File size: 5,266 Bytes
dcc91e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
from typing import Dict, List, Any
import requests
from bs4 import BeautifulSoup
from duckduckgo_search import ddg
from transformers import pipeline
from langchain.embeddings import HuggingFaceEmbeddings
import time
import json
import os
from urllib.parse import urlparse

class ModelManager:
    """Manages AI models for text processing"""
    def __init__(self):
        # Initialize with smaller, CPU-friendly models
        self.summarizer = pipeline(
            "summarization",
            model="facebook/bart-base",
            device=-1  # Use CPU
        )
        self.embeddings = HuggingFaceEmbeddings(
            model_name="sentence-transformers/all-MiniLM-L6-v2"
        )
    
    def generate_summary(self, text: str, max_length: int = 150) -> str:
        """Generate a concise summary of the text"""
        if not text or len(text.split()) < 50:
            return text
        
        try:
            summary = self.summarizer(
                text,
                max_length=max_length,
                min_length=30,
                do_sample=False
            )[0]['summary_text']
            return summary
        except Exception as e:
            print(f"Error in summarization: {e}")
            return text[:500] + "..."

class ContentProcessor:
    """Processes and analyzes different types of content"""
    def __init__(self):
        self.model_manager = ModelManager()
    
    def process_content(self, content: str) -> Dict[str, Any]:
        """Process content and generate insights"""
        if not content:
            return {"summary": "", "insights": []}
        
        try:
            summary = self.model_manager.generate_summary(content)
            return {
                "summary": summary,
                "insights": []  # Simplified for CPU deployment
            }
        except Exception as e:
            print(f"Error processing content: {e}")
            return {"summary": content[:500] + "...", "insights": []}

class WebSearchEngine:
    """Main search engine class"""
    def __init__(self):
        self.processor = ContentProcessor()
        self.session = requests.Session()
        self.request_delay = 1.0
        self.last_request_time = 0
    
    def is_valid_url(self, url: str) -> bool:
        """Check if URL is valid for crawling"""
        try:
            parsed = urlparse(url)
            return bool(parsed.netloc and parsed.scheme in ['http', 'https'])
        except:
            return False
    
    def get_metadata(self, soup: BeautifulSoup) -> Dict[str, str]:
        """Extract metadata from page"""
        metadata = {}
        
        # Get title
        title = soup.find('title')
        if title:
            metadata['title'] = title.text.strip()
        
        # Get meta description
        desc = soup.find('meta', attrs={'name': 'description'})
        if desc:
            metadata['description'] = desc.get('content', '')
        
        # Get publication date
        date = soup.find('meta', attrs={'property': 'article:published_time'})
        if date:
            metadata['published_date'] = date.get('content', '').split('T')[0]
        
        return metadata
    
    def process_url(self, url: str) -> Dict[str, Any]:
        """Process a single URL"""
        if not self.is_valid_url(url):
            return None
        
        try:
            # Rate limiting
            current_time = time.time()
            if current_time - self.last_request_time < self.request_delay:
                time.sleep(self.request_delay)
            
            response = self.session.get(url, timeout=10)
            self.last_request_time = time.time()
            
            if response.status_code != 200:
                return None
            
            soup = BeautifulSoup(response.text, 'lxml')
            metadata = self.get_metadata(soup)
            
            # Extract main content (simplified)
            content = ' '.join([p.text for p in soup.find_all('p')])
            processed = self.processor.process_content(content)
            
            return {
                'url': url,
                'title': metadata.get('title', url),
                'summary': processed['summary'],
                'published_date': metadata.get('published_date', '')
            }
        
        except Exception as e:
            print(f"Error processing URL {url}: {e}")
            return None
    
    def search(self, query: str, max_results: int = 5) -> List[Dict[str, Any]]:
        """Perform search and process results"""
        try:
            # Perform DuckDuckGo search
            search_results = ddg(query, max_results=max_results)
            
            results = []
            for result in search_results:
                processed = self.process_url(result['link'])
                if processed:
                    results.append(processed)
            
            return results[:max_results]
            
        except Exception as e:
            print(f"Error in search: {e}")
            return []

# Main search function
def search(query: str, max_results: int = 5) -> List[Dict[str, Any]]:
    """Main search function"""
    engine = WebSearchEngine()
    return engine.search(query, max_results)