fixed gzip decompression and index name for reports

README.md

@@ -39,8 +39,6 @@ czds [-h] [-u USERNAME] [-p PASSWORD] [-z] [-c CONCURRENCY] [-d] [-k] [-r] [-s]
 ###### Zone Options
 | `-z`, `--zones`       | Download zone files                          |                   |
 | `-c`, `--concurrency` | Number of concurrent downloads               | `3`               |
-| `-d`, `--decompress`  | Decompress zone files after download         |                   |
-| `-k`, `--keep`        | Keep original gzip files after decompression |                   |
 
 ###### Report Options
 | `-r`, `--report`      | Download the zone stats report               |                   |

czds/__init__.py

@@ -4,8 +4,7 @@
 
 from .client import CZDS
 
-
+__version__ = '1.3.8'
-__version__ = '1.3.2'
 __author__  = 'acidvegas'
 __email__   = 'acid.vegas@acid.vegas'
 __github__  = 'https://github.com/acidvegas/czds'

czds/__main__.py

@@ -10,11 +10,6 @@ import os
 
 from .client import CZDS
 
-from dotenv import load_dotenv
-
-
-load_dotenv()
-
 
 async def main():
     '''Entry point for the command line interface'''

czds/client.py

@@ -6,6 +6,8 @@ import asyncio
 import json
 import logging
 import os
+import csv
+import io
 
 try:
     import aiohttp
@@ -44,8 +46,21 @@ class CZDS:
         self.username = username
         self.password = password
 
-        # Set the session with longer timeouts
+        # Configure TCP keepalive
-        self.session = aiohttp.ClientSession(timeout=aiohttp.ClientTimeout(total=None, connect=60, sock_connect=60, sock_read=60))
+        connector = aiohttp.TCPConnector(
+            keepalive_timeout=300,     # Keep connections alive for 5 minutes
+            force_close=False,         # Don't force close connections
+            enable_cleanup_closed=True, # Cleanup closed connections
+            ttl_dns_cache=300,         # Cache DNS results for 5 minutes
+        )
+
+        # Set the session with longer timeouts and keepalive
+        self.session = aiohttp.ClientSession(
+            connector=connector,
+            timeout=aiohttp.ClientTimeout(total=None, connect=60, sock_connect=60, sock_read=None),
+            headers={'Connection': 'keep-alive'},
+            raise_for_status=True
+        )
 
         # Placeholder for the headers after authentication
         self.headers = None
@@ -125,15 +140,12 @@ class CZDS:
         Downloads the zone report stats from the API and scrubs the report for privacy
         
         :param filepath: Filepath to save the scrubbed report
-        :param scrub: Whether to scrub the username from the report
         :param format: Output format ('csv' or 'json')
         '''
-
         logging.info('Downloading zone stats report')
 
         # Send the request to the API
         async with self.session.get('https://czds-api.icann.org/czds/requests/report', headers=self.headers) as response:
-            # Check if the request was successful
             if response.status != 200:
                 raise Exception(f'Failed to download the zone stats report: {response.status} {await response.text()}')
 
@@ -144,9 +156,21 @@ class CZDS:
             content = content.replace(self.username, 'nobody@no.name')
             logging.debug('Scrubbed username from report')
 
-            # Convert the report to JSON format if requested (default is CSV)
+            # Convert the report to JSON format if requested
             if format.lower() == 'json':
-                content = json.dumps(content, indent=4)
+                # Parse CSV content
+                csv_reader = csv.DictReader(io.StringIO(content))
+                
+                # Convert to list of dicts with formatted keys
+                json_data = []
+                for row in csv_reader:
+                    formatted_row = {
+                        key.lower().replace(' ', '_'): value 
+                        for key, value in row.items()
+                    }
+                    json_data.append(formatted_row)
+                
+                content = json.dumps(json_data, indent=4)
                 logging.debug('Converted report to JSON format')
 
             # Save the report to a file if a filepath is provided
@@ -169,9 +193,16 @@ class CZDS:
         
         async def _download():
             tld_name    = url.split('/')[-1].split('.')[0] # Extract TLD from URL
-            max_retries = 10                               # Maximum number of retries for failed downloads
+            max_retries = 20                               # Maximum number of retries for failed downloads
             retry_delay = 5                                # Delay between retries in seconds
-            timeout     = aiohttp.ClientTimeout(total=120) # Timeout for the download
+            
+            # Headers for better connection stability
+            download_headers = {
+                **self.headers,
+                'Connection': 'keep-alive',
+                'Keep-Alive': 'timeout=600', # 10 minutes
+                'Accept-Encoding': 'gzip'
+            }
 
             # Start the attempt loop
             for attempt in range(max_retries):
@@ -179,7 +210,7 @@ class CZDS:
                     logging.info(f'Starting download of {tld_name} zone file{" (attempt " + str(attempt + 1) + ")" if attempt > 0 else ""}')
 
                     # Send the request to the API
-                    async with self.session.get(url, headers=self.headers, timeout=timeout) as response:
+                    async with self.session.get(url, headers=download_headers) as response:
                         # Check if the request was successful
                         if response.status != 200:
                             logging.error(f'Failed to download {tld_name}: {response.status} {await response.text()}')
@@ -219,7 +250,7 @@ class CZDS:
                                         await file.write(chunk)
                                         total_size += len(chunk)
                                         pbar.update(len(chunk))
-                                except (asyncio.TimeoutError, aiohttp.ClientError) as e:
+                                except Exception as e:
                                     logging.error(f'Connection error while downloading {tld_name}: {str(e)}')
                                     if attempt + 1 < max_retries:
                                         logging.info(f'Retrying {tld_name} in {retry_delay} seconds...')
@@ -246,7 +277,7 @@ class CZDS:
 
                         return filepath
 
-                except (aiohttp.ClientError, asyncio.TimeoutError) as e:
+                except Exception as e:
                     if attempt + 1 >= max_retries:
                         logging.error(f'Failed to download {tld_name} after {max_retries} attempts: {str(e)}')
                         if 'filepath' in locals() and os.path.exists(filepath):
@@ -255,12 +286,6 @@ class CZDS:
                     logging.warning(f'Download attempt {attempt + 1} failed for {tld_name}: {str(e)}')
                     await asyncio.sleep(retry_delay)
 
-                except Exception as e:
-                    logging.error(f'Error downloading {tld_name}: {str(e)}')
-                    if 'filepath' in locals() and os.path.exists(filepath):
-                        os.remove(filepath)
-                    raise
-
         async with semaphore:
             return await _download()
 

czds/utils.py

@@ -2,6 +2,7 @@
 # ICANN API for the Centralized Zones Data Service - developed by acidvegas (https://git.acid.vegas/czds)
 # czds/utils.py
 
+import asyncio
 import gzip
 import logging
 import os
@@ -24,43 +25,30 @@ async def gzip_decompress(filepath: str, cleanup: bool = True):
     :param filepath: Path to the gzip file
     :param cleanup: Whether to remove the original gzip file after decompressions
     '''
-
-    # Get the original size of the file
     original_size = os.path.getsize(filepath)
+    output_path = filepath[:-3]
     
     logging.debug(f'Decompressing {filepath} ({humanize_bytes(original_size)})...')
 
-    # Remove the .gz extension
+    # Use a large chunk size (256MB) for maximum throughput
-    output_path = filepath[:-3]
+    chunk_size = 256 * 1024 * 1024
 
-    # Set the chunk size to 25MB
+    # Run the actual decompression in a thread pool to prevent blocking
-    chunk_size = 25 * 1024 * 1024
-
-    # Create progress bar for decompression
     with tqdm(total=original_size, unit='B', unit_scale=True, desc=f'Decompressing {os.path.basename(filepath)}', leave=False) as pbar:
-        # Decompress the file
-        with gzip.open(filepath, 'rb') as gz:
         async with aiofiles.open(output_path, 'wb') as f_out:
+            # Run gzip decompression in thread pool since it's CPU-bound
+            loop = asyncio.get_event_loop()
+            with gzip.open(filepath, 'rb') as gz:
                 while True:
-                    # Read the next chunk
+                    chunk = await loop.run_in_executor(None, gz.read, chunk_size)
-                    chunk = gz.read(chunk_size)
-
-                    # If the chunk is empty, break
                     if not chunk:
                         break
-
-                    # Write the chunk to the output file
                     await f_out.write(chunk)
-
-                    # Update the progress bar
                     pbar.update(len(chunk))
 
-    # Get the decompressed size of the file
     decompressed_size = os.path.getsize(output_path)
-
     logging.debug(f'Decompressed {filepath} ({humanize_bytes(decompressed_size)})')
 
-    # If the cleanup flag is set, remove the original gzip file
     if cleanup:
         os.remove(filepath)
         logging.debug(f'Removed original gzip file: {filepath}')

setup.py

@@ -11,7 +11,7 @@ with open('README.md', 'r', encoding='utf-8') as fh:
 
 setup(
 	name='czds-api',
-	version='1.3.2',
+	version='1.3.8',
 	author='acidvegas',
 	author_email='acid.vegas@acid.vegas',
 	description='ICANN API for the Centralized Zones Data Service',