amzpy 0.1.0__py3-none-any.whl

amzpy/__init__.py

@@ -0,0 +1,21 @@
+"""
+AmzPy - Amazon Product Scraper
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+A lightweight Python library for scraping product information from Amazon.
+
+Basic usage:
+    >>> from amzpy import AmazonScraper
+    >>> scraper = AmazonScraper()
+    >>> details = scraper.get_product_details("https://www.amazon.com/dp/B0D4J2QDVY")
+    >>> print(details)
+
+:copyright: (c) 2025 by Anil Sardiwal.
+:license: MIT, see LICENSE for more details.
+"""
+
+from .scraper import AmazonScraper
+
+__version__ = "0.1.0"
+__author__ = "Anil Sardiwal"
+__license__ = "MIT"

amzpy/engine.py

@@ -0,0 +1,36 @@
+import requests
+from typing import Optional
+from fake_useragent import UserAgent
+
+class RequestEngine:
+    """Handles all HTTP requests to Amazon with anti-bot measures"""
+    
+    def __init__(self):
+        self.session = requests.Session()
+        self.ua = UserAgent(browsers=['Edge', 'Chrome'])
+        self.headers = {
+            'User-Agent': self.ua.random,
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Connection': 'keep-alive',
+        }
+        
+    def get(self, url: str) -> Optional[str]:
+        """
+        Make a GET request with anti-bot measures
+        
+        Args:
+            url (str): URL to fetch
+            
+        Returns:
+            str: HTML content if successful
+            None: If request fails
+        """
+        try:
+            # Update User-Agent for each request
+            self.headers['User-Agent'] = self.ua.random
+            response = self.session.get(url, headers=self.headers)
+            response.raise_for_status()
+            return response.text
+        except Exception:
+            return None

amzpy/parser.py

@@ -0,0 +1,59 @@
+from bs4 import BeautifulSoup
+from typing import Dict, Optional
+from engine import RequestEngine
+
+def parse_product_page(html_content: str, url: str = None, engine: RequestEngine = None, max_retries: int = 0) -> Optional[Dict]:
+    """
+    Parse Amazon product page HTML and extract relevant information
+    
+    Args:
+        html_content (str): Raw HTML content of the product page
+        url (str, optional): Product URL for retrying if needed
+        engine (RequestEngine, optional): RequestEngine instance for retries
+        max_retries (int): Number of remaining retry attempts
+        
+    Returns:
+        Dict: Extracted product information (title, price, img_url, currency)
+        None: If parsing fails after all retries
+    """
+    if not html_content:
+        return None
+        
+    soup = BeautifulSoup(html_content, 'html.parser')
+    
+    try:
+        # Get title
+        title = soup.select_one('#productTitle')
+        title = title.text.strip() if title else None
+        
+        # If title is None and we have retries left, try again
+        if title is None and max_retries > 0 and url and engine:
+            print(f"Retry attempt {max_retries} - Anti-bot measure detected")
+            new_html = engine.get(url)
+            return parse_product_page(new_html, url, engine, max_retries - 1)
+        
+        # Get price
+        price_element = soup.select_one('.a-price-whole')
+        price = price_element.text.strip().replace(',', '') if price_element else None
+        
+        # Get currency symbol
+        currency_element = soup.select_one('.a-price-symbol')
+        currency = currency_element.text.strip() if currency_element else None
+        
+        # Get main product image
+        img_element = soup.select_one('#landingImage') or soup.select_one('#imgBlkFront')
+        img_url = img_element.get('src') if img_element else None
+        
+        return {
+            "title": title,
+            "price": price,
+            "img_url": img_url,
+            "currency": currency
+        }
+    except Exception:
+        # If we have retries left, try again
+        if max_retries > 0 and url and engine:
+            print(f"Retry attempt {max_retries} - Error occurred")
+            new_html = engine.get(url)
+            return parse_product_page(new_html, url, engine, max_retries - 1)
+        return None

amzpy/scraper.py

@@ -0,0 +1,52 @@
+"""
+The main scraper module for the Amazon Product API.
+"""
+
+from typing import Dict, Optional
+from engine import RequestEngine
+from parser import parse_product_page
+from utils import parse_amazon_url
+
+class AmazonScraper:
+    """Main scraper class for Amazon product data"""
+    
+    def __init__(self, country_code: str = "com"):
+        """Initialize the Amazon scraper"""
+        self.base_url = f"https://www.amazon.{country_code}/"
+        self.engine = RequestEngine()
+    
+    def get_product_details(self, url: str, max_retries: int = 3) -> Optional[Dict]:
+        """
+        Fetch details for a product using its Amazon URL
+        
+        Args:
+            url (str): Amazon product URL
+            max_retries (int): Maximum retry attempts if anti-bot measures detected
+            
+        Returns:
+            Dict: Product details including title, price, img_url, and currency
+            None: If URL is invalid or error occurs
+        """
+        parsed = parse_amazon_url(url)
+        if not parsed:
+            return None
+            
+        base_url, product_id = parsed
+        
+        # Construct product URL and get HTML
+        product_url = f"{base_url}dp/{product_id}"
+        html_content = self.engine.get(product_url)
+        if not html_content:
+            return None
+            
+        # Parse the product page and return the data
+        return parse_product_page(html_content, product_url, self.engine, max_retries)
+    
+def main():
+    scraper = AmazonScraper()
+    url = "https://www.amazon.in/dp/B0D4J2QDVY"
+    details = scraper.get_product_details(url, max_retries=5)
+    print("Product details:", details)
+
+if __name__ == "__main__":
+    main()

amzpy/utils.py

@@ -0,0 +1,38 @@
+from typing import Tuple, Optional
+import re
+
+def parse_amazon_url(url: str) -> Optional[Tuple[str, str]]:
+    """
+    Parse Amazon product URL to extract base URL and product ID
+    
+    Args:
+        url (str): Full Amazon product URL
+        
+    Returns:
+        Tuple[str, str]: (base_url, product_id) if valid
+        None: If URL is invalid
+        
+    Examples:
+        >>> parse_amazon_url("https://www.amazon.com/dp/B0D4J2QDVY")
+        ("https://www.amazon.com/", "B0D4J2QDVY")
+        >>> parse_amazon_url("https://www.amazon.in/product-name/dp/B0D4J2QDVY/ref=...")
+        ("https://www.amazon.in/", "B0D4J2QDVY")
+    """
+    # Clean up the URL
+    url = url.strip()
+    
+    # Match Amazon domain and product ID
+    pattern = r'https?://(?:www\.)?amazon\.([a-z.]+)(?:/[^/]+)*?/(?:dp|gp/product)/([A-Z0-9]{10})'
+    match = re.search(pattern, url)
+    
+    if not match:
+        return None
+        
+    # Extract domain and construct base URL
+    domain = match.group(1)
+    base_url = f"https://www.amazon.{domain}/"
+    
+    # Extract product ID
+    product_id = match.group(2)
+    
+    return base_url, product_id 

amzpy-0.1.0.dist-info/METADATA

@@ -0,0 +1,92 @@
+Metadata-Version: 2.2
+Name: amzpy
+Version: 0.1.0
+Summary: A lightweight Amazon scraper library.
+Home-page: https://github.com/theonlyanil/amzpy
+Author: Anil Sardiwal
+Author-email: theonlyanil@gmail.com
+Keywords: amazon,scraper,web-scraping,product-data,e-commerce
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Internet :: WWW/HTTP :: Dynamic Content
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: requests
+Requires-Dist: beautifulsoup4
+Requires-Dist: fake-useragent
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# AmzPy - Amazon Product Scraper
+
+AmzPy is a lightweight Python library for scraping product information from Amazon. It provides a simple interface to fetch product details like title, price, currency, and image URL while handling anti-bot measures automatically.
+
+## Features
+
+- Easy-to-use API for scraping Amazon product data
+- Supports multiple Amazon domains (.com, .in, .co.uk, etc.)
+- Built-in anti-bot protection
+- Automatic retries on detection
+- Clean and typed Python interface
+
+## Installation
+
+Install using pip:
+`pip install amzpy`
+
+## Usage
+
+Here's a basic example of how to use AmzPy:
+
+```python
+from amzpy import AmazonScraper
+
+scraper = AmazonScraper()
+product_details = scraper.get_product_details("https://www.amazon.com/dp/B0D4J2QDVY")
+print(product_details)
+```
+
+This will output the product details including title, price, image URL, and currency.
+
+Feel free to explore the codebase for more details and advanced features. Happy scraping!
+
+Output:
+```json
+{
+"title": "Product Title",
+"price": "299",
+"currency": "$",
+"img_url": "https://..."
+}
+```
+## Requirements
+
+- Python 3.6+
+- requests
+- beautifulsoup4
+- fake-useragent
+
+## License
+
+This project is licensed under the MIT License - see the LICENSE file for details.
+
+## Contributing
+
+Contributions are welcome! Please read [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to contribute to this project.

amzpy-0.1.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+amzpy/__init__.py,sha256=D_HAyk3vKeexDTiuLozKEHMPqpWDX_hecvXdGsRL9LE,535
+amzpy/engine.py,sha256=5ZyzdaQnxEZorYZMxav-qJTPdnRHXFyimwDJvicjtbI,1171
+amzpy/parser.py,sha256=yLiJsFxPElTM7muvw7EicB6bjfv5d_uf23IX-LimWbA,2348
+amzpy/scraper.py,sha256=FmuIKkllHau384nVp1AqnYVk6k8FOaz8nFbGHILo0d4,1692
+amzpy/utils.py,sha256=iyrAnhDB_1Lnn49CVYEowFZ1QZhonl8U23ZltR_WyZ4,1132
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/test_scraper.py,sha256=XVbRrjM-b8ihuPjx5XezEU5o5twJ7xSBwp1ez28OcKs,582
+amzpy-0.1.0.dist-info/METADATA,sha256=B_jsC5mTALBpXwIMox5dNhEupQhcIogIhNOfy3UvOLI,2632
+amzpy-0.1.0.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+amzpy-0.1.0.dist-info/top_level.txt,sha256=Srr5VxRSsZN9fziW9RLJtXt4o0dXk-b64YMijWr4y4Y,12
+amzpy-0.1.0.dist-info/RECORD,,

amzpy-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.8.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

amzpy-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+amzpy
+tests

tests/test_scraper.py

@@ -0,0 +1,16 @@
+import unittest
+from amzpy.scraper import AmazonScraper
+
+class TestAmazonScraper(unittest.TestCase):
+    def setUp(self):
+        self.scraper = AmazonScraper(retries=5, delay=1)
+
+    def test_product_details(self):
+        url = "https://www.amazon.in/dp/B09JK1PZ7N"
+        result = self.scraper.get_product_details(url)
+        
+        self.assertNotEqual(result["title"], "Title not found", "Title should be properly scraped.")
+        self.assertNotEqual(result["price"], "Price not found", "Price should be properly scraped.")
+
+if __name__ == "__main__":
+    unittest.main()