montazerh82/persian_verbs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

change data structure of noor result

Browse Source
This commit is contained in:
HamidReza Montazer 2024-12-19 12:12:33 +03:30
parent f3e8c366d5
commit 8752b6225c
1 changed files with 29 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
3.dadegan_noor.ipynb
View File

@ -2,19 +2,20 @@
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from bs4 import BeautifulSoup\n",
"from pathlib import Path\n",
"from tqdm import tqdm"
"from tqdm import tqdm\n",
"import json"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@ -27,7 +28,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
@ -57,19 +58,19 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 4167/4167 [00:22<00:00, 186.02it/s]\n"
"100%|██████████| 4167/4167 [00:33<00:00, 122.76it/s]\n"
]
}
],
"source": [
"result = {}\n",
"results = []\n",
"\n",
"for verb in tqdm(verbs):\n",
" with open(htmls_path / (verb + \".html\"), \"r\") as f:\n",
@ -80,10 +81,27 @@
" past_stem = stems[0].text\n",
" present_stem = stems[1].text\n",
"\n",
" result[verb] = {}\n",
"\n",
" result[verb][\"past_stem\"] = past_stem\n",
" result[verb][\"present_stem\"] = present_stem"
" 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)"
]
},
{