persian_verbs/3.dadegan_noor.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "from bs4 import BeautifulSoup\n",
    "from pathlib import Path\n",
    "from tqdm import tqdm\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "this_dir_path = Path().resolve()\n",
    "data_path = this_dir_path / \"Data\"\n",
    "input_verb_path = data_path / \"verbs_noor.txt\"\n",
    "htmls_path = data_path / \"htmls_noor\"\n",
    "output_verb_path = data_path / \"verbs_noor.json\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(input_verb_path, \"r\") as f:\n",
    "    verbs = [verb[:-1] for verb in f.readlines()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for verb in tqdm(verbs):\n",
    "    response = requests.get(\"http://search.dadegan.ir/\", params={\"q\": verb})\n",
    "    with open(htmls_path / (verb + \".html\"), \"w\") as f:\n",
    "        f.write(response.text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def find_start_and_end(phrase, subphrase):\n",
    "    words1 = phrase.split()\n",
    "    words2 = subphrase.split()\n",
    "\n",
    "    for i in range(len(words1)):\n",
    "        if words1[i : i + len(words2)] == words2:\n",
    "            start = i\n",
    "            end = i + len(words2) - 1\n",
    "            return start, end\n",
    "\n",
    "    return \"404 - Not found!\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 4167/4167 [00:34<00:00, 122.03it/s]\n"
     ]
    }
   ],
   "source": [
    "results = []\n",
    "\n",
    "for verb in tqdm(verbs):\n",
    "    with open(htmls_path / (verb + \".html\"), \"r\") as f:\n",
    "        text = f.read()\n",
    "    soup = BeautifulSoup(text, \"html.parser\")\n",
    "\n",
    "    stems = soup.findAll(\"td\", {\"class\": \"c3\"})[1:]\n",
    "    past_stem = stems[0].text\n",
    "    present_stem = stems[1].text\n",
    "\n",
    "    structures = soup.select(\"div.section-wrapper.more-examples\")\n",
    "    for structure in structures:\n",
    "        examples = structure.findAll(\"div\", {\"class\": \"example\"})\n",
    "        valency = structure.findAll(\"div\", {\"class\": \"valency\"})[0]\n",
    "        for example in examples:\n",
    "            result = {}\n",
    "            result[\"verb\"] = verb\n",
    "            result[\"past_stem\"] = past_stem\n",
    "            result[\"present_stem\"] = present_stem\n",
    "            result[\"structure_key\"] = [\n",
    "                e.get(\"class\")[0] for e in valency.findAll(\"span\", recursive=False)\n",
    "            ]\n",
    "            result[\"structure_fa\"] = [\n",
    "                e.text for e in valency.findAll(\"span\", recursive=False)\n",
    "            ]\n",
    "            result[\"html\"] = str(example)\n",
    "            result[\"text\"] = example.text\n",
    "\n",
    "            result[\"tags\"] = []\n",
    "            spans = example.findAll(\"span\", recursive=False)\n",
    "            for span in spans:\n",
    "                span_text = span.get_text(strip=True)\n",
    "                start_index, end_index = find_start_and_end(example.text, span_text)\n",
    "\n",
    "                result[\"tags\"].append(\n",
    "                    {\n",
    "                        \"text\": span_text,\n",
    "                        \"start\": start_index,\n",
    "                        \"end\": end_index,\n",
    "                        \"class\": span[\"class\"][0],\n",
    "                    }\n",
    "                )\n",
    "\n",
    "            results.append(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(output_verb_path, \"w\", encoding=\"utf-8\") as f:\n",
    "    json.dump(results, f, ensure_ascii=False, indent=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".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": "3.10.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}