      "0120bdb3-a5d3-45e8-a7fa-e8ee854aa5d2\n",
      "Skipping 0120bdb3-a5d3-45e8-a7fa-e8ee854aa5d2 because it is not in English\n",
      "228 229\n",
      "0122db84-8be6-4e39-998a-6dfa8d2db5b1\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0122db84-8be6-4e39-998a-6dfa8d2db5b1.html\n",
      "upload: ../outputs/html-20270823/0122db84-8be6-4e39-998a-6dfa8d2db5b1.html to s3://suno-annotation-public/preference-20270823/0122db84-8be6-4e39-998a-6dfa8d2db5b1.html\n",
      "230 231\n",
      "0125aef3-83e9-4e06-b329-5f384d7bae7e\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0125aef3-83e9-4e06-b329-5f384d7bae7e.html\n",
      "upload: ../outputs/html-20270823/0125aef3-83e9-4e06-b329-5f384d7bae7e.html to s3://suno-annotation-public/preference-20270823/0125aef3-83e9-4e06-b329-5f384d7bae7e.html\n",
      "232 233\n",
      "012c3546-d255-434e-aa20-9b401f7d990b\n",
      "Skipping 012c3546-d255-434e-aa20-9b401f7d990b because it is not in English\n",
      "234 235\n",
      "012ef169-c8aa-4045-9185-3b099ed0c9f6\n",
      "Skipping 012ef169-c8aa-4045-9185-3b099ed0c9f6 because it is not in English\n",
      "236 237\n",
      "012efe2c-c956-4e26-b26f-0a6e4ee5ee3a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/012efe2c-c956-4e26-b26f-0a6e4ee5ee3a.html\n",
      "upload: ../outputs/html-20270823/012efe2c-c956-4e26-b26f-0a6e4ee5ee3a.html to s3://suno-annotation-public/preference-20270823/012efe2c-c956-4e26-b26f-0a6e4ee5ee3a.html\n",
      "238 239\n",
      "0130f2f7-957b-4b22-aac7-7f809440c58d\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0130f2f7-957b-4b22-aac7-7f809440c58d.html\n",
      "upload: ../outputs/html-20270823/0130f2f7-957b-4b22-aac7-7f809440c58d.html to s3://suno-annotation-public/preference-20270823/0130f2f7-957b-4b22-aac7-7f809440c58d.html\n",
      "240 241\n",
      "013821ea-5e4f-4191-885e-eb76b82656b1\n",
      "Skipping 013821ea-5e4f-4191-885e-eb76b82656b1 because it is not in English\n",
      "242 243\n",
      "0138eb84-d96d-4bb7-91e9-0e67a6863880\n",
      "Skipping 0138eb84-d96d-4bb7-91e9-0e67a6863880 because it is not in English\n",
      "244 245\n",
      "013a83ab-9040-4dec-8da2-69aad3731dc3\n",
      "Skipping 013a83ab-9040-4dec-8da2-69aad3731dc3 because it is not in English\n",
      "246 247\n",
      "013a955a-f2f4-4093-abef-cfafafc4fed0\n",
      "Skipping 013a955a-f2f4-4093-abef-cfafafc4fed0 because it is not in English\n",
      "248 249\n",
      "013e91b6-412b-4bc4-88b5-35a3575b05b7\n",
      "Skipping 013e91b6-412b-4bc4-88b5-35a3575b05b7 because it is not in English\n",
      "250 251\n",
      "013fe5ea-a278-482a-b8f6-73ac7a5a42c2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/013fe5ea-a278-482a-b8f6-73ac7a5a42c2.html\n",
      "upload: ../outputs/html-20270823/013fe5ea-a278-482a-b8f6-73ac7a5a42c2.html to s3://suno-annotation-public/preference-20270823/013fe5ea-a278-482a-b8f6-73ac7a5a42c2.html\n",
      "252 253\n",
      "01420be6-8860-4504-b43b-e6ddc15b16be\n",
      "Skipping 01420be6-8860-4504-b43b-e6ddc15b16be because it is not in English\n",
      "254 255\n",
      "01475183-dace-40cd-bbdf-4aac1c77ba8c\n",
      "Skipping 01475183-dace-40cd-bbdf-4aac1c77ba8c because it is not in English\n",
      "256 257\n",
      "014b8d50-3e56-430f-a436-11dbac9116d2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/014b8d50-3e56-430f-a436-11dbac9116d2.html\n",
      "upload: ../outputs/html-20270823/014b8d50-3e56-430f-a436-11dbac9116d2.html to s3://suno-annotation-public/preference-20270823/014b8d50-3e56-430f-a436-11dbac9116d2.html\n",
      "258 259\n",
      "01510736-5160-4e81-9c99-a1895d1ef267\n",
      "Skipping 01510736-5160-4e81-9c99-a1895d1ef267 because it is not in English\n",
      "260 261\n",
      "01513dfd-f8f4-45aa-8f48-6a51cff85061\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01513dfd-f8f4-45aa-8f48-6a51cff85061.html\n",
      "upload: ../outputs/html-20270823/01513dfd-f8f4-45aa-8f48-6a51cff85061.html to s3://suno-annotation-public/preference-20270823/01513dfd-f8f4-45aa-8f48-6a51cff85061.html\n",
      "262 263\n",
      "01545ce1-b647-4cb6-bdb6-b016c2e98349\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01545ce1-b647-4cb6-bdb6-b016c2e98349.html\n",
      "upload: ../outputs/html-20270823/01545ce1-b647-4cb6-bdb6-b016c2e98349.html to s3://suno-annotation-public/preference-20270823/01545ce1-b647-4cb6-bdb6-b016c2e98349.html\n",
      "264 265\n",
      "0154b935-fc35-4ffb-a2f2-1bd76984d63d\n",
      "Skipping 0154b935-fc35-4ffb-a2f2-1bd76984d63d because it contains profanity\n",
      "266 267\n",
      "0157e5b1-0ba7-46d3-878b-0fce351f7558\n",
      "Skipping 0157e5b1-0ba7-46d3-878b-0fce351f7558 because it contains profanity\n",
      "268 269\n",
      "015aa56a-5fbc-4a6c-b17b-0fbebfdd1198\n",
      "Skipping 015aa56a-5fbc-4a6c-b17b-0fbebfdd1198 because it is not in English\n",
      "270 271\n",
      "0161490c-162b-486e-ad46-fa842a96dff1\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0161490c-162b-486e-ad46-fa842a96dff1.html\n",
      "upload: ../outputs/html-20270823/0161490c-162b-486e-ad46-fa842a96dff1.html to s3://suno-annotation-public/preference-20270823/0161490c-162b-486e-ad46-fa842a96dff1.html\n",
      "272 273\n",
      "0161ea05-5f51-4781-be9c-00072bba9a00\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0161ea05-5f51-4781-be9c-00072bba9a00.html\n",
      "upload: ../outputs/html-20270823/0161ea05-5f51-4781-be9c-00072bba9a00.html to s3://suno-annotation-public/preference-20270823/0161ea05-5f51-4781-be9c-00072bba9a00.html\n",
      "274 275\n",
      "01633d60-0521-43dc-878b-5100b2bb1d77\n",
      "Skipping 01633d60-0521-43dc-878b-5100b2bb1d77 because it is not in English\n",
      "276 277\n",
      "016445d3-dcf8-4b63-9bd5-a75946d07a2a\n",
      "Skipping 016445d3-dcf8-4b63-9bd5-a75946d07a2a because it is not in English\n",
      "278 279\n",
      "01699dd5-9337-4c87-bfff-9afc8f2efddc\n",
      "Skipping 01699dd5-9337-4c87-bfff-9afc8f2efddc because it is not in English\n",
      "280 281\n",
      "016ad081-35fb-498f-ae29-e8007315f3b8\n",
      "Skipping 016ad081-35fb-498f-ae29-e8007315f3b8 because it contains profanity\n",
      "282 283\n",
      "016c2a01-a4ad-4f1b-9038-da7ae946f4e9\n",
      "Skipping 016c2a01-a4ad-4f1b-9038-da7ae946f4e9 because it is not in English\n",
      "284 285\n",
      "016d557e-a687-42e3-b589-caefefdeb59b\n",
      "Skipping 016d557e-a687-42e3-b589-caefefdeb59b because it is not in English\n",
      "286 287\n",
      "016d72c8-da63-4f34-89b5-d9d074084977\n",
      "Skipping 016d72c8-da63-4f34-89b5-d9d074084977 because it is not in English\n",
      "288 289\n",
      "016f1dae-da21-4583-b9ce-1114d1ec36bd\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/016f1dae-da21-4583-b9ce-1114d1ec36bd.html\n",
      "upload: ../outputs/html-20270823/016f1dae-da21-4583-b9ce-1114d1ec36bd.html to s3://suno-annotation-public/preference-20270823/016f1dae-da21-4583-b9ce-1114d1ec36bd.html\n",
      "290 291\n",
      "016fd20d-c76c-4c6d-8677-a3701bc02392\n",
      "Skipping 016fd20d-c76c-4c6d-8677-a3701bc02392 because it is not in English\n",
      "292 293\n",
      "01780092-603b-44f2-b042-6dbc33695ba6\n",
      "Skipping 01780092-603b-44f2-b042-6dbc33695ba6 because it is not in English\n",
      "294 295\n",
      "017997e4-90be-428d-8c82-46c8dd8bf492\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/017997e4-90be-428d-8c82-46c8dd8bf492.html\n",
      "upload: ../outputs/html-20270823/017997e4-90be-428d-8c82-46c8dd8bf492.html to s3://suno-annotation-public/preference-20270823/017997e4-90be-428d-8c82-46c8dd8bf492.html\n",
      "296 297\n",
      "017b8e73-13de-4f1d-8d25-a3fe137f9a75\n",
      "Skipping 017b8e73-13de-4f1d-8d25-a3fe137f9a75 because it is not in English\n",
      "298 299\n",
      "017dc2d6-e0cf-46cb-9b32-e3af84d5c0de\n",
      "Skipping 017dc2d6-e0cf-46cb-9b32-e3af84d5c0de because it contains profanity\n",
      "300 301\n",
      "01833c2f-a5e5-4764-b40f-836d3e02d43f\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01833c2f-a5e5-4764-b40f-836d3e02d43f.html\n",
      "upload: ../outputs/html-20270823/01833c2f-a5e5-4764-b40f-836d3e02d43f.html to s3://suno-annotation-public/preference-20270823/01833c2f-a5e5-4764-b40f-836d3e02d43f.html\n",
      "302 303\n",
      "0185ba89-3878-4bbd-80de-b5e700720636\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0185ba89-3878-4bbd-80de-b5e700720636.html\n",
      "upload: ../outputs/html-20270823/0185ba89-3878-4bbd-80de-b5e700720636.html to s3://suno-annotation-public/preference-20270823/0185ba89-3878-4bbd-80de-b5e700720636.html\n",
      "304 305\n",
      "018deacb-b788-4019-80d8-692b743106c7\n",
      "Skipping 018deacb-b788-4019-80d8-692b743106c7 because it is not in English\n",
      "306 307\n",
      "0194f4a7-6af3-4a12-9d09-de11f27f4f93\n",
      "Skipping 0194f4a7-6af3-4a12-9d09-de11f27f4f93 because it is not in English\n",
      "308 309\n",
      "019940ac-478e-4493-b776-e4a90ad325d7\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/019940ac-478e-4493-b776-e4a90ad325d7.html\n",
      "upload: ../outputs/html-20270823/019940ac-478e-4493-b776-e4a90ad325d7.html to s3://suno-annotation-public/preference-20270823/019940ac-478e-4493-b776-e4a90ad325d7.html\n",
      "310 311\n",
      "019be2ce-c535-4a1b-b6d1-e67f7a0fb9d8\n",
      "Skipping 019be2ce-c535-4a1b-b6d1-e67f7a0fb9d8 because it is not in English\n",
      "312 313\n",
      "01a05a06-cbb5-4f7a-9e9b-c99cf8510b9d\n",
      "Skipping 01a05a06-cbb5-4f7a-9e9b-c99cf8510b9d because it is not in English\n",
      "314 315\n",
      "01a23fc4-adae-4ea5-9434-bbcff5a6da3b\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01a23fc4-adae-4ea5-9434-bbcff5a6da3b.html\n",
      "upload: ../outputs/html-20270823/01a23fc4-adae-4ea5-9434-bbcff5a6da3b.html to s3://suno-annotation-public/preference-20270823/01a23fc4-adae-4ea5-9434-bbcff5a6da3b.html\n",
      "316 317\n",
      "01a58a82-002a-4d4c-a90f-57cbe22a0d14\n",
      "Skipping 01a58a82-002a-4d4c-a90f-57cbe22a0d14 because it is not in English\n",
      "318 319\n",
      "01a77069-8f83-4746-b0cb-a8c316d3a7a2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01a77069-8f83-4746-b0cb-a8c316d3a7a2.html\n",
      "upload: ../outputs/html-20270823/01a77069-8f83-4746-b0cb-a8c316d3a7a2.html to s3://suno-annotation-public/preference-20270823/01a77069-8f83-4746-b0cb-a8c316d3a7a2.html\n",
      "320 321\n",
      "01aab7d0-fb26-46c5-945c-f9101d33a47f\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01aab7d0-fb26-46c5-945c-f9101d33a47f.html\n",
      "upload: ../outputs/html-20270823/01aab7d0-fb26-46c5-945c-f9101d33a47f.html to s3://suno-annotation-public/preference-20270823/01aab7d0-fb26-46c5-945c-f9101d33a47f.html\n",
      "322 323\n",
      "01ab1d8b-28ec-4428-8699-dea9bd52b111\n",
      "Skipping 01ab1d8b-28ec-4428-8699-dea9bd52b111 because it is not in English\n",
      "324 325\n",
      "01ab3882-07e0-49a5-88fd-8e88fdb52ec1\n",
      "Skipping 01ab3882-07e0-49a5-88fd-8e88fdb52ec1 because it is not in English\n",
      "326 327\n",
      "01afed4d-553b-467e-98f7-ed95096be909\n",
      "Skipping 01afed4d-553b-467e-98f7-ed95096be909 because it is not in English\n",
      "328 329\n",
      "01b0d3f6-d490-4e16-9535-4b55e34b1537\n",
      "Skipping 01b0d3f6-d490-4e16-9535-4b55e34b1537 because it is not in English\n",
      "330 331\n",
      "01b4e532-8d3d-415e-a85c-e6ea0f460aca\n",
      "Skipping 01b4e532-8d3d-415e-a85c-e6ea0f460aca because it is not in English\n",
      "332 333\n",
      "01b58148-6bd6-4014-b6ea-b239b9c4c408\n",
      "Skipping 01b58148-6bd6-4014-b6ea-b239b9c4c408 because it is not in English\n",
      "334 335\n",
      "01b5b270-a1cc-4668-84aa-04bba35e4d0d\n",
      "Skipping 01b5b270-a1cc-4668-84aa-04bba35e4d0d because it is not in English\n",
      "336 337\n",
      "01b75c14-51c0-4e7b-b10c-89ec68e4662d\n",
      "Skipping 01b75c14-51c0-4e7b-b10c-89ec68e4662d because it is not in English\n",
      "338 339\n",
      "01b829b5-4536-486a-b6d4-5de7f0f778c8\n",
      "Skipping 01b829b5-4536-486a-b6d4-5de7f0f778c8 because it is not in English\n",
      "340 341\n",
      "01bb043c-e5c8-4ad8-b0fd-b6545c1c93c2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01bb043c-e5c8-4ad8-b0fd-b6545c1c93c2.html\n",
      "upload: ../outputs/html-20270823/01bb043c-e5c8-4ad8-b0fd-b6545c1c93c2.html to s3://suno-annotation-public/preference-20270823/01bb043c-e5c8-4ad8-b0fd-b6545c1c93c2.html\n",
      "342 343\n",
      "01bbcb57-abcb-4c37-aef8-5e9e81d8f24b\n",
      "Skipping 01bbcb57-abcb-4c37-aef8-5e9e81d8f24b because it is not in English\n",
      "344 345\n",
      "01bc6cc8-2e7d-4a1c-b8e8-2cd1b4dc1930\n",
      "Skipping 01bc6cc8-2e7d-4a1c-b8e8-2cd1b4dc1930 because it is not in English\n",
      "346 347\n",
      "01bde191-6eff-4823-8230-8b04e2883b19\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01bde191-6eff-4823-8230-8b04e2883b19.html\n",
      "upload: ../outputs/html-20270823/01bde191-6eff-4823-8230-8b04e2883b19.html to s3://suno-annotation-public/preference-20270823/01bde191-6eff-4823-8230-8b04e2883b19.html\n",
      "348 349\n",
      "01c0e26d-63af-413b-b37d-d238322f4b4b\n",
      "Skipping 01c0e26d-63af-413b-b37d-d238322f4b4b because it is not in English\n",
      "350 351\n",
      "01c13c24-6acf-4562-b511-bc15c64f35da\n",
      "Skipping 01c13c24-6acf-4562-b511-bc15c64f35da because it is not in English\n",
      "352 353\n",
      "01c173d4-162b-420f-91b0-50b3050a76b4\n",
      "Skipping 01c173d4-162b-420f-91b0-50b3050a76b4 because it is not in English\n",
      "354 355\n",
      "01c9fd1a-b84f-4c57-bdd7-7212dbfde91a\n",
      "Skipping 01c9fd1a-b84f-4c57-bdd7-7212dbfde91a because it is not in English\n",
      "356 357\n",
      "01cd73b5-b717-4d9e-bc40-d6735f5aa6c2\n",
      "Skipping 01cd73b5-b717-4d9e-bc40-d6735f5aa6c2 because it is not in English\n",
      "358 359\n",
      "01ce335a-09fa-4d02-87ad-b712163079e2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01ce335a-09fa-4d02-87ad-b712163079e2.html\n",
      "upload: ../outputs/html-20270823/01ce335a-09fa-4d02-87ad-b712163079e2.html to s3://suno-annotation-public/preference-20270823/01ce335a-09fa-4d02-87ad-b712163079e2.html\n",
      "360 361\n",
      "01d114f0-f483-4319-8ba7-f7f5301186d5\n",
      "Skipping 01d114f0-f483-4319-8ba7-f7f5301186d5 because it contains profanity\n",
      "362 363\n",
      "01d307ad-d3b7-4b15-be46-749d481f7936\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01d307ad-d3b7-4b15-be46-749d481f7936.html\n",
      "upload: ../outputs/html-20270823/01d307ad-d3b7-4b15-be46-749d481f7936.html to s3://suno-annotation-public/preference-20270823/01d307ad-d3b7-4b15-be46-749d481f7936.html\n",
      "364 365\n",
      "01d4a7ac-b0e1-4aaa-8f3e-7b1a112e6fc7\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01d4a7ac-b0e1-4aaa-8f3e-7b1a112e6fc7.html\n",
      "upload: ../outputs/html-20270823/01d4a7ac-b0e1-4aaa-8f3e-7b1a112e6fc7.html to s3://suno-annotation-public/preference-20270823/01d4a7ac-b0e1-4aaa-8f3e-7b1a112e6fc7.html\n",
      "366 367\n",
      "01d60a9c-68b3-4e3a-9364-effc60d8b226\n",
      "Skipping 01d60a9c-68b3-4e3a-9364-effc60d8b226 because it is not in English\n",
      "368 369\n",
      "01da0f6a-167d-430a-a0af-a2e36ef89922\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01da0f6a-167d-430a-a0af-a2e36ef89922.html\n",
      "upload: ../outputs/html-20270823/01da0f6a-167d-430a-a0af-a2e36ef89922.html to s3://suno-annotation-public/preference-20270823/01da0f6a-167d-430a-a0af-a2e36ef89922.html\n",
      "370 371\n",
      "01dfcca5-8865-4b1a-bad2-efcb7b60100a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01dfcca5-8865-4b1a-bad2-efcb7b60100a.html\n",
      "upload: ../outputs/html-20270823/01dfcca5-8865-4b1a-bad2-efcb7b60100a.html to s3://suno-annotation-public/preference-20270823/01dfcca5-8865-4b1a-bad2-efcb7b60100a.html\n",
      "372 373\n",
      "01e0fcf8-b9dc-4ac9-8219-1c0017bceecc\n",
      "Skipping 01e0fcf8-b9dc-4ac9-8219-1c0017bceecc because it contains profanity\n",
      "374 375\n",
      "01e48a1c-7854-4c97-8516-9888eff3e689\n",
      "Skipping 01e48a1c-7854-4c97-8516-9888eff3e689 because it is not in English\n",
      "376 377\n",
      "01e76823-ad54-4402-8485-e02cb0707bbb\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01e76823-ad54-4402-8485-e02cb0707bbb.html\n",
      "upload: ../outputs/html-20270823/01e76823-ad54-4402-8485-e02cb0707bbb.html to s3://suno-annotation-public/preference-20270823/01e76823-ad54-4402-8485-e02cb0707bbb.html\n",
      "378 379\n",
      "01e99a64-dd28-4440-9f0e-d0ce62df531b\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01e99a64-dd28-4440-9f0e-d0ce62df531b.html\n",
      "upload: ../outputs/html-20270823/01e99a64-dd28-4440-9f0e-d0ce62df531b.html to s3://suno-annotation-public/preference-20270823/01e99a64-dd28-4440-9f0e-d0ce62df531b.html\n",
      "380 381\n",
      "01ebf418-1020-48c2-a4ee-43e4512f801e\n",
      "Skipping 01ebf418-1020-48c2-a4ee-43e4512f801e because it is not in English\n",
      "382 383\n",
      "01ee6957-3fb7-4b4f-a8ed-83d9fbc6d8b9\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01ee6957-3fb7-4b4f-a8ed-83d9fbc6d8b9.html\n",
      "upload: ../outputs/html-20270823/01ee6957-3fb7-4b4f-a8ed-83d9fbc6d8b9.html to s3://suno-annotation-public/preference-20270823/01ee6957-3fb7-4b4f-a8ed-83d9fbc6d8b9.html\n",
      "384 385\n",
      "01f109fd-c887-4331-b20b-e4eb9bd83a55\n",
      "Skipping 01f109fd-c887-4331-b20b-e4eb9bd83a55 because it is not in English\n",
      "386 387\n",
      "01f80b52-09c3-4d89-b8b7-a8cec5a03186\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01f80b52-09c3-4d89-b8b7-a8cec5a03186.html\n",
      "upload: ../outputs/html-20270823/01f80b52-09c3-4d89-b8b7-a8cec5a03186.html to s3://suno-annotation-public/preference-20270823/01f80b52-09c3-4d89-b8b7-a8cec5a03186.html\n",
      "388 389\n",
      "01fb764d-4970-49c7-b334-15a4f10a27c9\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01fb764d-4970-49c7-b334-15a4f10a27c9.html\n",
      "upload: ../outputs/html-20270823/01fb764d-4970-49c7-b334-15a4f10a27c9.html to s3://suno-annotation-public/preference-20270823/01fb764d-4970-49c7-b334-15a4f10a27c9.html\n",
      "390 391\n",
      "01fdbf15-0ee6-4986-bbb8-999e4996c315\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/01fdbf15-0ee6-4986-bbb8-999e4996c315.html\n",
      "upload: ../outputs/html-20270823/01fdbf15-0ee6-4986-bbb8-999e4996c315.html to s3://suno-annotation-public/preference-20270823/01fdbf15-0ee6-4986-bbb8-999e4996c315.html\n",
      "392 393\n",
      "02025834-1913-47f0-97cf-1cac4e7d0225\n",
      "Skipping 02025834-1913-47f0-97cf-1cac4e7d0225 because it is not in English\n",
      "394 395\n",
      "020817a9-8de8-43b9-8aa4-a7bfeb48e5f2\n",
      "Skipping 020817a9-8de8-43b9-8aa4-a7bfeb48e5f2 because it is not in English\n",
      "396 397\n",
      "0209f4cc-7585-43ec-8a62-69f767f9ca3f\n",
      "Skipping 0209f4cc-7585-43ec-8a62-69f767f9ca3f because it is not in English\n",
      "398 399\n",
      "020bfe42-791a-4a38-b99b-f79a14eb292d\n",
      "Skipping 020bfe42-791a-4a38-b99b-f79a14eb292d because it is not in English\n",
      "400 401\n",
      "020cc065-7098-457b-aa69-efd0cbe37495\n",
      "Skipping 020cc065-7098-457b-aa69-efd0cbe37495 because it is not in English\n",
      "402 403\n",
      "020dd958-5c4e-4c48-aab7-0c683b603d39\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/020dd958-5c4e-4c48-aab7-0c683b603d39.html\n",
      "upload: ../outputs/html-20270823/020dd958-5c4e-4c48-aab7-0c683b603d39.html to s3://suno-annotation-public/preference-20270823/020dd958-5c4e-4c48-aab7-0c683b603d39.html\n",
      "404 405\n",
      "02139a81-04ac-4089-9b98-3254dd94f04a\n",
      "Skipping 02139a81-04ac-4089-9b98-3254dd94f04a because it contains profanity\n",
      "406 407\n",
      "0216cb9b-d6b8-48ff-919f-d71c81af607e\n",
      "Skipping 0216cb9b-d6b8-48ff-919f-d71c81af607e because it is not in English\n",
      "408 409\n",
      "02216a9c-aaa2-474b-bb1f-ebd4ac900c00\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02216a9c-aaa2-474b-bb1f-ebd4ac900c00.html\n",
      "upload: ../outputs/html-20270823/02216a9c-aaa2-474b-bb1f-ebd4ac900c00.html to s3://suno-annotation-public/preference-20270823/02216a9c-aaa2-474b-bb1f-ebd4ac900c00.html\n",
      "410 411\n",
      "0223c635-8367-4cac-a9e1-55c9eb522b04\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0223c635-8367-4cac-a9e1-55c9eb522b04.html\n",
      "upload: ../outputs/html-20270823/0223c635-8367-4cac-a9e1-55c9eb522b04.html to s3://suno-annotation-public/preference-20270823/0223c635-8367-4cac-a9e1-55c9eb522b04.html\n",
      "412 413\n",
      "0228bfc9-290d-44c5-93c5-2ff4626e7383\n",
      "Skipping 0228bfc9-290d-44c5-93c5-2ff4626e7383 because it is not in English\n",
      "414 415\n",
      "022f0dbc-1bd2-43dc-9fc2-ccdf430c3b8a\n",
      "Skipping 022f0dbc-1bd2-43dc-9fc2-ccdf430c3b8a because it is not in English\n",
      "416 417\n",
      "02333c70-c7d6-4960-a923-9ab7c35418eb\n",
      "Skipping 02333c70-c7d6-4960-a923-9ab7c35418eb because it is not in English\n",
      "418 419\n",
      "023361a2-94b8-429c-b9a8-606052467488\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/023361a2-94b8-429c-b9a8-606052467488.html\n",
      "upload: ../outputs/html-20270823/023361a2-94b8-429c-b9a8-606052467488.html to s3://suno-annotation-public/preference-20270823/023361a2-94b8-429c-b9a8-606052467488.html\n",
      "420 421\n",
      "023822cf-b498-4487-99da-073898aefe3b\n",
      "Skipping 023822cf-b498-4487-99da-073898aefe3b because it is not in English\n",
      "422 423\n",
      "023b8102-f8b9-4bb9-b0ab-5852b965b14d\n",
      "Skipping 023b8102-f8b9-4bb9-b0ab-5852b965b14d because it is not in English\n",
      "424 425\n",
      "023c4eab-c3c6-4c59-93a6-b9d69fecbb92\n",
      "Skipping 023c4eab-c3c6-4c59-93a6-b9d69fecbb92 because it is not in English\n",
      "426 427\n",
      "0240e9f0-ac83-45ec-b145-93fb520d8ad2\n",
      "Skipping 0240e9f0-ac83-45ec-b145-93fb520d8ad2 because it is not in English\n",
      "428 429\n",
      "024309e9-83d1-47d1-93ab-8e2252c50c2a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/024309e9-83d1-47d1-93ab-8e2252c50c2a.html\n",
      "upload: ../outputs/html-20270823/024309e9-83d1-47d1-93ab-8e2252c50c2a.html to s3://suno-annotation-public/preference-20270823/024309e9-83d1-47d1-93ab-8e2252c50c2a.html\n",
      "430 431\n",
      "02432b9b-aeed-4d0b-8d03-f4e883532f4b\n",
      "Skipping 02432b9b-aeed-4d0b-8d03-f4e883532f4b because it is not in English\n",
      "432 433\n",
      "024964a7-d9f8-4981-866d-1e8c14828cdb\n",
      "Skipping 024964a7-d9f8-4981-866d-1e8c14828cdb because it is not in English\n",
      "434 435\n",
      "024c56c1-3e51-42b8-a58d-7e0e61c3aacd\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/024c56c1-3e51-42b8-a58d-7e0e61c3aacd.html\n",
      "upload: ../outputs/html-20270823/024c56c1-3e51-42b8-a58d-7e0e61c3aacd.html to s3://suno-annotation-public/preference-20270823/024c56c1-3e51-42b8-a58d-7e0e61c3aacd.html\n",
      "436 437\n",
      "024c7c2c-8d20-4060-bf67-15f86905dff3\n",
      "Skipping 024c7c2c-8d20-4060-bf67-15f86905dff3 because it is not in English\n",
      "438 439\n",
      "024dcc9d-d735-4732-a75b-1a1d77363c2f\n",
      "Skipping 024dcc9d-d735-4732-a75b-1a1d77363c2f because it is not in English\n",
      "440 441\n",
      "024e5610-d80c-4e4d-9a63-a22b5d1ae91c\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/024e5610-d80c-4e4d-9a63-a22b5d1ae91c.html\n",
      "upload: ../outputs/html-20270823/024e5610-d80c-4e4d-9a63-a22b5d1ae91c.html to s3://suno-annotation-public/preference-20270823/024e5610-d80c-4e4d-9a63-a22b5d1ae91c.html\n",
      "442 443\n",
      "024e8a57-1784-4c12-804f-6878eb1b33c8\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/024e8a57-1784-4c12-804f-6878eb1b33c8.html\n",
      "upload: ../outputs/html-20270823/024e8a57-1784-4c12-804f-6878eb1b33c8.html to s3://suno-annotation-public/preference-20270823/024e8a57-1784-4c12-804f-6878eb1b33c8.html\n",
      "444 445\n",
      "02523ed0-cdf4-4d9b-ad6c-002524159575\n",
      "Skipping 02523ed0-cdf4-4d9b-ad6c-002524159575 because it is not in English\n",
      "446 447\n",
      "025b1b3d-9f33-4695-8fd5-2b9031ffc329\n",
      "Skipping 025b1b3d-9f33-4695-8fd5-2b9031ffc329 because it is not in English\n",
      "448 449\n",
      "025c271f-9009-4e52-9808-ef06aa81af17\n",
      "Skipping 025c271f-9009-4e52-9808-ef06aa81af17 because it is not in English\n",
      "450 451\n",
      "025c2ccc-8e2c-4501-b3a1-23d4f650a81e\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/025c2ccc-8e2c-4501-b3a1-23d4f650a81e.html\n",
      "upload: ../outputs/html-20270823/025c2ccc-8e2c-4501-b3a1-23d4f650a81e.html to s3://suno-annotation-public/preference-20270823/025c2ccc-8e2c-4501-b3a1-23d4f650a81e.html\n",
      "452 453\n",
      "0265ea08-6b25-4fa1-a2f3-aee22ca984c1\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0265ea08-6b25-4fa1-a2f3-aee22ca984c1.html\n",
      "upload: ../outputs/html-20270823/0265ea08-6b25-4fa1-a2f3-aee22ca984c1.html to s3://suno-annotation-public/preference-20270823/0265ea08-6b25-4fa1-a2f3-aee22ca984c1.html\n",
      "454 455\n",
      "0266ecbc-3057-47c5-8f8e-11c1cca57b3a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0266ecbc-3057-47c5-8f8e-11c1cca57b3a.html\n",
      "upload: ../outputs/html-20270823/0266ecbc-3057-47c5-8f8e-11c1cca57b3a.html to s3://suno-annotation-public/preference-20270823/0266ecbc-3057-47c5-8f8e-11c1cca57b3a.html\n",
      "456 457\n",
      "0268bff1-94a3-41a2-b5e0-1876a2a826be\n",
      "Skipping 0268bff1-94a3-41a2-b5e0-1876a2a826be because it is not in English\n",
      "458 459\n",
      "026bfa33-4682-4b3e-a673-563d5c057f38\n",
      "Skipping 026bfa33-4682-4b3e-a673-563d5c057f38 because it is not in English\n",
      "460 461\n",
      "026eeb93-dbd8-4967-bffe-54547b828bac\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/026eeb93-dbd8-4967-bffe-54547b828bac.html\n",
      "upload: ../outputs/html-20270823/026eeb93-dbd8-4967-bffe-54547b828bac.html to s3://suno-annotation-public/preference-20270823/026eeb93-dbd8-4967-bffe-54547b828bac.html\n",
      "462 463\n",
      "0274eb9a-9bac-43c5-9f2c-39fef5d03d13\n",
      "Skipping 0274eb9a-9bac-43c5-9f2c-39fef5d03d13 because it is not in English\n",
      "464 465\n",
      "0279bcc6-cfb1-44e4-b698-62c9e876fef5\n",
      "Skipping 0279bcc6-cfb1-44e4-b698-62c9e876fef5 because it is not in English\n",
      "466 467\n",
      "027c35c1-2bcc-45e2-be88-d40e852fd076\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/027c35c1-2bcc-45e2-be88-d40e852fd076.html\n",
      "upload: ../outputs/html-20270823/027c35c1-2bcc-45e2-be88-d40e852fd076.html to s3://suno-annotation-public/preference-20270823/027c35c1-2bcc-45e2-be88-d40e852fd076.html\n",
      "468 469\n",
      "027cf28b-11e1-46c1-9931-189b56e8bd7a\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/027cf28b-11e1-46c1-9931-189b56e8bd7a.html\n",
      "upload: ../outputs/html-20270823/027cf28b-11e1-46c1-9931-189b56e8bd7a.html to s3://suno-annotation-public/preference-20270823/027cf28b-11e1-46c1-9931-189b56e8bd7a.html\n",
      "470 471\n",
      "027d872d-fc9b-4b91-a085-bd633636c21a\n",
      "Skipping 027d872d-fc9b-4b91-a085-bd633636c21a because it is not in English\n",
      "472 473\n",
      "027ea30e-1ab9-449b-8b15-883161abb5e0\n",
      "Skipping 027ea30e-1ab9-449b-8b15-883161abb5e0 because it is not in English\n",
      "474 475\n",
      "02803b6e-261c-4ce3-b27b-2eef1f7a9852\n",
      "Skipping 02803b6e-261c-4ce3-b27b-2eef1f7a9852 because it is not in English\n",
      "476 477\n",
      "02813be5-a8fb-47ad-a842-628b6bd7b31e\n",
      "Skipping 02813be5-a8fb-47ad-a842-628b6bd7b31e because it is not in English\n",
      "478 479\n",
      "0287aa94-2b35-4e1a-a065-29b45e7762b8\n",
      "Skipping 0287aa94-2b35-4e1a-a065-29b45e7762b8 because it contains profanity\n",
      "480 481\n",
      "0287e46c-14b6-4cea-be77-0b6197b667ae\n",
      "Skipping 0287e46c-14b6-4cea-be77-0b6197b667ae because it is not in English\n",
      "482 483\n",
      "028f2403-deeb-4a85-8499-221d82dcbec2\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/028f2403-deeb-4a85-8499-221d82dcbec2.html\n",
      "upload: ../outputs/html-20270823/028f2403-deeb-4a85-8499-221d82dcbec2.html to s3://suno-annotation-public/preference-20270823/028f2403-deeb-4a85-8499-221d82dcbec2.html\n",
      "484 485\n",
      "029177bf-fe63-4330-91fa-265a13ee6731\n",
      "Skipping 029177bf-fe63-4330-91fa-265a13ee6731 because it is not in English\n",
      "486 487\n",
      "029448b8-7d79-4c33-952d-2e6ae672cf3e\n",
      "Skipping 029448b8-7d79-4c33-952d-2e6ae672cf3e because it is not in English\n",
      "488 489\n",
      "0296ccec-312d-4ef5-adc7-9d0ea555c553\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0296ccec-312d-4ef5-adc7-9d0ea555c553.html\n",
      "upload: ../outputs/html-20270823/0296ccec-312d-4ef5-adc7-9d0ea555c553.html to s3://suno-annotation-public/preference-20270823/0296ccec-312d-4ef5-adc7-9d0ea555c553.html\n",
      "490 491\n",
      "0299c54f-9509-40f3-b4d8-7036547db8ed\n",
      "Skipping 0299c54f-9509-40f3-b4d8-7036547db8ed because it is not in English\n",
      "492 493\n",
      "02a097d4-8b29-4e51-9481-786329ae0db7\n",
      "Skipping 02a097d4-8b29-4e51-9481-786329ae0db7 because it is not in English\n",
      "494 495\n",
      "02a4405d-1218-42d6-8d21-b3763d8e763c\n",
      "Skipping 02a4405d-1218-42d6-8d21-b3763d8e763c because it contains profanity\n",
      "496 497\n",
      "02a5a2e8-c823-4dac-8813-93782e8cb163\n",
      "Skipping 02a5a2e8-c823-4dac-8813-93782e8cb163 because it is not in English\n",
      "498 499\n",
      "02a5b347-4586-46d7-ae9f-1670ea2c402c\n",
      "Skipping 02a5b347-4586-46d7-ae9f-1670ea2c402c because it is not in English\n",
      "500 501\n",
      "02a8205b-a619-40de-bbaa-2f417cab038d\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02a8205b-a619-40de-bbaa-2f417cab038d.html\n",
      "upload: ../outputs/html-20270823/02a8205b-a619-40de-bbaa-2f417cab038d.html to s3://suno-annotation-public/preference-20270823/02a8205b-a619-40de-bbaa-2f417cab038d.html\n",
      "502 503\n",
      "02a85f09-2479-4752-b663-3c836d8b9dab\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02a85f09-2479-4752-b663-3c836d8b9dab.html\n",
      "upload: ../outputs/html-20270823/02a85f09-2479-4752-b663-3c836d8b9dab.html to s3://suno-annotation-public/preference-20270823/02a85f09-2479-4752-b663-3c836d8b9dab.html\n",
      "504 505\n",
      "02a8f955-7ddc-4f28-9762-8f5a533f950a\n",
      "Skipping 02a8f955-7ddc-4f28-9762-8f5a533f950a because it is not in English\n",
      "506 507\n",
      "02b398ea-fe84-4bd4-b842-20f1f98253b8\n",
      "Skipping 02b398ea-fe84-4bd4-b842-20f1f98253b8 because it is not in English\n",
      "508 509\n",
      "02b48381-74e9-42fa-9211-0ab0357d2125\n",
      "Skipping 02b48381-74e9-42fa-9211-0ab0357d2125 because it contains profanity\n",
      "510 511\n",
      "02b7b35d-ea76-4b75-8181-5bef7743d54b\n",
      "Skipping 02b7b35d-ea76-4b75-8181-5bef7743d54b because it is not in English\n",
      "512 513\n",
      "02ba9caf-1ee7-4cef-b11b-d50e892fe02a\n",
      "Skipping 02ba9caf-1ee7-4cef-b11b-d50e892fe02a because it is not in English\n",
      "514 515\n",
      "02be47de-cbf4-4852-83b6-0aec747ef104\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02be47de-cbf4-4852-83b6-0aec747ef104.html\n",
      "upload: ../outputs/html-20270823/02be47de-cbf4-4852-83b6-0aec747ef104.html to s3://suno-annotation-public/preference-20270823/02be47de-cbf4-4852-83b6-0aec747ef104.html\n",
      "516 517\n",
      "02c2654d-69fc-4125-aea5-b92f167405ae\n",
      "Skipping 02c2654d-69fc-4125-aea5-b92f167405ae because it contains profanity\n",
      "518 519\n",
      "02c5d9d9-8c2a-46d8-b1ba-4d7b02bbed89\n",
      "Skipping 02c5d9d9-8c2a-46d8-b1ba-4d7b02bbed89 because it is not in English\n",
      "520 521\n",
      "02c91123-286b-4208-8ae1-0176b077ea43\n",
      "Skipping 02c91123-286b-4208-8ae1-0176b077ea43 because it is not in English\n",
      "522 523\n",
      "02ccbbfa-4190-43eb-92ac-2de384e417b1\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02ccbbfa-4190-43eb-92ac-2de384e417b1.html\n",
      "upload: ../outputs/html-20270823/02ccbbfa-4190-43eb-92ac-2de384e417b1.html to s3://suno-annotation-public/preference-20270823/02ccbbfa-4190-43eb-92ac-2de384e417b1.html\n",
      "524 525\n",
      "02cd1c5e-8f90-4c86-95ce-eed32a1e9f7e\n",
      "Skipping 02cd1c5e-8f90-4c86-95ce-eed32a1e9f7e because it is not in English\n",
      "526 527\n",
      "02d242ac-96a0-442c-95fd-d11d10eb05ed\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02d242ac-96a0-442c-95fd-d11d10eb05ed.html\n",
      "upload: ../outputs/html-20270823/02d242ac-96a0-442c-95fd-d11d10eb05ed.html to s3://suno-annotation-public/preference-20270823/02d242ac-96a0-442c-95fd-d11d10eb05ed.html\n",
      "528 529\n",
      "02d5ea02-5800-4f0d-8e12-8113b1f744d1\n",
      "Skipping 02d5ea02-5800-4f0d-8e12-8113b1f744d1 because it is not in English\n",
      "530 531\n",
      "02d62e9f-aede-4fe1-9bf9-6e0c89a9424d\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02d62e9f-aede-4fe1-9bf9-6e0c89a9424d.html\n",
      "upload: ../outputs/html-20270823/02d62e9f-aede-4fe1-9bf9-6e0c89a9424d.html to s3://suno-annotation-public/preference-20270823/02d62e9f-aede-4fe1-9bf9-6e0c89a9424d.html\n",
      "532 533\n",
      "02d80342-3fb9-42e5-85a4-b73a0dc64d0f\n",
      "Skipping 02d80342-3fb9-42e5-85a4-b73a0dc64d0f because it is not in English\n",
      "534 535\n",
      "02d8b238-d3e8-4081-9b18-f11b67dbab6e\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02d8b238-d3e8-4081-9b18-f11b67dbab6e.html\n",
      "upload: ../outputs/html-20270823/02d8b238-d3e8-4081-9b18-f11b67dbab6e.html to s3://suno-annotation-public/preference-20270823/02d8b238-d3e8-4081-9b18-f11b67dbab6e.html\n",
      "536 537\n",
      "02dc1163-2084-4509-b5ea-6865b7f91cc0\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02dc1163-2084-4509-b5ea-6865b7f91cc0.html\n",
      "upload: ../outputs/html-20270823/02dc1163-2084-4509-b5ea-6865b7f91cc0.html to s3://suno-annotation-public/preference-20270823/02dc1163-2084-4509-b5ea-6865b7f91cc0.html\n",
      "538 539\n",
      "02deaccc-56d7-4421-b354-a1d5a9712cbf\n",
      "Skipping 02deaccc-56d7-4421-b354-a1d5a9712cbf because it is not in English\n",
      "540 541\n",
      "02df4fd9-b6bd-4df0-b5aa-66cabe0ed2fe\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02df4fd9-b6bd-4df0-b5aa-66cabe0ed2fe.html\n",
      "upload: ../outputs/html-20270823/02df4fd9-b6bd-4df0-b5aa-66cabe0ed2fe.html to s3://suno-annotation-public/preference-20270823/02df4fd9-b6bd-4df0-b5aa-66cabe0ed2fe.html\n",
      "542 543\n",
      "02e46d0f-3f0e-4026-a928-b7cf7514138c\n",
      "Skipping 02e46d0f-3f0e-4026-a928-b7cf7514138c because it is not in English\n",
      "544 545\n",
      "02e78979-add1-4a93-a57d-3753b8ff5b98\n",
      "Skipping 02e78979-add1-4a93-a57d-3753b8ff5b98 because it is not in English\n",
      "546 547\n",
      "02e8b6a5-505b-41b6-b1ca-72d10b7315cc\n",
      "Skipping 02e8b6a5-505b-41b6-b1ca-72d10b7315cc because it is not in English\n",
      "548 549\n",
      "02e9b17e-678b-4f85-a6eb-d01f430c5caa\n",
      "Skipping 02e9b17e-678b-4f85-a6eb-d01f430c5caa because it is not in English\n",
      "550 551\n",
      "02eb0e24-1d87-4083-809d-e54ed76d1f0a\n",
      "Skipping 02eb0e24-1d87-4083-809d-e54ed76d1f0a because it contains profanity\n",
      "552 553\n",
      "02ed589c-cda9-41ee-aebd-7e96103b883d\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02ed589c-cda9-41ee-aebd-7e96103b883d.html\n",
      "upload: ../outputs/html-20270823/02ed589c-cda9-41ee-aebd-7e96103b883d.html to s3://suno-annotation-public/preference-20270823/02ed589c-cda9-41ee-aebd-7e96103b883d.html\n",
      "554 555\n",
      "02ed7192-725c-4dcd-86aa-38a038011031\n",
      "Skipping 02ed7192-725c-4dcd-86aa-38a038011031 because it contains profanity\n",
      "556 557\n",
      "02efcbd4-06e8-4c3a-b20f-bcb64d42a7a5\n",
      "Skipping 02efcbd4-06e8-4c3a-b20f-bcb64d42a7a5 because it is not in English\n",
      "558 559\n",
      "02f1e07c-43c0-49bb-8f2e-72ee5d8f6cfe\n",
      "Skipping 02f1e07c-43c0-49bb-8f2e-72ee5d8f6cfe because it is not in English\n",
      "560 561\n",
      "02f49232-b829-4016-ad87-2150f09910c7\n",
      "Skipping 02f49232-b829-4016-ad87-2150f09910c7 because it is not in English\n",
      "562 563\n",
      "02f59f34-a3d3-4c18-b485-c86cd29cd245\n",
      "Skipping 02f59f34-a3d3-4c18-b485-c86cd29cd245 because it is not in English\n",
      "564 565\n",
      "02f6c919-aedd-4ca3-a3f4-c0dbd8add0ab\n",
      "Skipping 02f6c919-aedd-4ca3-a3f4-c0dbd8add0ab because it contains profanity\n",
      "566 567\n",
      "02f74031-8786-4ed1-b396-c7ac44c24df0\n",
      "Skipping 02f74031-8786-4ed1-b396-c7ac44c24df0 because it is not in English\n",
      "568 569\n",
      "02f7729c-f1d5-448b-8d2d-08975fcfeab3\n",
      "Skipping 02f7729c-f1d5-448b-8d2d-08975fcfeab3 because it is not in English\n",
      "570 571\n",
      "02fc882f-dbea-4a15-88ba-5531ba63a3e5\n",
      "Skipping 02fc882f-dbea-4a15-88ba-5531ba63a3e5 because it is not in English\n",
      "572 573\n",
      "02fce0ce-3709-42a0-a041-a9c179914e08\n",
      "Skipping 02fce0ce-3709-42a0-a041-a9c179914e08 because it contains profanity\n",
      "574 575\n",
      "02fd9a90-534a-4cd5-beb5-05a0f41a5dfb\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/02fd9a90-534a-4cd5-beb5-05a0f41a5dfb.html\n",
      "upload: ../outputs/html-20270823/02fd9a90-534a-4cd5-beb5-05a0f41a5dfb.html to s3://suno-annotation-public/preference-20270823/02fd9a90-534a-4cd5-beb5-05a0f41a5dfb.html\n",
      "576 577\n",
      "02ff844d-fdab-4a7d-a451-cc2233925cca\n",
      "Skipping 02ff844d-fdab-4a7d-a451-cc2233925cca because it contains profanity\n",
      "578 579\n",
      "030784bc-ce71-4c58-bc35-0d58ea9f4356\n",
      "Skipping 030784bc-ce71-4c58-bc35-0d58ea9f4356 because it is not in English\n",
      "580 581\n",
      "030998ce-a2b7-4f0d-a6af-64b912a88f3c\n",
      "Skipping 030998ce-a2b7-4f0d-a6af-64b912a88f3c because it is not in English\n",
      "582 583\n",
      "030ad4ba-eb26-457e-b49f-465ee4622c0c\n",
      "Skipping 030ad4ba-eb26-457e-b49f-465ee4622c0c because it is not in English\n",
      "584 585\n",
      "030c8ed5-de6f-4399-a388-ae11cb244186\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/030c8ed5-de6f-4399-a388-ae11cb244186.html\n",
      "upload: ../outputs/html-20270823/030c8ed5-de6f-4399-a388-ae11cb244186.html to s3://suno-annotation-public/preference-20270823/030c8ed5-de6f-4399-a388-ae11cb244186.html\n",
      "586 587\n",
      "030cb46d-02a7-4f43-8eba-d311da8c9796\n",
      "Skipping 030cb46d-02a7-4f43-8eba-d311da8c9796 because it is not in English\n",
      "588 589\n",
      "030dc410-4198-40e1-9830-c217b7f498f3\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/030dc410-4198-40e1-9830-c217b7f498f3.html\n",
      "upload: ../outputs/html-20270823/030dc410-4198-40e1-9830-c217b7f498f3.html to s3://suno-annotation-public/preference-20270823/030dc410-4198-40e1-9830-c217b7f498f3.html\n",
      "590 591\n",
      "03114d87-22ae-4c93-a2cb-7056eb35125a\n",
      "Skipping 03114d87-22ae-4c93-a2cb-7056eb35125a because it is not in English\n",
      "592 593\n",
      "0318982a-7c45-4f3a-8cad-a1a2ed72701c\n",
      "Skipping 0318982a-7c45-4f3a-8cad-a1a2ed72701c because it contains profanity\n",
      "594 595\n",
      "031c7682-d515-4648-8117-12525fb67572\n",
      "Skipping 031c7682-d515-4648-8117-12525fb67572 because it is not in English\n",
      "596 597\n",
      "03207d66-1126-43ea-8513-dbf809342302\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/03207d66-1126-43ea-8513-dbf809342302.html\n",
      "upload: ../outputs/html-20270823/03207d66-1126-43ea-8513-dbf809342302.html to s3://suno-annotation-public/preference-20270823/03207d66-1126-43ea-8513-dbf809342302.html\n",
      "598 599\n",
      "0320fc31-d98a-4690-b73d-ac8e7e74bbb1\n",
      "Skipping 0320fc31-d98a-4690-b73d-ac8e7e74bbb1 because it is not in English\n",
      "600 601\n",
      "032153d7-e644-4d9f-b545-058b449a36ba\n",
      "Skipping 032153d7-e644-4d9f-b545-058b449a36ba because it is not in English\n",
      "602 603\n",
      "0321b50d-a1d3-47b6-b1e3-9871586f00b0\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0321b50d-a1d3-47b6-b1e3-9871586f00b0.html\n",
      "upload: ../outputs/html-20270823/0321b50d-a1d3-47b6-b1e3-9871586f00b0.html to s3://suno-annotation-public/preference-20270823/0321b50d-a1d3-47b6-b1e3-9871586f00b0.html\n",
      "604 605\n",
      "0322e2d3-b261-4875-b26f-568c18162972\n",
      "Skipping 0322e2d3-b261-4875-b26f-568c18162972 because it is not in English\n",
      "606 607\n",
      "03234525-b114-42c1-9d59-99ebbda4d1f3\n",
      "Skipping 03234525-b114-42c1-9d59-99ebbda4d1f3 because it contains profanity\n",
      "608 609\n",
      "03239855-63fc-41ee-ac93-f60478e48ddd\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/03239855-63fc-41ee-ac93-f60478e48ddd.html\n",
      "upload: ../outputs/html-20270823/03239855-63fc-41ee-ac93-f60478e48ddd.html to s3://suno-annotation-public/preference-20270823/03239855-63fc-41ee-ac93-f60478e48ddd.html\n",
      "610 611\n",
      "0326d2a6-5b8a-4b55-be0d-29ad45f77fcc\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0326d2a6-5b8a-4b55-be0d-29ad45f77fcc.html\n",
      "upload: ../outputs/html-20270823/0326d2a6-5b8a-4b55-be0d-29ad45f77fcc.html to s3://suno-annotation-public/preference-20270823/0326d2a6-5b8a-4b55-be0d-29ad45f77fcc.html\n",
      "612 613\n",
      "0327c3ce-9c4a-46e3-8dd4-5f4fa48fc0ae\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0327c3ce-9c4a-46e3-8dd4-5f4fa48fc0ae.html\n",
      "upload: ../outputs/html-20270823/0327c3ce-9c4a-46e3-8dd4-5f4fa48fc0ae.html to s3://suno-annotation-public/preference-20270823/0327c3ce-9c4a-46e3-8dd4-5f4fa48fc0ae.html\n",
      "614 615\n",
      "032bde43-688a-40ab-9785-ee029b20d389\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/032bde43-688a-40ab-9785-ee029b20d389.html\n",
      "upload: ../outputs/html-20270823/032bde43-688a-40ab-9785-ee029b20d389.html to s3://suno-annotation-public/preference-20270823/032bde43-688a-40ab-9785-ee029b20d389.html\n",
      "616 617\n",
      "032c2caf-bec8-413b-bfe3-1bb85b0e8712\n",
      "Skipping 032c2caf-bec8-413b-bfe3-1bb85b0e8712 because it is not in English\n",
      "618 619\n",
      "032f0e04-9c44-4e7f-94a4-5ce4104c51d0\n",
      "Skipping 032f0e04-9c44-4e7f-94a4-5ce4104c51d0 because it is not in English\n",
      "620 621\n",
      "033243c6-0cf0-48df-9bd9-a41755df0bf9\n",
      "https://suno-annotation-public.s3.amazonaws.com/preference-20270823/033243c6-0cf0-48df-9bd9-a41755df0bf9.html\n",
      "upload: ../outputs/html-20270823/033243c6-0cf0-48df-9bd9-a41755df0bf9.html to s3://suno-annotation-public/preference-20270823/033243c6-0cf0-48df-9bd9-a41755df0bf9.html\n"
     ]
    }
   ],
   "source": [
    "\n",
    "timestamp = 20270823\n",
    "s3_bucket = f\"s3://suno-annotation-public/preference-{timestamp}/\" # this must have trailing slash\n",
    "s3_bucket_url = f\"https://suno-annotation-public.s3.amazonaws.com/preference-{timestamp}\"\n",
    "output_html_dir = f\"/home/christian/code/christian/outputs/html-{timestamp}\"\n",
    "os.makedirs(output_html_dir, exist_ok=True)\n",
    "base_html_filepath = \"/home/christian/code/christian/outputs/templates/ab_base.html\"\n",
    "max_num_examples = 100\n",
    "global_keys = []\n",
    "\n",
    "# open the html file\n",
    "# Read the HTML file\n",
    "with open(base_html_filepath, \"r\", encoding=\"utf-8\") as file:\n",
    "    soup = BeautifulSoup(file, \"html.parser\")\n",
    "\n",
    "metadata = {}\n",
    "\n",
    "assets = [] # list of assets to add to the dataset\n",
    "for i in range(0, len(df), 2):\n",
    "    # get the first and second clip\n",
    "    clip_0 = df.iloc[i]\n",
    "    clip_1 = df.iloc[i+1]\n",
    "    print(i, i+1)\n",
    "\n",
    "    # use request id as the unique identifier\n",
    "    request_id = clip_0[\"request_id\"]\n",
    "    print(request_id)\n",
    "\n",
    "    # get clip details\n",
    "    clip_0_id, clip_0_prompt, clip_0_tags = get_clip_details(clip_0)\n",
    "    clip_1_id, clip_1_prompt, clip_1_tags = get_clip_details(clip_1)\n",
    "\n",
    "    # check if the lyrics are english\n",
    "    if not is_english(clip_0_prompt):\n",
    "        print(f\"Skipping {request_id} because it is not in English\")\n",
    "        continue\n",
    "\n",
    "    # check for profanity\n",
    "    if profanity.contains_profanity(clip_0_prompt):\n",
    "        print(f\"Skipping {request_id} because it contains profanity\")\n",
    "        continue\n",
    "    \n",
    "    clip_0_s3_filepath = f\"s3://suno-data-uploads/studio/uploads/{clip_0_id}.mp3\"\n",
    "    clip_1_s3_filepath = f\"s3://suno-data-uploads/studio/uploads/{clip_1_id}.mp3\"\n",
    "\n",
    "    # check if the audio files exist\n",
    "    #if not check_s3_file_exists(clip_0_s3_filepath):\n",
    "    #os.system(f\"aws s3 cp {clip_0_s3_filepath} {s3_bucket}\")\n",
    "\n",
    "    #if not check_s3_file_exists(clip_1_s3_filepath):\n",
    "    #os.system(f\"aws s3 cp {clip_1_s3_filepath} {s3_bucket}\")\n",
    "\n",
    "    orig_pref = \"b\" # by default the second clip is the preferred one\n",
    "\n",
    "    # randomly swap the clips\n",
    "    if np.random.rand() > 0.5:\n",
    "        # swap the clips\n",
    "        tmp_clip_id = clip_0_id\n",
    "        clip_0_id = clip_1_id\n",
    "        clip_1_id = tmp_clip_id\n",
    "        orig_pref = \"a\"\n",
    "\n",
    "    # edit the html file to add audios and prompt information\n",
    "    soup.find(id=\"audio1\")['src'] = f\"{s3_bucket_url}/{clip_0_id}.mp3\"\n",
    "    soup.find(id=\"audio2\")['src'] = f\"{s3_bucket_url}/{clip_1_id}.mp3\"\n",
    "\n",
    "    # Find the elements by ID\n",
    "    lyrics_div = soup.find(id=\"lyrics\")\n",
    "    tags_div = soup.find(id=\"tags\")\n",
    "\n",
    "    # Clear the existing content\n",
    "    lyrics_div.clear()\n",
    "    tags_div.clear()\n",
    "\n",
    "    # Insert the content directly\n",
    "    tags_div.string = f\"Tags: {clip_0_tags}\"\n",
    "    lyrics_div.string = f\"Lyrics: {clip_0_prompt}\"\n",
    "\n",
    "    # Save the modified HTML back to disk\n",
    "    output_filepath = os.path.join(output_html_dir, f\"{request_id}.html\")\n",
    "    with open(output_filepath, \"w\", encoding=\"utf-8\") as fp:\n",
    "        fp.write(str(soup))\n",
    "\n",
    "    # push html file to s3 public bucket\n",
    "    s3_html_filepath = f\"{s3_bucket}{request_id}.html\"\n",
    "    s3_html_url = f\"{s3_bucket_url}/{request_id}.html\"\n",
    "    print(s3_html_url)\n",
    "    os.system(f\"aws s3 cp {output_filepath} {s3_html_filepath}\")\n",
    "\n",
    "    # add to data row list\n",
    "    assets.append(\n",
    "        {\n",
    "            \"row_data\": s3_html_url,\n",
    "            \"global_key\": request_id,\n",
    "        }\n",
    "    )\n",
    "\n",
    "    metadata[request_id] = {\n",
    "        \"clip_a_id\": clip_0_id,\n",
    "        \"clip_b_id\": clip_1_id,\n",
    "        \"clip_a_url\" : f\"{s3_bucket_url}/{clip_0_id}.mp3\",\n",
    "        \"clip_b_url\" : f\"{s3_bucket_url}/{clip_1_id}.mp3\",\n",
    "        \"orig_pref\": orig_pref,\n",
    "    }\n",
    "\n",
    "    global_keys.append(request_id)\n",
    "    \n",
    "\n",
    "    if len(assets) >= max_num_examples:\n",
    "        break\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "# save json metadata\n",
    "metadata_filepath = f\"/home/christian/code/christian/outputs/metadata-{timestamp}.json\"\n",
    "with open(metadata_filepath, \"w\") as fp:\n",
    "    json.dump(metadata, fp)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "None\n"
     ]
    }
   ],
   "source": [
    "# Bulk add data rows to the dataset\n",
    "task = dataset.create_data_rows(assets)\n",
    "task.wait_till_done()\n",
    "print(task.errors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'clip_a_id': '0f8eb3cb-02b5-4775-bedc-2201de0bda54', 'clip_b_id': 'b5276937-b967-44eb-b471-b5a06dc3691f', 'clip_a_url': 'https://suno-annotation-public.s3.amazonaws.com/preference-20270823/0f8eb3cb-02b5-4775-bedc-2201de0bda54.mp3', 'clip_b_url': 'https://suno-annotation-public.s3.amazonaws.com/preference-20270823/b5276937-b967-44eb-b471-b5a06dc3691f.mp3', 'orig_pref': 'a'}\n"
     ]
    }
   ],
   "source": [
    "print(metadata[\"026eeb93-dbd8-4967-bffe-54547b828bac\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Setup Ontology and Create Labeling Project"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/christian/miniconda3/envs/suno_env/lib/python3.10/site-packages/labelbox/schema/project.py:857: UserWarning: Connecting default labeling editor for the project.\n",
      "  warnings.warn(\"Connecting default labeling editor for the project.\")\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Batch:  <Batch {\n",
      "    \"consensus_settings_json\": \"{\\\"numberOfLabels\\\":3,\\\"coveragePercentage\\\":0}\",\n",
      "    \"created_at\": \"2024-08-30 19:00:57+00:00\",\n",
      "    \"name\": \"first-batch-html-demo\",\n",
      "    \"size\": 100,\n",
      "    \"uid\": \"30d6be30-6702-11ef-83af-65497ceb4e0c\",\n",
      "    \"updated_at\": \"2024-08-30 19:00:57+00:00\"\n",
      "}>\n"
     ]
    }
   ],
   "source": [
    "ontology_builder = lb.OntologyBuilder(\n",
    "    classifications=[ \n",
    "        lb.Classification( \n",
    "        class_type=lb.Classification.Type.RADIO, \n",
    "        name=\"Preference\", \n",
    "        options=[\n",
    "            lb.Option(value=\"A\"),\n",
    "            lb.Option(value=\"B\"),\n",
    "            lb.Option(value=\"Neither\")\n",
    "        ]\n",
    "        )\n",
    "    ]\n",
    ")\n",
    "\n",
    "ontology = client.create_ontology(\"Ontology HTML Annotations\", ontology_builder.asdict(), media_type=lb.MediaType.Html)\n",
    "\n",
    "project = client.create_project(name=\"html_project_2\", \n",
    "                                    media_type=lb.MediaType.Html)\n",
    "\n",
    "# Setup your ontology \n",
    "project.connect_ontology(ontology)\n",
    "\n",
    "# send rows to project\n",
    "batch = project.create_batch(\n",
    "  \"first-batch-html-demo\", # Each batch in a project must have a unique name\n",
    "  global_keys=global_keys, # Paginated collection of data row objects, list of data row ids or global keys\n",
    "  priority=5 # priority between 1(highest) - 5(lowest)\n",
    ")\n",
    "\n",
    "print(\"Batch: \", batch)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Covers"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# find all examples \n",
    "local_dir = \"/home/christian/code/christian/notebooks/outputs/covers-20240816\"\n",
    "s3_bucket = \"s3://suno-annotation-public/covers-20240816\"\n",
    "s3_bucket_url = \"https://suno-annotation-public.s3.amazonaws.com/covers-20240816\"\n",
    "\n",
    "# find all json files \n",
    "metas = glob.glob(os.path.join(local_dir, \"*.json\"))\n",
    "print(f\"Found {len(metas)} examples...\")\n",
    "\n",
    "metas = metas[:10] # just the first 10 for now\n",
    "\n",
    "assets = [] # list of assets to add to the dataset\n",
    "\n",
    "for meta in metas:\n",
    "    with open(meta, \"r\") as f:\n",
    "        data = json.load(f)\n",
    "\n",
    "    meta_id = data[\"uid\"]\n",
    "\n",
    "    # upload the audio files to s3 bucket\n",
    "    #os.system(f\"aws s3 cp {local_dir}/{meta_id}-source.mp3 {s3_bucket}/\")\n",
    "    #os.system(f\"aws s3 cp {local_dir}/{meta_id}-cover-0.mp3 {s3_bucket}/\")\n",
    "    #os.system(f\"aws s3 cp {local_dir}/{meta_id}-cover-1.mp3 {s3_bucket}/\")\n",
    "\n",
    "    # build paths to audio files with this uid\n",
    "    s3_src_a_path = os.path.join(s3_bucket_url, f\"{meta_id}-source.mp3\")\n",
    "    s3_gen_a_path = os.path.join(s3_bucket_url, f\"{meta_id}-cover-0.mp3\")\n",
    "    s3_gen_b_path = os.path.join(s3_bucket_url, f\"{meta_id}-cover-1.mp3\")\n",
    "\n",
    "    target_tags = data[\"target_tags\"]\n",
    "    print(\"target tags:\", target_tags)\n",
    "    lyrics = data[\"lyrics\"]\n",
    "\n",
    "    assets.append(\n",
    "        {\n",
    "            \"global_key\": meta_id,\n",
    "            \"row_data\": s3_html_url,\n",
    "        \n",
    "        }\n",
    "    )\n",
    "    \n",
    "# Bulk add data rows to the dataset\n",
    "task = dataset.create_data_rows(assets)\n",
    "task.wait_till_done()\n",
    "print(task.errors)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create data payload\n",
    "# Use global key, a unique ID to identify an asset throughout Labelbox workflow. Learn more: https://docs.labelbox.com/docs/global-keys\n",
    "# You can add metadata fields to your data rows. Learn more: https://docs.labelbox.com/docs/import-metadata\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "suno_env",
   "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": "3.10.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}