{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from glob import glob\n",
    "import xml.etree.ElementTree as ET\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "files = glob(\"../../kouigenjimonogatari.github.io/xml/lw/*.xml\")\n",
    "files.sort()\n",
    "data = []\n",
    "\n",
    "for file in files:\n",
    "    tree = ET.parse(file)\n",
    "    root = tree.getroot()\n",
    "\n",
    "    vol = int(file.split(\"/\")[-1].split(\".\")[0])\n",
    "    segs = root.findall(\".//{http://www.tei-c.org/ns/1.0}seg\")\n",
    "    texts = {}\n",
    "\n",
    "    for seg in segs:        \n",
    "        corresp = seg.attrib[\"corresp\"]\n",
    "        page = int(corresp.split(\"/\")[-1].split(\"-\")[0])\n",
    "        text = seg.text\n",
    "\n",
    "        if page not in texts:\n",
    "            texts[page] = []\n",
    "\n",
    "        texts[page].append(text)\n",
    "\n",
    "    for page in texts:\n",
    "        text = \" \".join(texts[page])\n",
    "        data.append({\"vol\": vol, \"page\": page, \"text\": text})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(\"../data.json\", \"w\") as f:\n",
    "    json.dump(data, f, ensure_ascii=False, indent=4)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "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": "3.9.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}