Merge pull request #4 from BrowserStackCE/Santosh_update

updated the code with latest changes

Author: princebaretto99

README.md

@@ -9,49 +9,49 @@ This project uses Selenium and Percy to capture visual snapshots of multiple URL
 
 ## Prerequisites
 
-- **Python**: Version 3.7 or higher
-- **Percy CLI**: Required for snapshot uploading (see installation steps below)
-- **ChromeDriver**: Ensure it matches your installed Chrome version
-- **Percy Account**: [Sign up for a Percy account](https://percy.io) to get your project token
+- **Python**: Version 3.7 or higher  
+- **Percy CLI**: Required for snapshot uploading (see installation steps below)  
+- **ChromeDriver**: Ensure it matches your installed Chrome version  
+- **Percy Account**: [Sign up for a Percy account](https://percy.io) to get your project token  
 
 ## Setup
 
-### Step 1: Install Percy CLI via npm
+### Step 1: Create a Python virtual environment
+
+It's recommended to create a virtual environment to manage dependencies isolated from your system Python.
+
+```bash
+python3 -m venv venv
+source venv/bin/activate 
+```
+
+### Step 2: Install Percy CLI via npm
 
 The Percy CLI is needed to capture and upload snapshots. Install it via npm:
 
 ```bash
 npm install
 ```
 
-### Step 2: Install Python dependencies
+### Step 3: Install Python dependencies
 
+With the virtual environment activated, install the required Python packages:
 
 ```bash
 pip3 install -r requirements.txt
 ```
 
-
 ## Usage
 
 ### Step 1: Update the `urls.csv` file
 
 This file contains all the URLs you need to capture using Percy.
 
-### Step 2: Update the `CHROMEDRIVER_PATH` variable in `batchProcess.py` file
-
-This will point the selenium test to your chromedrive to successfully launch the Chrome Browser. You can also update the variable `NUM_THREADS` if you want to increase the number of parallel threads.
-
-###  Step 3: Run the file to capture snapshots using Percy.
+### Step 2: Run the file to capture snapshots using Percy
 
 Export the Percy Token located in your project settings of Percy and then run the python command to initiate the execution.
 
 ```bash
 export PERCY_TOKEN=your-percy-token
 npx percy exec -- python3 batchProcess.py
-```
-
-
-
-
-
+```

batchProcess.py

@@ -1,53 +1,80 @@
 import csv
-import os
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
+from webdriver_manager.chrome import ChromeDriverManager
 from percy import percy_snapshot
 from time import sleep
 from concurrent.futures import ThreadPoolExecutor
+from selenium.webdriver.chrome.options import Options
+from urllib.parse import urlparse
+import re
 
-CSV_FILE = './urls.csv'  # Path to your CSV file
-NUM_THREADS = 5  # Number of parallel threads
-CHROMEDRIVER_PATH = "./chromedriver"
+CSV_FILE = './urls.csv'   # Path to your CSV file
+NUM_THREADS = 2           # Number of parallel threads
 
 # Load URLs from CSV
 def load_urls():
     with open(CSV_FILE, newline='') as file:
         reader = csv.reader(file)
-        return [row[0].strip() for row in reader if row[0].strip().startswith(("http://", "https://"))]
+        return [row[0].strip() for row in reader if row and row[0].strip().startswith(("http://", "https://"))]
+
+# Helper to split list into n even chunks
+def split_list(lst, n):
+    k, m = divmod(len(lst), n)
+    return [lst[i*k + min(i, m):(i+1)*k + min(i+1, m)] for i in range(n)]
 
 # Function for each thread to process its batch of URLs
 def process_urls(urls):
     if not urls:
         print("No URLs provided to process.")
         return
-    
-    service = Service(CHROMEDRIVER_PATH)
-    driver = webdriver.Chrome(service=service) 
+    # Use webdriver-manager to automatically install Chromedriver
+    options = Options()
+    options.add_argument("--headless=new")   # optional but recommended for Percy
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+
+    service = Service(ChromeDriverManager(driver_version="139.0.7258.155").install())
+    driver = webdriver.Chrome(service=service, options=options)
+    driver.set_window_size(1200, 800)
     try:
         for url in urls:
             print(f"Loading URL: {url}")
             driver.get(url)
-            sleep(2) 
+            sleep(2)
+
+            parsed_url = urlparse(url)
+            hostname = parsed_url.netloc
+            if hostname.startswith("www."):
+                hostname = hostname[4:]
+
+            # Sanitize path: remove leading slash and replace other slashes with underscores
+            path = parsed_url.path.lstrip('/')
+            sanitized_path = re.sub(r'[^a-zA-Z0-9_-]', '_', path)  # Replace non-alphanum/underscore/dash chars
+
+            # Construct snapshot name
+            if sanitized_path:
+                snapshot_name = f"Snapshot for {hostname}_{sanitized_path}"
+            else:
+                snapshot_name = f"Snapshot for {hostname}"
 
-            # Capture Percy snapshot
-            snapshot_name = f"Snapshot for {url}"
             print(f"Capturing Percy snapshot: {snapshot_name}")
-            percy_snapshot(driver, snapshot_name)
+            percy_snapshot(driver, snapshot_name,widths=[768, 1200])
+
     finally:
-        driver.quit()  # Ensure the driver closes after the batch is done
+        driver.quit()
 
 def main():
     urls = load_urls()
+    if not urls:
+        print("No URLs found in the CSV file.")
+        return
 
-    # Split URLs into batches based on the number of threads
-    batch_size = len(urls) // NUM_THREADS
-    url_batches = [urls[i:i + batch_size] for i in range(0, len(urls), batch_size)]
+    url_batches = split_list(urls, NUM_THREADS)
 
-    # Process each batch in parallel
     with ThreadPoolExecutor(max_workers=NUM_THREADS) as executor:
-        futures = [executor.submit(process_urls, batch) for batch in url_batches]
-        
+        # Submit only non-empty batches
+        futures = [executor.submit(process_urls, batch) for batch in url_batches if batch]
         for future in futures:
             future.result()
 

requirements.txt

@@ -16,3 +16,4 @@ typing_extensions==4.12.2
 urllib3==2.2.3
 websocket-client==1.8.0
 wsproto==1.2.0
+webdriver-manager==4.0.2

urls.csv

@@ -1,21 +1,2 @@
 URLs
-browserstack.com/docs
-browserstack.com/
 https://www.browserstack.com/docs/app-percy/integrate-bstack-sdk/webdriverio
-https://www.browserstack.com/docs/app-percy
-https://www.browserstack.com/docs/app-percy/overview/visual-testing-basics
-https://www.browserstack.com/docs/app-percy/overview/plans-and-billing
-https://www.browserstack.com/docs/app-percy/get-started/recommended-guidelines
-https://www.browserstack.com/docs/app-percy/source-code-integrations/overview
-https://www.browserstack.com/docs/app-percy/source-code-integrations/github
-https://www.browserstack.com/docs/app-automate/appium
-https://www.browserstack.com/docs/app-automate/appium/getting-started/java/integrate-your-tests
-https://www.browserstack.com/docs/app-automate/appium/getting-started/java/local-testing
-https://www.browserstack.com/docs/app-automate/appium/getting-started/java/parallelize-tests
-https://www.browserstack.com/docs/app-automate/appium/sdk-benefits
-https://www.browserstack.com/docs/app-automate/appium/how-sdk-works
-https://www.browserstack.com/docs/app-automate/appium/sdk-params
-https://www.browserstack.com/docs/app-automate/appium/sdk-faqs
-https://www.browserstack.com/docs/app-automate/appium/set-up-test-env
-https://www.browserstack.com/docs/app-automate/appium/set-up-test-env/upload-and-manage-apps
-https://www.browserstack.com/docs/app-automate/appium/upload-app-using-public-url