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

format output

Browse Source
This commit is contained in:
HamidReza Montazer 2024-12-25 11:21:06 +03:30
parent 8752b6225c
commit 65f4c0c380
1 changed files with 50 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

66
3.dadegan_noor.ipynb
View File

@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 39,
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
@ -15,7 +15,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
@ -28,7 +28,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
@ -40,15 +40,7 @@
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 3/3 [00:01<00:00, 2.62it/s]\n"
]
}
],
"outputs": [],
"source": [
"for verb in tqdm(verbs):\n",
" response = requests.get(\"http://search.dadegan.ir/\", params={\"q\": verb})\n",
@ -58,14 +50,33 @@
},
{
"cell_type": "code",
"execution_count": null,
"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 [00:33<00:00, 122.76it/s]\n"
"100%|██████████| 4167/4167 [00:34<00:00, 122.03it/s]\n"
]
}
],
@ -84,19 +95,42 @@
" 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\"] = str(structure.findAll(\"div\", {\"class\": \"valency\"})[0])\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": 59,
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [