feat: Implement Walmart scraper and integrate with existing architecture

- Added Walmart scraper to scrape product data from Walmart.com, including category pages and product details.
- Introduced a stealth browser module to handle bot protection and improve scraping reliability.
- Created a SQLite database for tracking product history, price changes, stock events, and user favorites.
- Developed a Discord bot for user interaction, allowing location setting and stock checking at local stores.
- Implemented a favorites system to manage priority products and categories with custom notification settings.
- Added news aggregation module to fetch and analyze Pokemon TCG news from various sources.
- Created tools for API discovery and monitoring, including a backend monitor for detecting new products.
- Added unit tests for database operations, product filtering, and API endpoints to ensure functionality.
- Enhanced existing modules with improved error handling and logging for better maintainability.
This commit is contained in:
2026-03-27 23:08:09 -04:00
parent cddae24e34
commit 8d382e723f
64 changed files with 15433 additions and 443 deletions
+74 -56
View File
@@ -9,7 +9,7 @@ from typing import List, Optional
from bs4 import BeautifulSoup
from .base import BaseScraper, Product
from browser import get_browser
from src.browser import get_browser
logger = logging.getLogger(__name__)
@@ -20,87 +20,105 @@ class TargetScraper(BaseScraper):
site_name = "target"
base_url = "https://www.target.com"
def scrape_category_page(self, url: str) -> List[Product]:
def scrape_category_page(self, url: str, max_pages: int = 1) -> List[Product]:
"""
Scrape a Target search/category page for all products
Args:
url: Search/category page URL
max_pages: Maximum number of pages to scrape (default 1)
Returns:
List of Product objects
"""
browser = get_browser()
products = []
all_products = []
try:
page, html = browser.get_page_content(
url,
wait_for_selector=None,
timeout=60000,
)
# Add sort by newest if not already in URL
if "sortBy=" not in url:
separator = "&" if "?" in url else "?"
url = f"{url}{separator}sortBy=newest"
for page_num in range(1, max_pages + 1):
products = []
page_url = url if page_num == 1 else f"{url}&Nao={24 * (page_num - 1)}"
# Save debug screenshot
try:
page.screenshot(path="debug_target.png")
logger.info("Saved debug screenshot to debug_target.png")
except:
pass
page, html = browser.get_page_content(
page_url,
wait_for_selector=None,
timeout=60000,
)
soup = BeautifulSoup(html, "html.parser")
# Try to find product data in page scripts (Target uses React/hydration)
scripts = soup.find_all("script", type="application/json")
for script in scripts:
# Save debug screenshot
try:
data = json.loads(script.string)
# Look for product data in the JSON
products.extend(self._extract_products_from_json(data))
except (json.JSONDecodeError, TypeError):
continue
page.screenshot(path="debug_target.png")
logger.info("Saved debug screenshot to debug_target.png")
except:
pass
# Parse product links from the page
product_links = soup.select("a[href*='/p/']")
logger.info(f"Found {len(product_links)} product links")
soup = BeautifulSoup(html, "html.parser")
# Group links by href and pick the best one (with aria-label or text)
href_to_links = {}
for link in product_links:
href = link.get("href", "")
if not href:
continue
if href not in href_to_links:
href_to_links[href] = []
href_to_links[href].append(link)
# Try to find product data in page scripts (Target uses React/hydration)
scripts = soup.find_all("script", type="application/json")
for script in scripts:
try:
data = json.loads(script.string)
# Look for product data in the JSON
products.extend(self._extract_products_from_json(data))
except (json.JSONDecodeError, TypeError):
continue
logger.info(f"Found {len(href_to_links)} unique hrefs")
# Parse product links from the page
product_links = soup.select("a[href*='/p/']")
logger.info(f"Found {len(product_links)} product links")
for href, links in href_to_links.items():
# Find the best link (one with aria-label or text content)
best_link = None
for link in links:
aria = link.get("aria-label", "")
text = link.get_text(strip=True)
if aria or (text and len(text) > 10):
best_link = link
break
if not best_link:
best_link = links[0] # Fallback to first link
# Group links by href and pick the best one (with aria-label or text)
href_to_links = {}
for link in product_links:
href = link.get("href", "")
if not href:
continue
if href not in href_to_links:
href_to_links[href] = []
href_to_links[href].append(link)
product = self._parse_product_link(best_link, soup)
if product:
products.append(product)
logger.info(f"Found {len(href_to_links)} unique hrefs")
page.close()
for href, links in href_to_links.items():
# Find the best link (one with aria-label or text content)
best_link = None
for link in links:
aria = link.get("aria-label", "")
text = link.get_text(strip=True)
if aria or (text and len(text) > 10):
best_link = link
break
if not best_link:
best_link = links[0] # Fallback to first link
except Exception as e:
logger.error(f"Error scraping Target category page: {e}")
raise
product = self._parse_product_link(best_link, soup)
if product:
products.append(product)
page.close()
except Exception as e:
logger.error(f"Error scraping Target page {page_num}: {e}")
if page_num == 1:
raise
break
all_products.extend(products)
# Stop if no products found on this page
if not products:
break
# Remove duplicates
seen_urls = set()
unique_products = []
for p in products:
for p in all_products:
if p.url not in seen_urls:
seen_urls.add(p.url)
unique_products.append(p)