datamule 1.5.3__tar.gz → 1.5.5__tar.gz

{datamule-1.5.3 → datamule-1.5.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.5.3
+Version: 1.5.5
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.5.3 → datamule-1.5.5}/datamule/sec/submissions/monitor.py

@@ -7,7 +7,7 @@ import asyncio
 from ..utils import headers, PreciseRateLimiter
 from .eftsquery import EFTSQuery
 import aiohttp
-
+from zoneinfo import ZoneInfo 
 
 async def poll_rss(limiter):
     base_url = 'https://www.sec.gov/cgi-bin/browse-edgar?count=100&action=getcurrent&output=rss'
@@ -77,15 +77,22 @@ class Monitor():
         )
 
     async def _async_monitor_submissions(self, data_callback=None, interval_callback=None,
-                            polling_interval=1000, quiet=True, start_date=None,
-                            validation_interval=60000):
+                        polling_interval=1000, quiet=True, start_date=None,
+                        validation_interval=60000):
         """
         Async implementation of monitor_submissions.
+        Either polling_interval or validation_interval (or both) must be specified.
+        If polling_interval is None, only EFTS validation will be performed.
+        If validation_interval is None, only RSS polling will be performed.
         """
 
+        # Validate that at least one interval is specified
+        if polling_interval is None and validation_interval is None:
+            raise ValueError("At least one of polling_interval or validation_interval must be specified")
+
         # Backfill if start_date is provided
         if start_date is not None:
-            today_date = datetime.now().date().strftime('%Y-%m-%d')
+            today_date = datetime.now(ZoneInfo("America/New_York")).strftime('%Y-%m-%d')
             if not quiet:
                 print(f"Backfilling from {start_date} to {today_date}")
 
@@ -100,26 +107,35 @@ class Monitor():
             if new_hits and data_callback:
                 data_callback(new_hits)
 
-        last_polling_time = time.time()
-        last_validation_time = last_polling_time
-        current_time = last_polling_time
-
+        # Initialize timing variables
+        current_time = time.time()
+        last_polling_time = current_time
+        last_validation_time = current_time
+        
+        # Determine which operations to perform
+        do_polling = polling_interval is not None
+        do_validation = validation_interval is not None
+        
         while True:
-            # RSS polling
-            if not quiet:
-                print(f"Polling RSS feed")
-            results = await poll_rss(self.ratelimiters['sec.gov'])
-            new_results = self._filter_new_accessions(results)
-            if new_results:
+            current_time = time.time()
+            
+            # RSS polling (if enabled)
+            if do_polling and (current_time - last_polling_time) >= polling_interval/1000:
                 if not quiet:
-                    print(f"Found {len(new_results)} new submissions via RSS")
-                if data_callback:
-                    data_callback(new_results)
+                    print(f"Polling RSS feed")
+                results = await poll_rss(self.ratelimiters['sec.gov'])
+                new_results = self._filter_new_accessions(results)
+                if new_results:
+                    if not quiet:
+                        print(f"Found {len(new_results)} new submissions via RSS")
+                    if data_callback:
+                        data_callback(new_results)
+                last_polling_time = current_time
             
-            # EFTS validation
-            if validation_interval and (current_time - last_validation_time) >= validation_interval/1000:
+            # EFTS validation (if enabled)
+            if do_validation and (current_time - last_validation_time) >= validation_interval/1000:
                 # Get submissions from the last 24 hours for validation
-                today_date = datetime.now().strftime('%Y-%m-%d')
+                today_date = datetime.now(ZoneInfo("America/New_York")).strftime('%Y-%m-%d')
                 if not quiet:
                     print(f"Validating submissions from {today_date}")
 
@@ -134,19 +150,23 @@ class Monitor():
                         print(f"Found {len(new_hits)} new submissions via EFTS validation")
                     if data_callback:
                         data_callback(new_hits)
-                last_polling_time = time.time()
                 last_validation_time = current_time
             
             # Interval callback
             if interval_callback:
                 interval_callback()
 
-            next_poll_time = last_polling_time + (polling_interval / 1000)
+            # Calculate next wake-up time
+            next_times = []
+            if do_polling:
+                next_times.append(last_polling_time + (polling_interval / 1000))
+            if do_validation:
+                next_times.append(last_validation_time + (validation_interval / 1000))
+            
+            next_wake_time = min(next_times)
             current_time = time.time()
-            time_to_sleep = max(0, next_poll_time - current_time)
+            time_to_sleep = max(0, next_wake_time - current_time)
             await asyncio.sleep(time_to_sleep)
-            last_polling_time = next_poll_time
-
 
     def monitor_submissions(self, data_callback=None, interval_callback=None,
                             polling_interval=1000, quiet=True, start_date=None,

{datamule-1.5.3 → datamule-1.5.5}/datamule/seclibrary/downloader.py

@@ -98,6 +98,7 @@ class Downloader:
             filename, content = item
             output_path = os.path.join(self.output_dir, filename.split('.')[0] + '.tar')
             write_sgml_file_to_tar(output_path, bytes_content=content, filter_document_types=self.keep_document_types, keep_filtered_metadata=self.keep_filtered_metadata,standardize_metadata=self.standardize_metadata)
+
             self.pbar.update(1)
 
         def _processing_worker(self):
@@ -296,6 +297,64 @@ class Downloader:
             self.loop.call_soon_threadsafe(self.loop.stop)
 
 
+    
+    def download_files_using_filename(self, filenames, output_dir="downloads", keep_document_types=[], keep_filtered_metadata=False, standardize_metadata=True):
+        """
+        Download and process SEC filings using specific filenames.
+        
+        Parameters:
+        - filenames: List of specific filenames to download (e.g., ['000091205797006494.sgml', '000100704297000007.sgml.zst'])
+        - output_dir: Directory to save downloaded files
+        - keep_document_types: List of document types to keep (e.g., ['10-K', 'EX-10.1'])
+        - keep_filtered_metadata: Whether to keep metadata for filtered documents
+        - standardize_metadata: Whether to standardize metadata format
+        """
+        if self.api_key is None:
+            raise ValueError("No API key found. Please set DATAMULE_API_KEY environment variable or provide api_key in constructor")
+        
+        if not filenames:
+            raise ValueError("No filenames provided")
+        
+        if not isinstance(filenames, (list, tuple)):
+            filenames = [filenames]
+        
+        # Validate filenames format
+        for filename in filenames:
+            if not isinstance(filename, str):
+                raise ValueError(f"Invalid filename type: {type(filename)}. Expected string.")
+            if not (filename.endswith('.sgml') or filename.endswith('.sgml.zst')):
+                raise ValueError(f"Invalid filename format: {filename}. Expected .sgml or .sgml.zst extension.")
+        
+        # Generate URLs directly from filenames
+        print(f"Generating URLs for {len(filenames)} files...")
+        urls = []
+        for filename in filenames:
+            url = f"{self.BASE_URL}{filename}"
+            urls.append(url)
+        
+        # Remove duplicates while preserving order
+        seen = set()
+        urls = [url for url in urls if not (url in seen or seen.add(url))]
+        
+        print(f"Downloading {len(urls)} files...")
+        
+        # Process the batch asynchronously using existing infrastructure
+        start_time = time.time()
+        
+        asyncio.run(self.process_batch(
+            urls, 
+            output_dir, 
+            keep_document_types=keep_document_types, 
+            keep_filtered_metadata=keep_filtered_metadata, 
+            standardize_metadata=standardize_metadata
+        ))
+        
+        # Calculate and display performance metrics
+        elapsed_time = time.time() - start_time
+        print(f"\nProcessing completed in {elapsed_time:.2f} seconds")
+        print(f"Processing speed: {len(urls)/elapsed_time:.2f} files/second")
+
+
 def download(submission_type=None, cik=None, filing_date=None, api_key=None, output_dir="downloads", accession_numbers=None, keep_document_types=[],keep_filtered_metadata=False,standardize_metadata=True):
     """
     Query SEC filings and download/process them.
@@ -325,4 +384,27 @@ def download(submission_type=None, cik=None, filing_date=None, api_key=None, out
         keep_document_types=keep_document_types,
         keep_filtered_metadata=keep_filtered_metadata,
         standardize_metadata=standardize_metadata
+    )
+
+def download_files_using_filename(filenames, api_key=None, output_dir="downloads", keep_document_types=[], keep_filtered_metadata=False, standardize_metadata=True):
+    """
+    Download and process SEC filings using specific filenames.
+    
+    Parameters:
+    - filenames: List of specific filenames to download (e.g., ['000091205797006494.sgml', '000100704297000007.sgml.zst'])
+    - api_key: API key for datamule service (optional if DATAMULE_API_KEY env var is set)
+    - output_dir: Directory to save downloaded files
+    - keep_document_types: List of document types to keep (e.g., ['10-K', 'EX-10.1'])
+    - keep_filtered_metadata: Whether to keep metadata for filtered documents
+    - standardize_metadata: Whether to standardize metadata format
+    """
+    downloader = Downloader(api_key=api_key)
+    downloader.QUEUE_SIZE = 1
+    downloader.MAX_CONCURRENT_DOWNLOADS = 1
+    downloader.download_files_using_filename(
+        filenames=filenames,
+        output_dir=output_dir,
+        keep_document_types=keep_document_types,
+        keep_filtered_metadata=keep_filtered_metadata,
+        standardize_metadata=standardize_metadata
     )

{datamule-1.5.3 → datamule-1.5.5}/datamule/submission.py

@@ -3,6 +3,7 @@ import json
 from .document.document import Document
 from secsgml import parse_sgml_content_into_memory
 from secsgml.utils import bytes_to_str
+from secsgml.parse_sgml import transform_metadata_string
 import tarfile
 import shutil
 import zstandard as zstd
@@ -86,6 +87,10 @@ class Submission:
         if sgml_content is not None:
             self.path = None
             metadata, raw_documents = parse_sgml_content_into_memory(sgml_content)
+
+            # standardize metadata
+            metadata = transform_metadata_string(metadata)
+
             self.metadata = Document(type='submission_metadata', content=metadata, extension='.json',filing_date=None,accession=None,path=None)
             # code dupe
             self.accession = self.metadata.content['accession-number']
@@ -123,6 +128,9 @@ class Submission:
                 metadata_path = self.path / 'metadata.json'
                 with metadata_path.open('r') as f:
                     metadata = json.load(f) 
+
+            # standardize metadata
+            metadata = transform_metadata_string(metadata)
             self.metadata = Document(type='submission_metadata', content=metadata, extension='.json',filing_date=None,accession=None,path=metadata_path)
             self.accession = self.metadata.content['accession-number']
             self.filing_date= f"{self.metadata.content['filing-date'][:4]}-{self.metadata.content['filing-date'][4:6]}-{self.metadata.content['filing-date'][6:8]}"

{datamule-1.5.3 → datamule-1.5.5}/datamule.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 1.5.3
+Version: 1.5.5
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman

{datamule-1.5.3 → datamule-1.5.5}/setup.py

@@ -32,7 +32,7 @@ if not os.path.exists(file_path):
 setup(
     name="datamule",
     author="John Friedman",
-    version="1.5.3",
+    version="1.5.5",
     description="Work with SEC submissions at scale.",
     packages=find_packages(include=['datamule', 'datamule.*']),
     url="https://github.com/john-friedman/datamule-python",