Spaces:
Paused
Paused
Upload 2 files
Browse files- app/enhanced_legal_scraper.py +366 -0
- app/legal_scraper_interface.py +1190 -0
app/enhanced_legal_scraper.py
ADDED
@@ -0,0 +1,366 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import os
|
3 |
+
import sys
|
4 |
+
from pathlib import Path
|
5 |
+
|
6 |
+
# اضافه کردن مسیر فعلی به sys.path
|
7 |
+
sys.path.insert(0, str(Path(__file__).parent))
|
8 |
+
|
9 |
+
# ایمپورت رابط اسکراپر
|
10 |
+
from enhanced_legal_scraper import EnhancedLegalScraper, LegalDocument
|
11 |
+
import pandas as pd
|
12 |
+
import sqlite3
|
13 |
+
import json
|
14 |
+
from datetime import datetime
|
15 |
+
from typing import List, Dict, Tuple
|
16 |
+
import plotly.express as px
|
17 |
+
|
18 |
+
class LegalScraperInterface:
|
19 |
+
"""Gradio interface for enhanced legal scraper"""
|
20 |
+
|
21 |
+
def __init__(self):
|
22 |
+
self.scraper = EnhancedLegalScraper(delay=1.5)
|
23 |
+
self.is_scraping = False
|
24 |
+
|
25 |
+
def scrape_websites(self, urls_text: str, max_docs: int) -> Tuple[str, str, str]:
|
26 |
+
"""Scrape websites from provided URLs"""
|
27 |
+
if self.is_scraping:
|
28 |
+
return "❌ اسکراپینگ در حال انجام است", "", ""
|
29 |
+
|
30 |
+
urls = [url.strip() for url in urls_text.split('\n') if url.strip()]
|
31 |
+
if not urls:
|
32 |
+
return "❌ لطفاً URL وارد کنید", "", ""
|
33 |
+
|
34 |
+
try:
|
35 |
+
self.is_scraping = True
|
36 |
+
documents = self.scraper.scrape_real_sources(urls, max_docs)
|
37 |
+
|
38 |
+
status = f"✅ اسکراپینگ کامل شد - {len(documents)} سند جمعآوری شد"
|
39 |
+
|
40 |
+
summary_lines = [
|
41 |
+
f"📊 **خلاصه نتایج:**",
|
42 |
+
f"- تعداد کل اسناد: {len(documents)}",
|
43 |
+
f"- منابع پردازش شده: {len(urls)}",
|
44 |
+
f"- زمان اسکراپینگ: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}",
|
45 |
+
"",
|
46 |
+
"📋 **جزئیات:**"
|
47 |
+
]
|
48 |
+
|
49 |
+
for i, doc in enumerate(documents[:5]):
|
50 |
+
summary_lines.append(f"{i+1}. {doc.title[:50]}...")
|
51 |
+
|
52 |
+
summary = "\n".join(summary_lines)
|
53 |
+
|
54 |
+
preview_lines = []
|
55 |
+
for doc in documents[:3]:
|
56 |
+
preview_lines.extend([
|
57 |
+
f"**{doc.title}**",
|
58 |
+
f"نوع: {doc.document_type}",
|
59 |
+
f"منبع: {doc.source_url}",
|
60 |
+
f"امتیاز اهمیت: {doc.importance_score:.2f}",
|
61 |
+
f"خلاصه: {doc.summary[:100]}..." if doc.summary else "بدون خلاصه",
|
62 |
+
"---"
|
63 |
+
])
|
64 |
+
|
65 |
+
preview = "\n".join(preview_lines) if preview_lines else "هیچ سندی یافت نشد"
|
66 |
+
|
67 |
+
return status, summary, preview
|
68 |
+
|
69 |
+
except Exception as e:
|
70 |
+
error_msg = f"❌ خطا در اسکراپینگ: {str(e)}"
|
71 |
+
return error_msg, "", ""
|
72 |
+
|
73 |
+
finally:
|
74 |
+
self.is_scraping = False
|
75 |
+
|
76 |
+
def get_database_stats(self) -> Tuple[str, str]:
|
77 |
+
"""Get database statistics and visualizations"""
|
78 |
+
try:
|
79 |
+
stats = self.scraper.get_enhanced_statistics()
|
80 |
+
|
81 |
+
stats_lines = [
|
82 |
+
"📊 **آمار پایگاه داده:**",
|
83 |
+
f"- کل اسناد: {stats.get('total_documents', 0)}",
|
84 |
+
"",
|
85 |
+
"📈 **بر اساس نوع:**"
|
86 |
+
]
|
87 |
+
|
88 |
+
for doc_type, count in stats.get('by_type', {}).items():
|
89 |
+
type_name = {
|
90 |
+
'law': 'قوانین',
|
91 |
+
'news': 'اخبار',
|
92 |
+
'ruling': 'آرا',
|
93 |
+
'regulation': 'آییننامه',
|
94 |
+
'general': 'عمومی'
|
95 |
+
}.get(doc_type, doc_type)
|
96 |
+
stats_lines.append(f"- {type_name}: {count}")
|
97 |
+
|
98 |
+
stats_text = "\n".join(stats_lines)
|
99 |
+
|
100 |
+
viz_html = self._create_stats_visualization(stats)
|
101 |
+
|
102 |
+
return stats_text, viz_html
|
103 |
+
|
104 |
+
except Exception as e:
|
105 |
+
error_msg = f"خطا در دریافت آمار: {str(e)}"
|
106 |
+
return error_msg, ""
|
107 |
+
|
108 |
+
def _create_stats_visualization(self, stats: Dict) -> str:
|
109 |
+
"""Create visualization for statistics"""
|
110 |
+
try:
|
111 |
+
by_type = stats.get('by_type', {})
|
112 |
+
if by_type and stats.get('total_documents', 0) > 0:
|
113 |
+
type_names = {
|
114 |
+
'law': 'قوانین',
|
115 |
+
'news': 'اخبار',
|
116 |
+
'ruling': 'آرا',
|
117 |
+
'regulation': 'آییننامه',
|
118 |
+
'general': 'عمومی'
|
119 |
+
}
|
120 |
+
|
121 |
+
labels = [type_names.get(k, k) for k in by_type.keys()]
|
122 |
+
values = list(by_type.values())
|
123 |
+
|
124 |
+
fig = px.pie(
|
125 |
+
values=values,
|
126 |
+
names=labels,
|
127 |
+
title="توزیع اسناد بر اساس نوع"
|
128 |
+
)
|
129 |
+
fig.update_traces(textposition='inside', textinfo='percent+label')
|
130 |
+
|
131 |
+
return fig.to_html()
|
132 |
+
else:
|
133 |
+
return "<p>دادهای برای نمایش یافت نشد</p>"
|
134 |
+
|
135 |
+
except Exception as e:
|
136 |
+
return f"<p>خطا در ایجاد نمودار: {str(e)}</p>"
|
137 |
+
|
138 |
+
def search_documents(self, query: str, search_type: str) -> str:
|
139 |
+
"""Search in collected documents"""
|
140 |
+
if not query.strip():
|
141 |
+
return "لطفاً کلیدواژهای برای جستجو وارد کنید"
|
142 |
+
|
143 |
+
try:
|
144 |
+
if search_type == "هوشمند":
|
145 |
+
results = self.scraper.search_with_similarity(query, limit=10)
|
146 |
+
else:
|
147 |
+
results = self.scraper._text_search(query, limit=10)
|
148 |
+
|
149 |
+
if not results:
|
150 |
+
return f"هیچ سندی با کلیدواژه '{query}' یافت نشد"
|
151 |
+
|
152 |
+
result_lines = [f"🔍 **نتایج جستجو برای '{query}':** ({len(results)} مورد یافت شد)\n"]
|
153 |
+
|
154 |
+
for i, result in enumerate(results):
|
155 |
+
result_lines.extend([
|
156 |
+
f"**{i+1}. {result['title']}**",
|
157 |
+
f" نوع: {result['document_type']}",
|
158 |
+
f" منبع: {result['source_url']}",
|
159 |
+
f" امتیاز شباهت: {result.get('similarity_score', 0):.3f}" if 'similarity_score' in result else "",
|
160 |
+
f" تاریخ: {result['date_published'] or 'نامشخص'}",
|
161 |
+
f" خلاصه: {result['summary'][:100]}..." if result.get('summary') else "",
|
162 |
+
"---"
|
163 |
+
])
|
164 |
+
|
165 |
+
return "\n".join(result_lines)
|
166 |
+
|
167 |
+
except Exception as e:
|
168 |
+
error_msg = f"خطا در جستجو: {str(e)}"
|
169 |
+
return error_msg
|
170 |
+
|
171 |
+
def create_scraper_interface():
|
172 |
+
"""Create Gradio interface for legal scraper"""
|
173 |
+
|
174 |
+
scraper_interface = LegalScraperInterface()
|
175 |
+
|
176 |
+
css = """
|
177 |
+
.gradio-container {
|
178 |
+
max-width: 1200px !important;
|
179 |
+
margin: auto;
|
180 |
+
font-family: 'Tahoma', sans-serif;
|
181 |
+
}
|
182 |
+
.header {
|
183 |
+
background: linear-gradient(135deg, #2c3e50, #3498db);
|
184 |
+
color: white;
|
185 |
+
padding: 20px;
|
186 |
+
border-radius: 10px;
|
187 |
+
text-align: center;
|
188 |
+
margin-bottom: 20px;
|
189 |
+
}
|
190 |
+
"""
|
191 |
+
|
192 |
+
with gr.Blocks(css=css, title="اسکراپر پیشرفته اسناد حقوقی", theme=gr.themes.Soft()) as interface:
|
193 |
+
|
194 |
+
gr.HTML("""
|
195 |
+
<div class="header">
|
196 |
+
<h1>🤖 اسکراپر پیشرفته اسناد حقوقی</h1>
|
197 |
+
<p>سیستم هوشمند جمعآوری و تحلیل اسناد حقوقی با قابلیتهای NLP</p>
|
198 |
+
</div>
|
199 |
+
""")
|
200 |
+
|
201 |
+
with gr.Tab("🕷️ اسکراپینگ"):
|
202 |
+
gr.Markdown("## جمعآوری اسناد از منابع حقوقی")
|
203 |
+
|
204 |
+
with gr.Row():
|
205 |
+
with gr.Column(scale=2):
|
206 |
+
urls_input = gr.Textbox(
|
207 |
+
label="📝 URL های منابع حقوقی",
|
208 |
+
placeholder="هر URL را در یک خط وارد کنید:\nhttps://rc.majlis.ir\nhttps://dolat.ir",
|
209 |
+
lines=5,
|
210 |
+
value="\n".join([
|
211 |
+
"https://rc.majlis.ir",
|
212 |
+
"https://dolat.ir",
|
213 |
+
"https://iribnews.ir"
|
214 |
+
])
|
215 |
+
)
|
216 |
+
|
217 |
+
max_docs = gr.Slider(
|
218 |
+
label="حداکثر اسناد",
|
219 |
+
minimum=5,
|
220 |
+
maximum=50,
|
221 |
+
value=15,
|
222 |
+
step=5
|
223 |
+
)
|
224 |
+
|
225 |
+
scrape_btn = gr.Button("🚀 شروع اسکراپینگ", variant="primary")
|
226 |
+
|
227 |
+
with gr.Column(scale=1):
|
228 |
+
status_output = gr.Textbox(
|
229 |
+
label="⚡ وضعیت",
|
230 |
+
interactive=False,
|
231 |
+
lines=2
|
232 |
+
)
|
233 |
+
|
234 |
+
with gr.Row():
|
235 |
+
summary_output = gr.Textbox(
|
236 |
+
label="📊 خلاصه نتایج",
|
237 |
+
interactive=False,
|
238 |
+
lines=6
|
239 |
+
)
|
240 |
+
|
241 |
+
preview_output = gr.Textbox(
|
242 |
+
label="👁️ پیشنمایش اسناد",
|
243 |
+
interactive=False,
|
244 |
+
lines=6,
|
245 |
+
show_copy_button=True
|
246 |
+
)
|
247 |
+
|
248 |
+
scrape_btn.click(
|
249 |
+
fn=scraper_interface.scrape_websites,
|
250 |
+
inputs=[urls_input, max_docs],
|
251 |
+
outputs=[status_output, summary_output, preview_output]
|
252 |
+
)
|
253 |
+
|
254 |
+
with gr.Tab("🔍 جستجوی هوشمند"):
|
255 |
+
gr.Markdown("## جستجوی پیشرفته در اسناد")
|
256 |
+
|
257 |
+
with gr.Row():
|
258 |
+
search_input = gr.Textbox(
|
259 |
+
label="🔍 کلیدواژه جستجو",
|
260 |
+
placeholder="موضوع یا کلیدواژه مورد نظر را وارد کنید..."
|
261 |
+
)
|
262 |
+
|
263 |
+
search_type = gr.Dropdown(
|
264 |
+
label="نوع جستجو",
|
265 |
+
choices=["هوشمند", "متنی"],
|
266 |
+
value="هوشمند"
|
267 |
+
)
|
268 |
+
|
269 |
+
search_btn = gr.Button("🔍 جستجو", variant="primary")
|
270 |
+
|
271 |
+
search_results = gr.Textbox(
|
272 |
+
label="📋 نتایج جستجو",
|
273 |
+
interactive=False,
|
274 |
+
lines=15,
|
275 |
+
show_copy_button=True
|
276 |
+
)
|
277 |
+
|
278 |
+
search_btn.click(
|
279 |
+
fn=scraper_interface.search_documents,
|
280 |
+
inputs=[search_input, search_type],
|
281 |
+
outputs=[search_results]
|
282 |
+
)
|
283 |
+
|
284 |
+
with gr.Tab("📊 آمار و تحلیل"):
|
285 |
+
gr.Markdown("## آمار پیشرفته پایگاه داده")
|
286 |
+
|
287 |
+
stats_btn = gr.Button("📊 بروزرسانی آمار", variant="secondary")
|
288 |
+
|
289 |
+
with gr.Row():
|
290 |
+
stats_text = gr.Textbox(
|
291 |
+
label="📈 آمار متنی",
|
292 |
+
interactive=False,
|
293 |
+
lines=10
|
294 |
+
)
|
295 |
+
|
296 |
+
stats_plot = gr.HTML(
|
297 |
+
label="📊 نمودارها"
|
298 |
+
)
|
299 |
+
|
300 |
+
stats_btn.click(
|
301 |
+
fn=scraper_interface.get_database_stats,
|
302 |
+
outputs=[stats_text, stats_plot]
|
303 |
+
)
|
304 |
+
|
305 |
+
with gr.Tab("📚 راهنما"):
|
306 |
+
gr.Markdown("""
|
307 |
+
# 🤖 راهنمای اسکراپر پیشرفته
|
308 |
+
|
309 |
+
## ویژگیهای پیشرفته
|
310 |
+
|
311 |
+
### 🧠 پردازش زبان طبیعی (NLP)
|
312 |
+
- استخراج خودکار کلمات کلیدی
|
313 |
+
- تولید خلاصه متن
|
314 |
+
- تحلیل احساسات
|
315 |
+
- شناسایی موجودیتهای حقوقی
|
316 |
+
- جستجوی هوشمند بر اساس شباهت معنایی
|
317 |
+
|
318 |
+
### 📊 تحلیل پیشرفته
|
319 |
+
- امتیازدهی اهمیت اسناد
|
320 |
+
- طبقهبندی خودکار
|
321 |
+
- آمار و نمودارهای تحلیلی
|
322 |
+
- گزارشهای آماری
|
323 |
+
|
324 |
+
## منابع پیشنهادی
|
325 |
+
|
326 |
+
- **مجلس شورای اسلامی**: https://rc.majlis.ir
|
327 |
+
- **دولت**: https://dolat.ir
|
328 |
+
- **خبرگزاریها**: IRIB, IRNA, Tasnim, Mehr, Fars
|
329 |
+
|
330 |
+
## نکات فنی
|
331 |
+
|
332 |
+
- سیستم از فایل robots.txt پیروی میکند
|
333 |
+
- محدودیت سرعت درخواست رعایت میشود
|
334 |
+
- دادهها در پایگاه داده SQLite ذخیره میشوند
|
335 |
+
- از مدلهای هوش مصنوعی برای پردازش استفاده میشود
|
336 |
+
|
337 |
+
⚠️ **تذکر**: این ابزار برای مقاصد آموزشی و پژوهشی ارائه شده است.
|
338 |
+
""")
|
339 |
+
|
340 |
+
return interface
|
341 |
+
|
342 |
+
def main():
|
343 |
+
"""Main entry point for Hugging Face Spaces"""
|
344 |
+
print("🚀 راه اندازی اسکراپر پیشرفته اسناد حقوقی...")
|
345 |
+
print("📁 ایجاد دایرکتوریهای مورد نیاز...")
|
346 |
+
|
347 |
+
# Create required directories
|
348 |
+
os.makedirs("/app/data", exist_ok=True)
|
349 |
+
os.makedirs("/app/logs", exist_ok=True)
|
350 |
+
os.makedirs("/app/cache", exist_ok=True)
|
351 |
+
|
352 |
+
# Create interface
|
353 |
+
interface = create_scraper_interface()
|
354 |
+
|
355 |
+
# Launch with Hugging Face optimized settings
|
356 |
+
interface.launch(
|
357 |
+
server_name="0.0.0.0",
|
358 |
+
server_port=7860,
|
359 |
+
share=False,
|
360 |
+
show_error=True,
|
361 |
+
debug=False,
|
362 |
+
enable_queue=True
|
363 |
+
)
|
364 |
+
|
365 |
+
if __name__ == "__main__":
|
366 |
+
main()
|
app/legal_scraper_interface.py
ADDED
@@ -0,0 +1,1190 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import requests
|
2 |
+
import time
|
3 |
+
import json
|
4 |
+
import csv
|
5 |
+
import sqlite3
|
6 |
+
import logging
|
7 |
+
from datetime import datetime, timedelta
|
8 |
+
from typing import Dict, List, Optional, Tuple, Union
|
9 |
+
from dataclasses import dataclass, asdict
|
10 |
+
from pathlib import Path
|
11 |
+
import re
|
12 |
+
import pandas as pd
|
13 |
+
import numpy as np
|
14 |
+
from sklearn.feature_extraction.text import TfidfVectorizer
|
15 |
+
from sklearn.metrics.pairwise import cosine_similarity
|
16 |
+
from bs4 import BeautifulSoup
|
17 |
+
|
18 |
+
try:
|
19 |
+
import torch
|
20 |
+
from transformers import AutoTokenizer, AutoModel
|
21 |
+
TORCH_AVAILABLE = True
|
22 |
+
except ImportError:
|
23 |
+
TORCH_AVAILABLE = False
|
24 |
+
print("⚠️ PyTorch not available, running without advanced NLP features")
|
25 |
+
|
26 |
+
try:
|
27 |
+
import hazm
|
28 |
+
from hazm import Normalizer, word_tokenize, sent_tokenize
|
29 |
+
HAZM_AVAILABLE = True
|
30 |
+
except ImportError:
|
31 |
+
HAZM_AVAILABLE = False
|
32 |
+
print("⚠️ Hazm not available, using basic text processing")
|
33 |
+
|
34 |
+
# Configure logging
|
35 |
+
logging.basicConfig(
|
36 |
+
level=logging.INFO,
|
37 |
+
format='%(asctime)s - %(levelname)s - %(message)s',
|
38 |
+
handlers=[
|
39 |
+
logging.FileHandler('legal_scraper.log'),
|
40 |
+
logging.StreamHandler()
|
41 |
+
]
|
42 |
+
)
|
43 |
+
logger = logging.getLogger(__name__)
|
44 |
+
|
45 |
+
# Predefined Iranian legal and news sources
|
46 |
+
IRANIAN_LEGAL_SOURCES = [
|
47 |
+
"https://www.irna.ir", # خبرگزاری جمهوری اسلامی
|
48 |
+
"https://www.tasnimnews.com", # خبرگزاری تسنیم
|
49 |
+
"https://www.mehrnews.com", # خبرگزاری مهر
|
50 |
+
"https://www.farsnews.ir", # خبرگزاری فارس
|
51 |
+
"https://iribnews.ir", # خبرگزاری صدا و سیما
|
52 |
+
"https://www.dolat.ir", # پورتال دولت
|
53 |
+
"https://rc.majlis.ir", # مرکز پژوهشهای مجلس
|
54 |
+
]
|
55 |
+
|
56 |
+
@dataclass
|
57 |
+
class LegalDocument:
|
58 |
+
"""Enhanced legal document with NLP features"""
|
59 |
+
title: str
|
60 |
+
content: str
|
61 |
+
source_url: str
|
62 |
+
document_type: str
|
63 |
+
date_published: Optional[str] = None
|
64 |
+
date_scraped: str = None
|
65 |
+
category: Optional[str] = None
|
66 |
+
tags: List[str] = None
|
67 |
+
summary: Optional[str] = None
|
68 |
+
importance_score: float = 0.0
|
69 |
+
sentiment_score: float = 0.0
|
70 |
+
legal_entities: List[str] = None
|
71 |
+
keywords: List[str] = None
|
72 |
+
embedding: List[float] = None
|
73 |
+
language: str = "fa"
|
74 |
+
|
75 |
+
def __post_init__(self):
|
76 |
+
if self.date_scraped is None:
|
77 |
+
self.date_scraped = datetime.now().isoformat()
|
78 |
+
if self.tags is None:
|
79 |
+
self.tags = []
|
80 |
+
if self.legal_entities is None:
|
81 |
+
self.legal_entities = []
|
82 |
+
if self.keywords is None:
|
83 |
+
self.keywords = []
|
84 |
+
|
85 |
+
class PersianNLPProcessor:
|
86 |
+
"""Persian NLP processor using available models"""
|
87 |
+
|
88 |
+
def __init__(self):
|
89 |
+
if HAZM_AVAILABLE:
|
90 |
+
self.normalizer = Normalizer()
|
91 |
+
else:
|
92 |
+
self.normalizer = None
|
93 |
+
|
94 |
+
self.device = torch.device('cpu')
|
95 |
+
|
96 |
+
self.tokenizer = None
|
97 |
+
self.model = None
|
98 |
+
|
99 |
+
if TORCH_AVAILABLE:
|
100 |
+
try:
|
101 |
+
model_names = [
|
102 |
+
"HooshvareLab/bert-fa-base-uncased",
|
103 |
+
"HooshvareLab/bert-base-parsbert-uncased",
|
104 |
+
"distilbert-base-multilingual-cased"
|
105 |
+
]
|
106 |
+
|
107 |
+
for model_name in model_names:
|
108 |
+
try:
|
109 |
+
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
|
110 |
+
self.model = AutoModel.from_pretrained(model_name)
|
111 |
+
self.model.to(self.device)
|
112 |
+
logger.info(f"✅ Loaded model: {model_name}")
|
113 |
+
break
|
114 |
+
except Exception as e:
|
115 |
+
logger.warning(f"⚠️ Failed to load {model_name}: {e}")
|
116 |
+
continue
|
117 |
+
except Exception as e:
|
118 |
+
logger.error(f"❌ Failed to load any Persian BERT model: {e}")
|
119 |
+
|
120 |
+
self.legal_categories = {
|
121 |
+
'قانون': ['قانون', 'ماده', 'بند', 'فصل', 'تبصره', 'اصلاحیه'],
|
122 |
+
'رای': ['رای', 'حکم', 'دادگاه', 'قاضی', 'محکوم', 'دادرسی'],
|
123 |
+
'آییننامه': ['آییننامه', 'دستورالعمل', 'بخشنامه', 'مقررات'],
|
124 |
+
'اخبار': ['خبر', 'گزارش', 'اعلام', 'اطلاعیه', 'بیانیه'],
|
125 |
+
'نظریه': ['نظریه', 'تفسیر', 'استعلام', 'پاسخ', 'رأی']
|
126 |
+
}
|
127 |
+
|
128 |
+
self.tfidf = None
|
129 |
+
self._init_tfidf()
|
130 |
+
|
131 |
+
def _init_tfidf(self):
|
132 |
+
"""Initialize TF-IDF vectorizer"""
|
133 |
+
try:
|
134 |
+
self.tfidf = TfidfVectorizer(
|
135 |
+
max_features=1000,
|
136 |
+
stop_words=self._get_persian_stopwords(),
|
137 |
+
ngram_range=(1, 2),
|
138 |
+
min_df=1,
|
139 |
+
max_df=0.8
|
140 |
+
)
|
141 |
+
except Exception as e:
|
142 |
+
logger.error(f"TF-IDF initialization failed: {e}")
|
143 |
+
|
144 |
+
def _get_persian_stopwords(self) -> List[str]:
|
145 |
+
"""Get Persian stopwords"""
|
146 |
+
return [
|
147 |
+
'در', 'به', 'از', 'که', 'این', 'آن', 'با', 'را', 'و', 'است',
|
148 |
+
'برای', 'تا', 'کرد', 'شد', 'می', 'خود', 'هم', 'نیز', 'یا', 'اما',
|
149 |
+
'اگر', 'چون', 'پس', 'بعد', 'قبل', 'روی', 'زیر', 'کنار', 'داخل',
|
150 |
+
'نیست', 'بود', 'باشد', 'کند', 'کنند', 'شود', 'گردد', 'دارد', 'دارند'
|
151 |
+
]
|
152 |
+
|
153 |
+
def normalize_text(self, text: str) -> str:
|
154 |
+
"""Normalize Persian text"""
|
155 |
+
if not text:
|
156 |
+
return ""
|
157 |
+
|
158 |
+
try:
|
159 |
+
text = re.sub(r'[^\w\s\u0600-\u06FF]', ' ', text)
|
160 |
+
text = re.sub(r'\s+', ' ', text)
|
161 |
+
|
162 |
+
if self.normalizer:
|
163 |
+
text = self.normalizer.normalize(text)
|
164 |
+
|
165 |
+
return text.strip()
|
166 |
+
except Exception as e:
|
167 |
+
logger.error(f"Text normalization failed: {e}")
|
168 |
+
return text.strip()
|
169 |
+
|
170 |
+
def extract_keywords(self, text: str, top_k: int = 10) -> List[str]:
|
171 |
+
"""Extract keywords using TF-IDF"""
|
172 |
+
try:
|
173 |
+
if not self.tfidf or not text:
|
174 |
+
return []
|
175 |
+
|
176 |
+
normalized_text = self.normalize_text(text)
|
177 |
+
|
178 |
+
if HAZM_AVAILABLE:
|
179 |
+
tokens = word_tokenize(normalized_text)
|
180 |
+
processed_text = ' '.join(tokens)
|
181 |
+
else:
|
182 |
+
processed_text = normalized_text
|
183 |
+
|
184 |
+
tfidf_matrix = self.tfidf.fit_transform([processed_text])
|
185 |
+
feature_names = self.tfidf.get_feature_names_out()
|
186 |
+
scores = tfidf_matrix.toarray()[0]
|
187 |
+
|
188 |
+
keyword_scores = list(zip(feature_names, scores))
|
189 |
+
keyword_scores.sort(key=lambda x: x[1], reverse=True)
|
190 |
+
|
191 |
+
return [kw[0] for kw in keyword_scores[:top_k] if kw[1] > 0]
|
192 |
+
|
193 |
+
except Exception as e:
|
194 |
+
logger.error(f"Keyword extraction failed: {e}")
|
195 |
+
return []
|
196 |
+
|
197 |
+
def classify_document(self, text: str) -> Tuple[str, float]:
|
198 |
+
"""Classify document type with confidence score"""
|
199 |
+
try:
|
200 |
+
normalized_text = self.normalize_text(text.lower())
|
201 |
+
|
202 |
+
scores = {}
|
203 |
+
for category, keywords in self.legal_categories.items():
|
204 |
+
score = 0
|
205 |
+
for keyword in keywords:
|
206 |
+
count = normalized_text.count(keyword)
|
207 |
+
score += count * (len(keyword) / 5)
|
208 |
+
|
209 |
+
if len(normalized_text) > 0:
|
210 |
+
scores[category] = score / (len(normalized_text) / 1000)
|
211 |
+
else:
|
212 |
+
scores[category] = 0
|
213 |
+
|
214 |
+
if not scores or max(scores.values()) == 0:
|
215 |
+
return "عمومی", 0.0
|
216 |
+
|
217 |
+
best_category = max(scores.items(), key=lambda x: x[1])
|
218 |
+
total_score = sum(scores.values())
|
219 |
+
confidence = min(best_category[1] / total_score, 1.0) if total_score > 0 else 0.0
|
220 |
+
|
221 |
+
return best_category[0], confidence
|
222 |
+
|
223 |
+
except Exception as e:
|
224 |
+
logger.error(f"Document classification failed: {e}")
|
225 |
+
return "عمومی", 0.0
|
226 |
+
|
227 |
+
def calculate_importance_score(self, doc: LegalDocument) -> float:
|
228 |
+
"""Calculate document importance score"""
|
229 |
+
try:
|
230 |
+
score = 0.0
|
231 |
+
|
232 |
+
title_lower = doc.title.lower()
|
233 |
+
high_importance_words = ['قانون', 'اساسی', 'حکم', 'رای', 'مصوبه']
|
234 |
+
medium_importance_words = ['آییننامه', 'بخشنامه', 'دستورالعمل']
|
235 |
+
|
236 |
+
for word in high_importance_words:
|
237 |
+
if word in title_lower:
|
238 |
+
score += 0.3
|
239 |
+
break
|
240 |
+
|
241 |
+
for word in medium_importance_words:
|
242 |
+
if word in title_lower:
|
243 |
+
score += 0.2
|
244 |
+
break
|
245 |
+
|
246 |
+
content_length = len(doc.content)
|
247 |
+
if content_length > 5000:
|
248 |
+
score += 0.25
|
249 |
+
elif content_length > 2000:
|
250 |
+
score += 0.15
|
251 |
+
elif content_length > 500:
|
252 |
+
score += 0.1
|
253 |
+
|
254 |
+
if doc.date_published:
|
255 |
+
try:
|
256 |
+
date_formats = ['%Y-%m-%d', '%Y/%m/%d', '%d/%m/%Y']
|
257 |
+
pub_date = None
|
258 |
+
|
259 |
+
for fmt in date_formats:
|
260 |
+
try:
|
261 |
+
pub_date = datetime.strptime(doc.date_published, fmt)
|
262 |
+
break
|
263 |
+
except:
|
264 |
+
continue
|
265 |
+
|
266 |
+
if pub_date:
|
267 |
+
days_old = (datetime.now() - pub_date).days
|
268 |
+
if days_old < 30:
|
269 |
+
score += 0.25
|
270 |
+
elif days_old < 365:
|
271 |
+
score += 0.15
|
272 |
+
elif days_old < 1825:
|
273 |
+
score += 0.05
|
274 |
+
except:
|
275 |
+
pass
|
276 |
+
|
277 |
+
legal_keywords = ['قانون', 'ماده', 'بند', 'حکم', 'رای', 'دادگاه', 'محکمه']
|
278 |
+
content_lower = doc.content.lower()
|
279 |
+
keyword_count = sum(content_lower.count(kw) for kw in legal_keywords)
|
280 |
+
word_count = len(doc.content.split())
|
281 |
+
|
282 |
+
if word_count > 0:
|
283 |
+
keyword_density = keyword_count / word_count
|
284 |
+
score += min(keyword_density * 5, 0.2)
|
285 |
+
|
286 |
+
type_bonuses = {
|
287 |
+
'law': 0.2,
|
288 |
+
'ruling': 0.15,
|
289 |
+
'regulation': 0.1,
|
290 |
+
'news': 0.05
|
291 |
+
}
|
292 |
+
score += type_bonuses.get(doc.document_type, 0)
|
293 |
+
|
294 |
+
return min(score, 1.0)
|
295 |
+
|
296 |
+
except Exception as e:
|
297 |
+
logger.error(f"Importance score calculation failed: {e}")
|
298 |
+
return 0.0
|
299 |
+
|
300 |
+
def extract_legal_entities(self, text: str) -> List[str]:
|
301 |
+
"""Extract legal entities from text"""
|
302 |
+
try:
|
303 |
+
entities = []
|
304 |
+
|
305 |
+
patterns = {
|
306 |
+
'قوانین': r'قانون\s+[\u0600-\u06FF\s]{3,30}',
|
307 |
+
'مواد': r'ماده\s+\d+[\u0600-\u06FF\s]*',
|
308 |
+
'دادگاهها': r'دادگاه\s+[\u0600-\u06FF\s]{3,30}',
|
309 |
+
'مراجع': r'(وزارت|سازمان|اداره|شورای|کمیته)\s+[\u0600-\u06FF\s]{3,30}',
|
310 |
+
'احکام': r'(حکم|رای)\s+(شماره\s+)?\d+',
|
311 |
+
}
|
312 |
+
|
313 |
+
for entity_type, pattern in patterns.items():
|
314 |
+
matches = re.findall(pattern, text)
|
315 |
+
for match in matches:
|
316 |
+
clean_match = re.sub(r'\s+', ' ', match.strip())
|
317 |
+
if len(clean_match) > 5 and len(clean_match) < 100:
|
318 |
+
entities.append(clean_match)
|
319 |
+
|
320 |
+
unique_entities = list(dict.fromkeys(entities))
|
321 |
+
return unique_entities[:15]
|
322 |
+
|
323 |
+
except Exception as e:
|
324 |
+
logger.error(f"Entity extraction failed: {e}")
|
325 |
+
return []
|
326 |
+
|
327 |
+
def get_text_embedding(self, text: str) -> Optional[List[float]]:
|
328 |
+
"""Get text embedding using available model"""
|
329 |
+
if not self.model or not self.tokenizer or not TORCH_AVAILABLE:
|
330 |
+
return None
|
331 |
+
|
332 |
+
try:
|
333 |
+
normalized_text = self.normalize_text(text)
|
334 |
+
if len(normalized_text) > 512:
|
335 |
+
normalized_text = normalized_text[:512]
|
336 |
+
|
337 |
+
if not normalized_text:
|
338 |
+
return None
|
339 |
+
|
340 |
+
inputs = self.tokenizer(
|
341 |
+
normalized_text,
|
342 |
+
return_tensors="pt",
|
343 |
+
padding=True,
|
344 |
+
truncation=True,
|
345 |
+
max_length=512
|
346 |
+
).to(self.device)
|
347 |
+
|
348 |
+
with torch.no_grad():
|
349 |
+
outputs = self.model(**inputs)
|
350 |
+
embedding = outputs.last_hidden_state[:, 0, :].cpu().numpy()[0]
|
351 |
+
|
352 |
+
return embedding.tolist()
|
353 |
+
|
354 |
+
except Exception as e:
|
355 |
+
logger.error(f"Embedding generation failed: {e}")
|
356 |
+
return None
|
357 |
+
|
358 |
+
def generate_summary(self, text: str, max_length: int = 200) -> str:
|
359 |
+
"""Generate text summary"""
|
360 |
+
try:
|
361 |
+
if len(text) <= max_length:
|
362 |
+
return text
|
363 |
+
|
364 |
+
if HAZM_AVAILABLE:
|
365 |
+
sentences = sent_tokenize(text)
|
366 |
+
else:
|
367 |
+
sentences = re.split(r'[.!?]+', text)
|
368 |
+
sentences = [s.strip() for s in sentences if s.strip()]
|
369 |
+
|
370 |
+
if len(sentences) <= 2:
|
371 |
+
return text[:max_length] + "..." if len(text) > max_length else text
|
372 |
+
|
373 |
+
keywords = self.extract_keywords(text, top_k=15)
|
374 |
+
|
375 |
+
sentence_scores = []
|
376 |
+
for sentence in sentences:
|
377 |
+
if len(sentence) < 20:
|
378 |
+
continue
|
379 |
+
|
380 |
+
score = 0
|
381 |
+
sentence_lower = sentence.lower()
|
382 |
+
|
383 |
+
for kw in keywords:
|
384 |
+
if kw in sentence_lower:
|
385 |
+
score += 1
|
386 |
+
|
387 |
+
legal_terms = ['قانون', 'ماده', 'حکم', 'رای', 'دادگاه']
|
388 |
+
for term in legal_terms:
|
389 |
+
if term in sentence_lower:
|
390 |
+
score += 0.5
|
391 |
+
|
392 |
+
if len(sentence) > 200:
|
393 |
+
score *= 0.8
|
394 |
+
|
395 |
+
sentence_scores.append((sentence, score))
|
396 |
+
|
397 |
+
sentence_scores.sort(key=lambda x: x[1], reverse=True)
|
398 |
+
|
399 |
+
selected_sentences = []
|
400 |
+
current_length = 0
|
401 |
+
|
402 |
+
for sentence, score in sentence_scores:
|
403 |
+
if current_length + len(sentence) <= max_length:
|
404 |
+
selected_sentences.append(sentence)
|
405 |
+
current_length += len(sentence)
|
406 |
+
else:
|
407 |
+
break
|
408 |
+
|
409 |
+
if not selected_sentences:
|
410 |
+
return text[:max_length] + "..."
|
411 |
+
|
412 |
+
summary = ' '.join(selected_sentences)
|
413 |
+
return summary if len(summary) <= max_length else summary[:max_length] + "..."
|
414 |
+
|
415 |
+
except Exception as e:
|
416 |
+
logger.error(f"Summary generation failed: {e}")
|
417 |
+
return text[:max_length] + "..." if len(text) > max_length else text
|
418 |
+
|
419 |
+
def process_document(self, doc: LegalDocument) -> LegalDocument:
|
420 |
+
"""Process document with all available NLP features"""
|
421 |
+
try:
|
422 |
+
logger.info(f"Processing document: {doc.title[:50]}...")
|
423 |
+
|
424 |
+
doc.keywords = self.extract_keywords(doc.content)
|
425 |
+
|
426 |
+
doc_type, confidence = self.classify_document(doc.content)
|
427 |
+
if confidence > 0.3:
|
428 |
+
doc.category = doc_type
|
429 |
+
|
430 |
+
doc.importance_score = self.calculate_importance_score(doc)
|
431 |
+
|
432 |
+
doc.legal_entities = self.extract_legal_entities(doc.content)
|
433 |
+
|
434 |
+
doc.summary = self.generate_summary(doc.content)
|
435 |
+
|
436 |
+
doc.embedding = self.get_text_embedding(doc.content)
|
437 |
+
|
438 |
+
logger.info(f"✅ Processed: {doc.title[:30]}... (Score: {doc.importance_score:.2f})")
|
439 |
+
|
440 |
+
return doc
|
441 |
+
|
442 |
+
except Exception as e:
|
443 |
+
logger.error(f"Document processing failed: {e}")
|
444 |
+
return doc
|
445 |
+
|
446 |
+
class EnhancedLegalScraper:
|
447 |
+
"""Enhanced legal scraper with real web scraping and NLP"""
|
448 |
+
|
449 |
+
def __init__(self, delay: float = 1.0):
|
450 |
+
self.delay = delay
|
451 |
+
self.session = requests.Session()
|
452 |
+
|
453 |
+
try:
|
454 |
+
self.nlp_processor = PersianNLPProcessor()
|
455 |
+
logger.info("✅ NLP processor initialized")
|
456 |
+
except Exception as e:
|
457 |
+
logger.error(f"❌ NLP processor initialization failed: {e}")
|
458 |
+
self.nlp_processor = None
|
459 |
+
|
460 |
+
self.db_path = self._get_db_path()
|
461 |
+
|
462 |
+
self.session.headers.update({
|
463 |
+
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
464 |
+
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
465 |
+
'Accept-Language': 'fa,en-US;q=0.7,en;q=0.3',
|
466 |
+
'Accept-Encoding': 'gzip, deflate',
|
467 |
+
'Connection': 'keep-alive',
|
468 |
+
'Upgrade-Insecure-Requests': '1',
|
469 |
+
})
|
470 |
+
|
471 |
+
self._init_database()
|
472 |
+
|
473 |
+
def _get_db_path(self) -> str:
|
474 |
+
"""Get appropriate database path for the environment"""
|
475 |
+
possible_paths = [
|
476 |
+
"/tmp/legal_scraper.db",
|
477 |
+
"./data/legal_scraper.db",
|
478 |
+
"legal_scraper.db"
|
479 |
+
]
|
480 |
+
|
481 |
+
for path in possible_paths:
|
482 |
+
try:
|
483 |
+
Path(path).parent.mkdir(parents=True, exist_ok=True)
|
484 |
+
return path
|
485 |
+
except:
|
486 |
+
continue
|
487 |
+
|
488 |
+
return ":memory:"
|
489 |
+
|
490 |
+
def _init_database(self):
|
491 |
+
"""Initialize enhanced database with NLP fields"""
|
492 |
+
try:
|
493 |
+
conn = sqlite3.connect(self.db_path)
|
494 |
+
cursor = conn.cursor()
|
495 |
+
|
496 |
+
cursor.execute('''
|
497 |
+
CREATE TABLE IF NOT EXISTS legal_documents (
|
498 |
+
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
499 |
+
title TEXT NOT NULL,
|
500 |
+
content TEXT NOT NULL,
|
501 |
+
source_url TEXT UNIQUE NOT NULL,
|
502 |
+
document_type TEXT NOT NULL,
|
503 |
+
date_published TEXT,
|
504 |
+
date_scraped TEXT NOT NULL,
|
505 |
+
category TEXT,
|
506 |
+
tags TEXT,
|
507 |
+
summary TEXT,
|
508 |
+
importance_score REAL DEFAULT 0.0,
|
509 |
+
sentiment_score REAL DEFAULT 0.0,
|
510 |
+
legal_entities TEXT,
|
511 |
+
keywords TEXT,
|
512 |
+
embedding TEXT,
|
513 |
+
language TEXT DEFAULT 'fa',
|
514 |
+
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
|
515 |
+
)
|
516 |
+
''')
|
517 |
+
|
518 |
+
indexes = [
|
519 |
+
'CREATE INDEX IF NOT EXISTS idx_source_url ON legal_documents(source_url)',
|
520 |
+
'CREATE INDEX IF NOT EXISTS idx_document_type ON legal_documents(document_type)',
|
521 |
+
'CREATE INDEX IF NOT EXISTS idx_importance_score ON legal_documents(importance_score DESC)',
|
522 |
+
'CREATE INDEX IF NOT EXISTS idx_category ON legal_documents(category)',
|
523 |
+
'CREATE INDEX IF NOT EXISTS idx_date_published ON legal_documents(date_published)',
|
524 |
+
'CREATE INDEX IF NOT EXISTS idx_date_scraped ON legal_documents(date_scraped DESC)'
|
525 |
+
]
|
526 |
+
|
527 |
+
for index in indexes:
|
528 |
+
cursor.execute(index)
|
529 |
+
|
530 |
+
conn.commit()
|
531 |
+
conn.close()
|
532 |
+
logger.info(f"✅ Database initialized: {self.db_path}")
|
533 |
+
|
534 |
+
except Exception as e:
|
535 |
+
logger.error(f"❌ Database initialization failed: {e}")
|
536 |
+
raise
|
537 |
+
|
538 |
+
def save_document(self, doc: LegalDocument) -> bool:
|
539 |
+
"""Save enhanced document to database"""
|
540 |
+
try:
|
541 |
+
conn = sqlite3.connect(self.db_path)
|
542 |
+
cursor = conn.cursor()
|
543 |
+
|
544 |
+
cursor.execute('''
|
545 |
+
INSERT OR REPLACE INTO legal_documents
|
546 |
+
(title, content, source_url, document_type, date_published,
|
547 |
+
date_scraped, category, tags, summary, importance_score,
|
548 |
+
sentiment_score, legal_entities, keywords, embedding, language)
|
549 |
+
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
|
550 |
+
''', (
|
551 |
+
doc.title,
|
552 |
+
doc.content,
|
553 |
+
doc.source_url,
|
554 |
+
doc.document_type,
|
555 |
+
doc.date_published,
|
556 |
+
doc.date_scraped,
|
557 |
+
doc.category,
|
558 |
+
json.dumps(doc.tags, ensure_ascii=False) if doc.tags else None,
|
559 |
+
doc.summary,
|
560 |
+
doc.importance_score,
|
561 |
+
doc.sentiment_score,
|
562 |
+
json.dumps(doc.legal_entities, ensure_ascii=False) if doc.legal_entities else None,
|
563 |
+
json.dumps(doc.keywords, ensure_ascii=False) if doc.keywords else None,
|
564 |
+
json.dumps(doc.embedding) if doc.embedding else None,
|
565 |
+
doc.language
|
566 |
+
))
|
567 |
+
|
568 |
+
conn.commit()
|
569 |
+
conn.close()
|
570 |
+
return True
|
571 |
+
|
572 |
+
except Exception as e:
|
573 |
+
logger.error(f"Failed to save document {doc.source_url}: {e}")
|
574 |
+
return False
|
575 |
+
|
576 |
+
def get_enhanced_statistics(self) -> Dict:
|
577 |
+
"""Get comprehensive statistics with NLP insights"""
|
578 |
+
try:
|
579 |
+
conn = sqlite3.connect(self.db_path)
|
580 |
+
cursor = conn.cursor()
|
581 |
+
|
582 |
+
stats = {}
|
583 |
+
|
584 |
+
cursor.execute('SELECT COUNT(*) FROM legal_documents')
|
585 |
+
stats['total_documents'] = cursor.fetchone()[0]
|
586 |
+
|
587 |
+
cursor.execute('SELECT document_type, COUNT(*) FROM legal_documents GROUP BY document_type')
|
588 |
+
stats['by_type'] = dict(cursor.fetchall())
|
589 |
+
|
590 |
+
cursor.execute('SELECT category, COUNT(*) FROM legal_documents WHERE category IS NOT NULL GROUP BY category')
|
591 |
+
stats['by_category'] = dict(cursor.fetchall())
|
592 |
+
|
593 |
+
cursor.execute('SELECT COUNT(*) FROM legal_documents WHERE importance_score >= 0.7')
|
594 |
+
high_importance = cursor.fetchone()[0]
|
595 |
+
cursor.execute('SELECT COUNT(*) FROM legal_documents WHERE importance_score >= 0.3 AND importance_score < 0.7')
|
596 |
+
medium_importance = cursor.fetchone()[0]
|
597 |
+
cursor.execute('SELECT COUNT(*) FROM legal_documents WHERE importance_score < 0.3')
|
598 |
+
low_importance = cursor.fetchone()[0]
|
599 |
+
|
600 |
+
stats['importance_distribution'] = {
|
601 |
+
'high': high_importance,
|
602 |
+
'medium': medium_importance,
|
603 |
+
'low': low_importance
|
604 |
+
}
|
605 |
+
|
606 |
+
cursor.execute('SELECT keywords FROM legal_documents WHERE keywords IS NOT NULL')
|
607 |
+
all_keywords = []
|
608 |
+
for row in cursor.fetchall():
|
609 |
+
try:
|
610 |
+
keywords = json.loads(row[0])
|
611 |
+
all_keywords.extend(keywords)
|
612 |
+
except:
|
613 |
+
continue
|
614 |
+
|
615 |
+
if all_keywords:
|
616 |
+
keyword_counts = {}
|
617 |
+
for kw in all_keywords:
|
618 |
+
keyword_counts[kw] = keyword_counts.get(kw, 0) + 1
|
619 |
+
|
620 |
+
topទ
|
621 |
+
top_keywords = sorted(keyword_counts.items(), key=lambda x: x[1], reverse=True)[:25]
|
622 |
+
stats['top_keywords'] = dict(top_keywords)
|
623 |
+
|
624 |
+
cursor.execute('''
|
625 |
+
SELECT DATE(date_scraped) as day, COUNT(*)
|
626 |
+
FROM legal_documents
|
627 |
+
WHERE date_scraped >= date('now', '-7 days')
|
628 |
+
GROUP BY DATE(date_scraped)
|
629 |
+
ORDER BY day DESC
|
630 |
+
''')
|
631 |
+
stats['recent_activity'] = dict(cursor.fetchall())
|
632 |
+
|
633 |
+
cursor.execute('''
|
634 |
+
SELECT document_type, AVG(importance_score)
|
635 |
+
FROM legal_documents
|
636 |
+
GROUP BY document_type
|
637 |
+
''')
|
638 |
+
stats['avg_importance_by_type'] = dict(cursor.fetchall())
|
639 |
+
|
640 |
+
cursor.execute('SELECT COUNT(*) FROM legal_documents WHERE embedding IS NOT NULL')
|
641 |
+
stats['documents_with_embeddings'] = cursor.fetchone()[0]
|
642 |
+
|
643 |
+
cursor.execute('SELECT language, COUNT(*) FROM legal_documents GROUP BY language')
|
644 |
+
stats['by_language'] = dict(cursor.fetchall())
|
645 |
+
|
646 |
+
conn.close()
|
647 |
+
return stats
|
648 |
+
|
649 |
+
except Exception as e:
|
650 |
+
logger.error(f"Statistics generation failed: {e}")
|
651 |
+
return {
|
652 |
+
'total_documents': 0,
|
653 |
+
'by_type': {},
|
654 |
+
'by_category': {},
|
655 |
+
'importance_distribution': {'high': 0, 'medium': 0, 'low': 0},
|
656 |
+
'top_keywords': {},
|
657 |
+
'recent_activity': {},
|
658 |
+
'avg_importance_by_type': {},
|
659 |
+
'documents_with_embeddings': 0,
|
660 |
+
'by_language': {}
|
661 |
+
}
|
662 |
+
|
663 |
+
def search_with_similarity(self, query: str, limit: int = 20) -> List[Dict]:
|
664 |
+
"""Advanced search using embeddings and similarity"""
|
665 |
+
if not self.nlp_processor or not self.nlp_processor.model:
|
666 |
+
return self._text_search(query, limit)
|
667 |
+
|
668 |
+
try:
|
669 |
+
query_embedding = self.nlp_processor.get_text_embedding(query)
|
670 |
+
if not query_embedding:
|
671 |
+
return self._text_search(query, limit)
|
672 |
+
|
673 |
+
conn = sqlite3.connect(self.db_path)
|
674 |
+
cursor = conn.cursor()
|
675 |
+
|
676 |
+
cursor.execute('''
|
677 |
+
SELECT id, title, content, source_url, document_type,
|
678 |
+
importance_score, summary, embedding
|
679 |
+
FROM legal_documents
|
680 |
+
WHERE embedding IS NOT NULL
|
681 |
+
''')
|
682 |
+
|
683 |
+
results = []
|
684 |
+
query_vector = np.array(query_embedding)
|
685 |
+
|
686 |
+
for row in cursor.fetchall():
|
687 |
+
try:
|
688 |
+
doc_embedding = json.loads(row[7])
|
689 |
+
doc_vector = np.array(doc_embedding)
|
690 |
+
|
691 |
+
similarity = cosine_similarity([query_vector], [doc_vector])[0][0]
|
692 |
+
|
693 |
+
combined_score = (similarity * 0.7) + (row[5] * 0.3)
|
694 |
+
|
695 |
+
results.append({
|
696 |
+
'id': row[0],
|
697 |
+
'title': row[1],
|
698 |
+
'content': row[2][:500] + "..." if len(row[2]) > 500 else row[2],
|
699 |
+
'source_url': row[3],
|
700 |
+
'document_type': row[4],
|
701 |
+
'importance_score': row[5],
|
702 |
+
'summary': row[6],
|
703 |
+
'similarity_score': similarity,
|
704 |
+
'combined_score': combined_score
|
705 |
+
})
|
706 |
+
|
707 |
+
except Exception as e:
|
708 |
+
logger.error(f"Error processing document embedding: {e}")
|
709 |
+
continue
|
710 |
+
|
711 |
+
results.sort(key=lambda x: x['combined_score'], reverse=True)
|
712 |
+
conn.close()
|
713 |
+
|
714 |
+
return results[:limit]
|
715 |
+
|
716 |
+
except Exception as e:
|
717 |
+
logger.error(f"Similarity search failed: {e}")
|
718 |
+
return self._text_search(query, limit)
|
719 |
+
|
720 |
+
def _text_search(self, query: str, limit: int = 20) -> List[Dict]:
|
721 |
+
"""Fallback text search"""
|
722 |
+
try:
|
723 |
+
conn = sqlite3.connect(self.db_path)
|
724 |
+
cursor = conn.cursor()
|
725 |
+
|
726 |
+
if self.nlp_processor:
|
727 |
+
normalized_query = self.nlp_processor.normalize_text(query)
|
728 |
+
else:
|
729 |
+
normalized_query = query
|
730 |
+
|
731 |
+
query_words = normalized_query.split()
|
732 |
+
|
733 |
+
search_conditions = []
|
734 |
+
params = []
|
735 |
+
|
736 |
+
for word in query_words:
|
737 |
+
search_conditions.append("(title LIKE ? OR content LIKE ?)")
|
738 |
+
params.extend([f'%{word}%', f'%{word}%'])
|
739 |
+
|
740 |
+
where_clause = " OR ".join(search_conditions)
|
741 |
+
|
742 |
+
cursor.execute(f'''
|
743 |
+
SELECT id, title, content, source_url, document_type,
|
744 |
+
importance_score, summary
|
745 |
+
FROM legal_documents
|
746 |
+
WHERE {where_clause}
|
747 |
+
ORDER BY importance_score DESC
|
748 |
+
LIMIT ?
|
749 |
+
''', params + [limit])
|
750 |
+
|
751 |
+
results = []
|
752 |
+
for row in cursor.fetchall():
|
753 |
+
results.append({
|
754 |
+
'id': row[0],
|
755 |
+
'title': row[1],
|
756 |
+
'content': row[2][:500] + "..." if len(row[2]) > 500 else row[2],
|
757 |
+
'source_url': row[3],
|
758 |
+
'document_type': row[4],
|
759 |
+
'importance_score': row[5],
|
760 |
+
'summary': row[6],
|
761 |
+
'similarity_score': 0.0
|
762 |
+
})
|
763 |
+
|
764 |
+
conn.close()
|
765 |
+
return results
|
766 |
+
|
767 |
+
except Exception as e:
|
768 |
+
logger.error(f"Text search failed: {e}")
|
769 |
+
return []
|
770 |
+
|
771 |
+
def export_to_csv(self, filename: str = None) -> str:
|
772 |
+
"""Export data to CSV with full details"""
|
773 |
+
try:
|
774 |
+
if not filename:
|
775 |
+
timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
|
776 |
+
filename = f"legal_documents_{timestamp}.csv"
|
777 |
+
|
778 |
+
conn = sqlite3.connect(self.db_path)
|
779 |
+
|
780 |
+
query = '''
|
781 |
+
SELECT title, content, source_url, document_type,
|
782 |
+
date_published, date_scraped, category, summary,
|
783 |
+
importance_score, keywords, legal_entities
|
784 |
+
FROM legal_documents
|
785 |
+
ORDER BY importance_score DESC, date_scraped DESC
|
786 |
+
'''
|
787 |
+
|
788 |
+
df = pd.read_sql_query(query, conn)
|
789 |
+
conn.close()
|
790 |
+
|
791 |
+
for col in ['keywords', 'legal_entities']:
|
792 |
+
if col in df.columns:
|
793 |
+
df[col] = df[col].apply(lambda x: ', '.join(json.loads(x)) if x else '')
|
794 |
+
|
795 |
+
df.to_csv(filename, index=False, encoding='utf-8-sig')
|
796 |
+
logger.info(f"✅ Data exported to CSV: {filename}")
|
797 |
+
|
798 |
+
return filename
|
799 |
+
|
800 |
+
except Exception as e:
|
801 |
+
logger.error(f"CSV export failed: {e}")
|
802 |
+
return ""
|
803 |
+
|
804 |
+
def scrape_real_sources(self, urls: List[str] = IRANIAN_LEGAL_SOURCES, max_docs: int = 20) -> List[LegalDocument]:
|
805 |
+
"""Real web scraping implementation with source-specific extraction"""
|
806 |
+
documents = []
|
807 |
+
|
808 |
+
for i, url in enumerate(urls):
|
809 |
+
if len(documents) >= max_docs:
|
810 |
+
break
|
811 |
+
|
812 |
+
try:
|
813 |
+
logger.info(f"🔄 Scraping {i+1}/{len(urls)}: {url}")
|
814 |
+
time.sleep(self.delay)
|
815 |
+
|
816 |
+
response = self.session.get(url, timeout=15)
|
817 |
+
response.raise_for_status()
|
818 |
+
|
819 |
+
if response.encoding == 'ISO-8859-1':
|
820 |
+
response.encoding = response.apparent_encoding
|
821 |
+
|
822 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
823 |
+
|
824 |
+
# Extract documents using source-specific logic
|
825 |
+
extracted_items = self._extract_source_specific_content(soup, url, max_docs - len(documents))
|
826 |
+
|
827 |
+
for item in extracted_items:
|
828 |
+
if len(documents) >= max_docs:
|
829 |
+
break
|
830 |
+
|
831 |
+
doc = LegalDocument(
|
832 |
+
title=item['title'],
|
833 |
+
content=item['content'],
|
834 |
+
source_url=item['url'],
|
835 |
+
document_type=self._determine_document_type(item['title'], item['content']),
|
836 |
+
date_published=item['date']
|
837 |
+
)
|
838 |
+
|
839 |
+
if self.nlp_processor:
|
840 |
+
doc = self.nlp_processor.process_document(doc)
|
841 |
+
|
842 |
+
documents.append(doc)
|
843 |
+
logger.info(f"✅ Extracted: {doc.title[:50]}...")
|
844 |
+
|
845 |
+
except Exception as e:
|
846 |
+
logger.error(f"❌ Error scraping {url}: {e}")
|
847 |
+
continue
|
848 |
+
|
849 |
+
documents.sort(key=lambda x: x.importance_score, reverse=True)
|
850 |
+
return documents
|
851 |
+
|
852 |
+
def _extract_source_specific_content(self, soup: BeautifulSoup, url: str, max_items: int) -> List[Dict]:
|
853 |
+
"""Extract content based on source-specific selectors"""
|
854 |
+
if 'irna.ir' in url:
|
855 |
+
return self._extract_irna_content(soup, url, max_items)
|
856 |
+
elif 'tasnimnews.com' in url:
|
857 |
+
return self._extract_tasnim_content(soup, url, max_items)
|
858 |
+
elif 'mehrnews.com' in url:
|
859 |
+
return self._extract_mehr_content(soup, url, max_items)
|
860 |
+
elif 'farsnews.ir' in url:
|
861 |
+
return self._extract_fars_content(soup, url, max_items)
|
862 |
+
else:
|
863 |
+
return self._extract_generic_content(soup, url, max_items)
|
864 |
+
|
865 |
+
def _extract_irna_content(self, soup: BeautifulSoup, base_url: str, max_items: int) -> List[Dict]:
|
866 |
+
"""Extract content from IRNA"""
|
867 |
+
items = []
|
868 |
+
try:
|
869 |
+
articles = soup.select('.news-item, .article, .story')[:max_items]
|
870 |
+
|
871 |
+
for article in articles:
|
872 |
+
title_elem = soup.select_one('h1, h2, h3, .title, .headline, a')
|
873 |
+
if title_elem:
|
874 |
+
title = title_elem.get_text(strip=True)
|
875 |
+
content = article.get_text(strip=True)
|
876 |
+
|
877 |
+
if len(title) > 10 and len(content) > 100:
|
878 |
+
items.append({
|
879 |
+
'title': title,
|
880 |
+
'content': content,
|
881 |
+
'url': base_url,
|
882 |
+
'date': self._extract_date(soup)
|
883 |
+
})
|
884 |
+
|
885 |
+
if not items:
|
886 |
+
main_content = soup.select_one('main, .main-content, .content, article')
|
887 |
+
if main_content:
|
888 |
+
title = soup.select_one('h1, title')
|
889 |
+
title_text = title.get_text(strip=True) if title else "خبر ایرنا"
|
890 |
+
content_text = main_content.get_text(strip=True)
|
891 |
+
|
892 |
+
if len(content_text) > 200:
|
893 |
+
items.append({
|
894 |
+
'title': title_text,
|
895 |
+
'content': content_text,
|
896 |
+
'url': base_url,
|
897 |
+
'date': self._extract_date(soup)
|
898 |
+
})
|
899 |
+
|
900 |
+
except Exception as e:
|
901 |
+
logger.error(f"IRNA extraction error: {e}")
|
902 |
+
|
903 |
+
return items
|
904 |
+
|
905 |
+
def _extract_tasnim_content(self, soup: BeautifulSoup, base_url: str, max_items: int) -> List[Dict]:
|
906 |
+
"""Extract content from Tasnim"""
|
907 |
+
items = []
|
908 |
+
try:
|
909 |
+
articles = soup.select('.news-box, .item, .story-item')[:max_items]
|
910 |
+
|
911 |
+
for article in articles:
|
912 |
+
title_elem = article.select_one('h2, h3, .title, a')
|
913 |
+
if title_elem:
|
914 |
+
title = title_elem.get_text(strip=True)
|
915 |
+
content = article.get_text(strip=True)
|
916 |
+
|
917 |
+
if len(title) > 10 and len(content) > 100:
|
918 |
+
items.append({
|
919 |
+
'title': title,
|
920 |
+
'content': content,
|
921 |
+
'url': base_url,
|
922 |
+
'date': self._extract_date(soup)
|
923 |
+
})
|
924 |
+
|
925 |
+
if not items:
|
926 |
+
main_content = soup.select_one('.news-content, .story-body, main')
|
927 |
+
if main_content:
|
928 |
+
title = soup.select_one('h1, .news-title')
|
929 |
+
title_text = title.get_text(strip=True) if title else "خبر تسنیم"
|
930 |
+
content_text = main_content.get_text(strip=True)
|
931 |
+
|
932 |
+
if len(content_text) > 200:
|
933 |
+
items.append({
|
934 |
+
'title': title_text,
|
935 |
+
'content': content_text,
|
936 |
+
'url': base_url,
|
937 |
+
'date': self._extract_date(soup)
|
938 |
+
})
|
939 |
+
|
940 |
+
except Exception as e:
|
941 |
+
logger.error(f"Tasnim extraction error: {e}")
|
942 |
+
|
943 |
+
return items
|
944 |
+
|
945 |
+
def _extract_mehr_content(self, soup: BeautifulSoup, base_url: str, max_items: int) -> List[Dict]:
|
946 |
+
"""Extract content from Mehr News"""
|
947 |
+
items = []
|
948 |
+
try:
|
949 |
+
articles = soup.select('.news-item, .article-item, .story')[:max_items]
|
950 |
+
|
951 |
+
for article in articles:
|
952 |
+
title_elem = article.select_one('h2, h3, .title, .headline')
|
953 |
+
if title_elem:
|
954 |
+
title = title_elem.get_text(strip=True)
|
955 |
+
content = article.get_text(strip=True)
|
956 |
+
|
957 |
+
if len(title) > 10 and len(content) > 100:
|
958 |
+
items.append({
|
959 |
+
'title': title,
|
960 |
+
'content': content,
|
961 |
+
'url': base_url,
|
962 |
+
'date': self._extract_date(soup)
|
963 |
+
})
|
964 |
+
|
965 |
+
if not items:
|
966 |
+
main_content = soup.select_one('.content, .news-body, article')
|
967 |
+
if main_content:
|
968 |
+
title = soup.select_one('h1, .page-title')
|
969 |
+
title_text = title.get_text(strip=True) if title else "خبر مهر"
|
970 |
+
content_text = main_content.get_text(strip=True)
|
971 |
+
|
972 |
+
if len(content_text) > 200:
|
973 |
+
items.append({
|
974 |
+
'title': title_text,
|
975 |
+
'content': content_text,
|
976 |
+
'url': base_url,
|
977 |
+
'date': self._extract_date(soup)
|
978 |
+
})
|
979 |
+
|
980 |
+
except Exception as e:
|
981 |
+
logger.error(f"Mehr extraction error: {e}")
|
982 |
+
|
983 |
+
return items
|
984 |
+
|
985 |
+
def _extract_fars_content(self, soup: BeautifulSoup, base_url: str, max_items: int) -> List[Dict]:
|
986 |
+
"""Extract content from Fars News"""
|
987 |
+
items = []
|
988 |
+
try:
|
989 |
+
articles = soup.select('.news, .item, .story-item')[:max_items]
|
990 |
+
|
991 |
+
for article in articles:
|
992 |
+
title_elem = article.select_one('h2, h3, .title, a')
|
993 |
+
if title_elem:
|
994 |
+
title = title_elem.get_text(strip=True)
|
995 |
+
content = article.get_text(strip=True)
|
996 |
+
|
997 |
+
if len(title) > 10 and len(content) > 100:
|
998 |
+
items.append({
|
999 |
+
'title': title,
|
1000 |
+
'content': content,
|
1001 |
+
'url': base_url,
|
1002 |
+
'date': self._extract_date(soup)
|
1003 |
+
})
|
1004 |
+
|
1005 |
+
if not items:
|
1006 |
+
main_content = soup.select_one('.news-content, .story, main')
|
1007 |
+
if main_content:
|
1008 |
+
title = soup.select_one('h1, .news-title')
|
1009 |
+
title_text = title.get_text(strip=True) if title else "خبر فارس"
|
1010 |
+
content_text = main_content.get_text(strip=True)
|
1011 |
+
|
1012 |
+
if len(content_text) > 200:
|
1013 |
+
items.append({
|
1014 |
+
'title': title_text,
|
1015 |
+
'content': content_text,
|
1016 |
+
'url': base_url,
|
1017 |
+
'date': self._extract_date(soup)
|
1018 |
+
})
|
1019 |
+
|
1020 |
+
except Exception as e:
|
1021 |
+
logger.error(f"Fars extraction error: {e}")
|
1022 |
+
|
1023 |
+
return items
|
1024 |
+
|
1025 |
+
def _extract_generic_content(self, soup: BeautifulSoup, base_url: str, max_items: int) -> List[Dict]:
|
1026 |
+
"""Generic content extraction for unknown sources"""
|
1027 |
+
items = []
|
1028 |
+
try:
|
1029 |
+
articles = soup.select('article, .article, .post, .news-item, .story')[:max_items]
|
1030 |
+
|
1031 |
+
for article in articles:
|
1032 |
+
title_elem = article.select_one('h1, h2, h3, .title, .headline')
|
1033 |
+
if title_elem:
|
1034 |
+
title = title_elem.get_text(strip=True)
|
1035 |
+
content = article.get_text(strip=True)
|
1036 |
+
|
1037 |
+
if len(title) > 10 and len(content) > 150:
|
1038 |
+
items.append({
|
1039 |
+
'title': title,
|
1040 |
+
'content': content,
|
1041 |
+
'url': base_url,
|
1042 |
+
'date': self._extract_date(soup)
|
1043 |
+
})
|
1044 |
+
|
1045 |
+
if not items:
|
1046 |
+
title_elem = soup.select_one('h1, title')
|
1047 |
+
content_elem = soup.select_one('main, .main-content, .content, .entry-content, body')
|
1048 |
+
|
1049 |
+
if title_elem and content_elem:
|
1050 |
+
for unwanted in content_elem(['script', 'style', 'nav', 'header', 'footer']):
|
1051 |
+
unwanted.decompose()
|
1052 |
+
|
1053 |
+
title = title_elem.get_text(strip=True)
|
1054 |
+
content = content_elem.get_text(strip=True)
|
1055 |
+
|
1056 |
+
if len(title) > 5 and len(content) > 200:
|
1057 |
+
items.append({
|
1058 |
+
'title': title,
|
1059 |
+
'content': content,
|
1060 |
+
'url': base_url,
|
1061 |
+
'date': self._extract_date(soup)
|
1062 |
+
})
|
1063 |
+
|
1064 |
+
except Exception as e:
|
1065 |
+
logger.error(f"Generic extraction error: {e}")
|
1066 |
+
|
1067 |
+
return items
|
1068 |
+
|
1069 |
+
def _extract_document_from_soup(self, soup: BeautifulSoup, url: str) -> Optional[LegalDocument]:
|
1070 |
+
"""Extract main document from BeautifulSoup object using source-specific logic"""
|
1071 |
+
try:
|
1072 |
+
items = self._extract_source_specific_content(soup, url, 1)
|
1073 |
+
|
1074 |
+
if not items:
|
1075 |
+
return None
|
1076 |
+
|
1077 |
+
item = items[0]
|
1078 |
+
|
1079 |
+
return LegalDocument(
|
1080 |
+
title=item['title'],
|
1081 |
+
content=item['content'],
|
1082 |
+
source_url=item['url'],
|
1083 |
+
document_type=self._determine_document_type(item['title'], item['content']),
|
1084 |
+
date_published=item['date']
|
1085 |
+
)
|
1086 |
+
|
1087 |
+
except Exception as e:
|
1088 |
+
logger.error(f"Document extraction failed: {e}")
|
1089 |
+
return None
|
1090 |
+
|
1091 |
+
def _extract_additional_articles(self, soup: BeautifulSoup, base_url: str) -> List[LegalDocument]:
|
1092 |
+
"""Extract additional articles from the same page using source-specific logic"""
|
1093 |
+
documents = []
|
1094 |
+
|
1095 |
+
try:
|
1096 |
+
items = self._extract_source_specific_content(soup, base_url, 3)
|
1097 |
+
|
1098 |
+
for item in items:
|
1099 |
+
doc = LegalDocument(
|
1100 |
+
title=item['title'],
|
1101 |
+
content=item['content'],
|
1102 |
+
source_url=item['url'],
|
1103 |
+
document_type=self._determine_document_type(item['title'], item['content']),
|
1104 |
+
date_published=item['date']
|
1105 |
+
)
|
1106 |
+
|
1107 |
+
documents.append(doc)
|
1108 |
+
|
1109 |
+
except Exception as e:
|
1110 |
+
logger.error(f"Additional articles extraction failed: {e}")
|
1111 |
+
|
1112 |
+
return documents[:3]
|
1113 |
+
|
1114 |
+
def _determine_document_type(self, title: str, content: str) -> str:
|
1115 |
+
"""Determine document type based on content"""
|
1116 |
+
text = (title + " " + content).lower()
|
1117 |
+
|
1118 |
+
if any(word in text for word in ['قانون', 'ماده', 'فصل', 'بند', 'تبصره']):
|
1119 |
+
return 'law'
|
1120 |
+
elif any(word in text for word in ['رای', 'حکم', 'دادگاه', 'قاضی']):
|
1121 |
+
return 'ruling'
|
1122 |
+
elif any(word in text for word in ['آییننامه', 'دستورالعمل', 'بخشنامه']):
|
1123 |
+
return 'regulation'
|
1124 |
+
elif any(word in text for word in ['خبر', 'اعلام', 'گزارش', 'اطلاعیه']):
|
1125 |
+
return 'news'
|
1126 |
+
else:
|
1127 |
+
return 'general'
|
1128 |
+
|
1129 |
+
def _extract_date(self, soup: BeautifulSoup) -> Optional[str]:
|
1130 |
+
"""Extract publication date"""
|
1131 |
+
try:
|
1132 |
+
date_selectors = [
|
1133 |
+
'meta[name="article:published_time"]',
|
1134 |
+
'meta[property="article:published_time"]',
|
1135 |
+
'meta[name="date"]',
|
1136 |
+
'meta[name="DC.date"]',
|
1137 |
+
'.date',
|
1138 |
+
'.publish-date',
|
1139 |
+
'.article-date',
|
1140 |
+
'time[datetime]'
|
1141 |
+
]
|
1142 |
+
|
1143 |
+
for selector in date_selectors:
|
1144 |
+
element = soup.select_one(selector)
|
1145 |
+
if element:
|
1146 |
+
date_str = element.get('content') or element.get('datetime') or element.get_text()
|
1147 |
+
if date_str:
|
1148 |
+
return self._normalize_date(date_str)
|
1149 |
+
|
1150 |
+
text = soup.get_text()
|
1151 |
+
persian_date_patterns = [
|
1152 |
+
r'(\d{4}/\d{1,2}/\d{1,2})',
|
1153 |
+
r'(\d{1,2}/\d{1,2}/\d{4})',
|
1154 |
+
r'(\d{4}-\d{1,2}-\d{1,2})'
|
1155 |
+
]
|
1156 |
+
|
1157 |
+
for pattern in persian_date_patterns:
|
1158 |
+
match = re.search(pattern, text)
|
1159 |
+
if match:
|
1160 |
+
return match.group(1)
|
1161 |
+
|
1162 |
+
return None
|
1163 |
+
|
1164 |
+
except Exception:
|
1165 |
+
return None
|
1166 |
+
|
1167 |
+
def _normalize_date(self, date_str: str) -> Optional[str]:
|
1168 |
+
"""Normalize date string to standard format"""
|
1169 |
+
try:
|
1170 |
+
date_str = re.sub(r'[^\d/\-:]', ' ', date_str).strip()
|
1171 |
+
|
1172 |
+
formats = [
|
1173 |
+
'%Y-%m-%d',
|
1174 |
+
'%Y/%m/%d',
|
1175 |
+
'%d/%m/%Y',
|
1176 |
+
'%Y-%m-%d %H:%M:%S',
|
1177 |
+
'%Y/%m/%d %H:%M:%S'
|
1178 |
+
]
|
1179 |
+
|
1180 |
+
for fmt in formats:
|
1181 |
+
try:
|
1182 |
+
parsed_date = datetime.strptime(date_str, fmt)
|
1183 |
+
return parsed_date.strftime('%Y-%m-%d')
|
1184 |
+
except ValueError:
|
1185 |
+
continue
|
1186 |
+
|
1187 |
+
return date_str
|
1188 |
+
|
1189 |
+
except Exception:
|
1190 |
+
return None
|