1.extract_verbs_from_PVC.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -20,10 +20,7 @@
     "data_path = this_dir_path / \"Data\"\n",
     "verb_path = data_path / \"PVC\" / \"Data\" / \"TXT\" / \"verb.txt\"\n",
     "processed_past_verb_path = data_path / \"verbs_past_PVC.json\"\n",
-    "processed_present_verb_path = data_path / \"verbs_present_PVC.json\"\n",
-    "\n",
-    "# You can download the PVC data from https://www.peykaregan.ir/dataset/%D9%85%D8%AC%D9%85%D9%88%D8%B9%D9%87-%D8%A7%D9%81%D8%B9%D8%A7%D9%84-%D8%AA%D8%B5%D8%B1%DB%8C%D9%81%E2%80%8C%D8%B4%D8%AF%D9%87-%D9%81%D8%A7%D8%B1%D8%B3%DB%8C\n",
-    "# After downloading, unzip the data and place it in a directory called Data."
+    "processed_present_verb_path = data_path / \"verbs_present_PVC.json\""
    ]
   },
   {

3.dadegan_noor.ipynb

@@ -2,20 +2,19 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
     "import requests\n",
     "from bs4 import BeautifulSoup\n",
     "from pathlib import Path\n",
-    "from tqdm import tqdm\n",
-    "import json"
+    "from tqdm import tqdm"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -28,7 +27,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -58,19 +57,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 4167/4167 [00:33<00:00, 122.76it/s]\n"
+      "100%|██████████| 4167/4167 [00:22<00:00, 186.02it/s]\n"
      ]
     }
    ],
    "source": [
-    "results = []\n",
+    "result = {}\n",
     "\n",
     "for verb in tqdm(verbs):\n",
     "    with open(htmls_path / (verb + \".html\"), \"r\") as f:\n",
@@ -81,27 +80,10 @@
     "    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",
-    "        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\"] = str(structure.findAll(\"div\", {\"class\": \"valency\"})[0])\n",
-    "            result[\"text\"] = example.text\n",
-    "            results.append(result)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open(output_verb_path, \"w\", encoding=\"utf-8\") as f:\n",
-    "    json.dump(results, f, ensure_ascii=False, indent=4)"
+    "    result[verb] = {}\n",
+    "\n",
+    "    result[verb][\"past_stem\"] = past_stem\n",
+    "    result[verb][\"present_stem\"] = present_stem"
    ]
   },
   {