Add argparse CLIs for parser and validator

docs/getting-started.md

@@ -85,15 +85,15 @@ Once you have your DAR file, you can use the `dar_parser.py` tool to read and an
 
 ### Step 1: Parse the DAR File
 
-Run the `dar_parser.py` script to parse the DAR file and extract key information.
+Run the `dar_parser.py` script with the `--summary` flag to parse the DAR file and display a summary.
 
 ```bash
-python tools/dar_parser.py
+python tools/dar_parser.py --summary output.dar
 ```
 
 ### Step 2: View the Parsed Data
 
-The script will prompt you for the path to your DAR file and output a summary, including:
+The script will output a summary that includes:
 - Number of renders captured.
 - Summary of scraping results.
 - Number of HTTP request entries.
@@ -110,6 +110,14 @@ parser = DARParser('output.dar')
 parser.print_dar_summary()
 ```
 
+### Step 3: Validate the DAR File
+
+Use the validator script to ensure the file conforms to the DAR schema:
+
+```bash
+python tools/validators/dar_validator.py --validate output.dar
+```
+
 ## Integrating DAR in Your Scraping Workflow
 
 DAR is especially useful when integrated into web scraping workflows, providing insights into how pages are loaded and data is collected. Here’s how you can incorporate DAR into your existing scraping setup.

docs/usage-examples.md

@@ -46,7 +46,7 @@ Parsing DAR files is straightforward using the `dar_parser.py` script. This pars
 2. **Parse the DAR file using the `dar_parser.py` script**:
 
     ```bash
-    python tools/dar_parser.py
+    python tools/dar_parser.py --summary sample_output.dar
     ```
 
 3. **View the parsed data**: The script will output a summary of the DAR file, including the number of renders, summary of results, and number of request entries.
@@ -122,6 +122,14 @@ parser = DARParser('session.dar')
 parser.print_dar_summary()
 ```
 
+## Validating a DAR File
+
+Before using a DAR file in production, you can validate it against the schema:
+
+```bash
+python tools/validators/dar_validator.py --validate session.dar
+```
+
 ## Error Handling and Metrics
 
 DAR files include detailed error logs and performance metrics that are invaluable for debugging and optimizing your scraping processes. These insights allow you to fine-tune your approach and ensure data quality.

tools/dar_parser.py

@@ -8,6 +8,7 @@
 """
 
 import json
+import argparse
 
 
 class DARParser:
@@ -89,12 +90,31 @@ def print_dar_summary(self):
         print(f"Number of Request Entries: {len(self.get_request_entries())}")
 
 
+def main():
+    arg_parser = argparse.ArgumentParser(
+        description="Parse a DAR file and display information"
+    )
+    arg_parser.add_argument(
+        "file",
+        help="Path to the DAR file to parse",
+    )
+    arg_parser.add_argument(
+        "--summary",
+        action="store_true",
+        help="Print a summary of the DAR file",
+    )
+
+    args = arg_parser.parse_args()
+
+    parser = DARParser(args.file)
+
+    if args.summary:
+        parser.print_dar_summary()
+
+
 if __name__ == "__main__":
-    # Example usage
-    file_path = input("Enter the path to your DAR file: ")
     try:
-        parser = DARParser(file_path)
-        parser.print_dar_summary()
+        main()
     except Exception as e:
         print(f"An error occurred: {e}")
 

tools/validators/dar_validator.py

@@ -8,7 +8,7 @@
 """
 
 import json
-import sys
+import argparse
 
 
 class DARValidator:
@@ -120,15 +120,30 @@ def print_validation_report(self):
             print("DAR file is valid and conforms to the schema.")
 
 
-if __name__ == "__main__":
-    if len(sys.argv) != 2:
-        print("Usage: python dar_validator.py <path_to_dar_file>")
-        sys.exit(1)
+def main():
+    arg_parser = argparse.ArgumentParser(
+        description="Validate a DAR file against the schema"
+    )
+    arg_parser.add_argument(
+        "file",
+        help="Path to the DAR file to validate",
+    )
+    arg_parser.add_argument(
+        "--validate",
+        action="store_true",
+        help="Run validation and print a report",
+    )
+
+    args = arg_parser.parse_args()
+
+    validator = DARValidator(args.file)
+    if args.validate:
+        validator.print_validation_report()
+
 
-    file_path = sys.argv[1]
+if __name__ == "__main__":
     try:
-        validator = DARValidator(file_path)
-        validator.print_validation_report()
+        main()
     except Exception as e:
         print(f"An error occurred: {e}")