File size: 8,344 Bytes
cce70aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
import requests
from bs4 import BeautifulSoup
import time
import random
import json
from pathlib import Path
import logging
from urllib.parse import urljoin

# Configure logging
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s - %(levelname)s - %(message)s'
)
logger = logging.getLogger(__name__)

class BengaliDataCollector:
    def __init__(self):
        self.headers = {
            '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'
        }
        self.output_dir = Path('data/raw')
        self.output_dir.mkdir(parents=True, exist_ok=True)
        
    def make_request(self, url, retries=3, delay=1):
        """Make HTTP request with retry logic and rate limiting"""
        for attempt in range(retries):
            try:
                time.sleep(delay + random.random())  # Rate limiting with jitter
                response = requests.get(url, headers=self.headers)
                response.raise_for_status()
                return response
            except requests.RequestException as e:
                logger.warning(f"Attempt {attempt + 1} failed for {url}: {str(e)}")
                if attempt == retries - 1:
                    logger.error(f"Failed to fetch {url} after {retries} attempts")
                    raise
                time.sleep(delay * (attempt + 1))  # Exponential backoff
                
    def scrape_wikipedia(self):
        """Scrape Bengali text from Wikipedia"""
        url = "https://bn.wikipedia.org/wiki/প্রধান_পাতা"
        logger.info(f"Scraping Wikipedia: {url}")
        
        try:
            response = self.make_request(url)
            soup = BeautifulSoup(response.content, 'html.parser')
            
            # Get main content and featured articles
            content_div = soup.find('div', {'id': 'mw-content-text'})
            articles = []
            
            if content_div:
                # Extract article links
                article_links = content_div.find_all('a', href=True)
                for link in article_links[:50]:  # Limit to first 50 articles
                    if link['href'].startswith('/wiki/') and ':' not in link['href']:
                        article_url = urljoin('https://bn.wikipedia.org', link['href'])
                        try:
                            article_response = self.make_request(article_url)
                            article_soup = BeautifulSoup(article_response.content, 'html.parser')
                            
                            # Extract article content
                            article_content = article_soup.find('div', {'id': 'mw-content-text'})
                            if article_content:
                                text = article_content.get_text(separator='\n', strip=True)
                                articles.append({
                                    'url': article_url,
                                    'content': text
                                })
                                logger.info(f"Successfully scraped article: {article_url}")
                        except Exception as e:
                            logger.error(f"Failed to scrape article {article_url}: {str(e)}")
                            
            # Save Wikipedia data
            with open(self.output_dir / 'wikipedia_data.json', 'w', encoding='utf-8') as f:
                json.dump(articles, f, ensure_ascii=False, indent=2)
                
            return len(articles)
        except Exception as e:
            logger.error(f"Failed to scrape Wikipedia: {str(e)}")
            return 0

    def scrape_prothom_alo(self):
        """Scrape Bengali text from Prothom Alo"""
        base_url = "https://www.prothomalo.com"
        categories = ['bangladesh', 'international', 'opinion', 'science-technology']
        articles = []
        
        for category in categories:
            url = f"{base_url}/{category}"
            logger.info(f"Scraping Prothom Alo category: {category}")
            
            try:
                response = self.make_request(url)
                soup = BeautifulSoup(response.content, 'html.parser')
                
                # Find article links
                article_links = soup.find_all('a', href=True)
                for link in article_links[:10]:  # Limit to 10 articles per category
                    article_url = urljoin(base_url, link['href'])
                    if category in article_url:
                        try:
                            article_response = self.make_request(article_url)
                            article_soup = BeautifulSoup(article_response.content, 'html.parser')
                            
                            # Extract article content
                            article_content = article_soup.find('div', {'class': 'story-content'})
                            if article_content:
                                text = article_content.get_text(separator='\n', strip=True)
                                articles.append({
                                    'url': article_url,
                                    'category': category,
                                    'content': text
                                })
                                logger.info(f"Successfully scraped article: {article_url}")
                        except Exception as e:
                            logger.error(f"Failed to scrape article {article_url}: {str(e)}")
            
            except Exception as e:
                logger.error(f"Failed to scrape category {category}: {str(e)}")
                
        # Save Prothom Alo data
        with open(self.output_dir / 'prothomalo_data.json', 'w', encoding='utf-8') as f:
            json.dump(articles, f, ensure_ascii=False, indent=2)
            
        return len(articles)

    def collect(self):
        """Main method to collect data from all sources"""
        logger.info("Starting data collection")
        
        wiki_count = self.scrape_wikipedia()
        logger.info(f"Collected {wiki_count} articles from Wikipedia")
        
        prothomalo_count = self.scrape_prothom_alo()
        logger.info(f"Collected {prothomalo_count} articles from Prothom Alo")
        
        # Combine and process the collected data
        self.process_collected_data()
        
        logger.info("Data collection completed")
        
    def process_collected_data(self):
        """Process and combine collected data"""
        try:
            # Read collected data
            with open(self.output_dir / 'wikipedia_data.json', 'r', encoding='utf-8') as f:
                wiki_data = json.load(f)
            
            with open(self.output_dir / 'prothomalo_data.json', 'r', encoding='utf-8') as f:
                news_data = json.load(f)
            
            # Combine and format data
            processed_data = []
            
            # Process Wikipedia articles
            for article in wiki_data:
                processed_data.append({
                    'text': article['content'],
                    'source': 'wikipedia',
                    'url': article['url']
                })
            
            # Process news articles
            for article in news_data:
                processed_data.append({
                    'text': article['content'],
                    'source': 'prothomalo',
                    'category': article.get('category', ''),
                    'url': article['url']
                })
            
            # Save processed data
            with open(self.output_dir / 'processed_data.json', 'w', encoding='utf-8') as f:
                json.dump(processed_data, f, ensure_ascii=False, indent=2)
                
            logger.info(f"Successfully processed {len(processed_data)} articles")
            
        except Exception as e:
            logger.error(f"Failed to process collected data: {str(e)}")
            raise

if __name__ == "__main__":
    collector = BengaliDataCollector()
    collector.collect()