feat: enhance URL comparison logic and Chrome debugging configuration

- Added a new function to ensure URLs have a scheme, defaulting to 'http://' if missing.
- Integrated tldextract to normalize URLs by extracting domain parts and handling 'www' subdomains.
- Updated the compare_urls function to include logging for better traceability during URL comparisons.
- Added tldextract to requirements.txt to support the new functionality.
- Updated the AWS manager with a new AMI ID for the specified resolution.
- Modified Chrome desktop launcher to include --remote-debugging-port=1337 for GUI debugging support.

These changes improve the robustness of URL handling and enable consistent Chrome debugging capabilities without altering existing logic.

desktop_env/evaluators/metrics/utils.py

@@ -10,7 +10,7 @@ import zipfile
 #import pandas as pd
 from typing import Any, TypeVar, Union, Iterable, Optional, Callable
 from typing import Dict, List, Set, Match, Tuple, Pattern
-from urllib.parse import urlparse, urlunparse
+from urllib.parse import urlparse, urlunparse, ParseResult
 
 import formulas
 import lxml.cssselect
@@ -29,6 +29,7 @@ from openpyxl.worksheet.cell_range import MultiCellRange, CellRange
 from openpyxl.worksheet.dimensions import DimensionHolder
 from openpyxl.worksheet.filters import AutoFilter, SortState
 from openpyxl.worksheet.worksheet import Worksheet
+import tldextract
 
 V = TypeVar("Value")
 
@@ -699,29 +700,59 @@ def are_lists_equal(list1, list2, comparison_func):
     return True
 
 
-def compare_urls(url1, url2):
+def compare_urls(url1, url2, full=True):
     if url1 is None or url2 is None:
         return url1 == url2
+    
+    logger.info(f"compare_urls. url1: {url1}; url2: {url2}")
+
+    def parse_with_default_scheme(url):
+        """
+        Ensure the URL has a scheme. If not, prepend 'http://'
+        so it parses as host + path instead of just a path.
+        """
+        # Regex to check if URL has scheme like 'http://', 'https://', etc.
+        if not re.match(r'^[a-zA-Z][a-zA-Z0-9+\-.]*://', url):
+            url = f"http://{url}"
+        return urlparse(url)
 
     def normalize_url(url):
-        # Parse the URL
-        parsed_url = urlparse(url)
+        # Parse the URL; if no scheme is present, assume 'http'
+        parsed_url = parse_with_default_scheme(url)
+        scheme = parsed_url.scheme.lower()
 
-        # If no scheme is present, assume 'http'
-        scheme = parsed_url.scheme if parsed_url.scheme else 'http'
+        # Extract the domain parts using tldextract
+        extracted = tldextract.extract(parsed_url.netloc.lower())
+        # e.g., extracted = TLDExtractResult(subdomain='www', domain='airbnb', suffix='com.sg')
+        
+        # Drop 'www' if it's the only subdomain
+        subdomain = extracted.subdomain
+        if subdomain == 'www':
+            subdomain = ''
 
-        # Lowercase the scheme and netloc, remove 'www.', and handle trailing slash
-        normalized_netloc = parsed_url.netloc.lower().replace("www.", "")
+        # Instead of using the suffix (e.g., 'com', 'com.sg'), ignore it completely
+        # so that both 'airbnb.com' and 'airbnb.com.sg' become just 'airbnb' or 'www.airbnb'
+        if subdomain:
+            normalized_netloc = f"{subdomain}.{extracted.domain}"
+        else:
+            normalized_netloc = extracted.domain
+
+        # Handle trailing slash in the path
         normalized_path = parsed_url.path if parsed_url.path != '/' else ''
 
-        # Reassemble the URL with normalized components
-        normalized_parsed_url = parsed_url._replace(scheme=scheme.lower(), netloc=normalized_netloc,
-                                                    path=normalized_path)
-        normalized_url = urlunparse(normalized_parsed_url)
+        # Reassemble the URL with the normalized components
+        normalized_parsed_url = ParseResult(
+            scheme=scheme.lower(),
+            netloc=normalized_netloc,
+            path=normalized_path,
+            params=parsed_url.params if full else '',       # Keep the params
+            query=parsed_url.query if full else '',         # Keep the query string
+            fragment=parsed_url.fragment if full else '',   # Keep the fragment
+        )
+        return urlunparse(normalized_parsed_url)
 
-        return normalized_url
-
-    # Normalize both URLs for comparison
+    logger.info(f"After normalization. url1: {normalize_url(url1)}; url2: {normalize_url(url2)}")
+    # Normalize both URLs
     norm_url1 = normalize_url(url1)
     norm_url2 = normalize_url(url2)
 

desktop_env/providers/aws/manager.py

@@ -37,7 +37,7 @@ DEFAULT_REGION = "us-east-1"
 # todo: public the AMI images
 IMAGE_ID_MAP = {
     "us-east-1": {
-        (1920, 1080): "ami-09138bff939f82bd8"
+        (1920, 1080): "ami-0d23263edb96951d8"
     },
     "ap-east-1": {
         (1920, 1080): "ami-0c092a5b8be4116f5"

requirements.txt

@@ -62,3 +62,4 @@ azure-mgmt-network
 docker
 loguru
 dotenv
+tldextract