datamule 2.3.0__py3-none-any.whl → 2.3.3__py3-none-any.whl

datamule/__init__.py

@@ -8,6 +8,7 @@ from .index import Index
 from .package_updater import PackageUpdater
 from .utils.format_accession import format_accession
 from .utils.construct_submissions_data import construct_submissions_data
+from .book.book import Book
 
 
 # Keep the notebook environment setup

datamule/book/book.py

@@ -0,0 +1,13 @@
+from .s3transfer import s3_transfer
+
+class Book:
+    def __init__(self):
+        pass
+
+    def s3_transfer(self, datamule_bucket, s3_credentials, max_workers=4, errors_json_filename='s3_transfer_errors.json', retry_errors=3,
+                    force_daily=True, cik=None, submission_type=None, filing_date=None, datamule_api_key=None,accession=None):
+        
+        s3_transfer(datamule_bucket=datamule_bucket, s3_credentials=s3_credentials, max_workers=max_workers, 
+                          errors_json_filename=errors_json_filename, retry_errors=retry_errors,
+                          force_daily=force_daily, cik=cik, submission_type=submission_type, 
+                          filing_date=filing_date, datamule_api_key=datamule_api_key,accession_number=accession)

datamule/book/s3transfer.py

@@ -0,0 +1,264 @@
+import asyncio
+import aiohttp
+import aioboto3
+import ssl
+import time
+import json
+from datetime import datetime, timedelta
+from urllib.parse import urlparse
+from tqdm import tqdm
+import logging
+from ..sheet import Sheet
+from ..utils.format_accession import format_accession
+
+# Set up logging
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s'
+)
+logger = logging.getLogger(__name__)
+
+
+def generate_date_range(start_date_str, end_date_str):
+    start_date = datetime.strptime(start_date_str, '%Y-%m-%d')
+    end_date = datetime.strptime(end_date_str, '%Y-%m-%d')
+    
+    dates = []
+    current_date = start_date
+    
+    while current_date <= end_date:
+        dates.append(current_date.strftime('%Y-%m-%d'))
+        current_date += timedelta(days=1)
+    
+    return dates
+
+
+def get_filings_sgml_r2_urls(submission_type=None, cik=None, datamule_api_key=None, filing_date=None,accession_number=None):
+    datamule_bucket_endpoint = 'https://sec-library.datamule.xyz/'
+    sheet = Sheet('s3transfer')
+    submissions = sheet.get_submissions(distinct=True, quiet=False, api_key=datamule_api_key,
+                                    submission_type=submission_type, cik=cik, columns=['accessionNumber'], filing_date=filing_date,
+                                    accession_number=accession_number)
+    
+    accessions = [format_accession(sub['accessionNumber'], 'no-dash') for sub in submissions]
+    
+    urls = [f"{datamule_bucket_endpoint}{accession}.sgml" for accession in accessions]
+
+    return urls
+
+
+class AsyncS3Transfer:
+    def __init__(self, s3_credentials, max_workers=100, chunk_size=2*1024*1024):
+        self.s3_credentials = s3_credentials
+        self.max_workers = max_workers
+        self.chunk_size = chunk_size
+        
+    async def __aenter__(self):
+        # Create aiohttp session with optimized connector
+        connector = aiohttp.TCPConnector(
+            limit=self.max_workers,
+            force_close=False,
+            ssl=ssl.create_default_context(),
+            ttl_dns_cache=300,
+            keepalive_timeout=60
+        )
+        
+        self.session = aiohttp.ClientSession(
+            connector=connector,
+            timeout=aiohttp.ClientTimeout(total=600),
+            headers={
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
+                'Connection': 'keep-alive',
+                'Accept-Encoding': 'gzip, deflate, br'
+            }
+        )
+        
+        # Create async boto3 client
+        if self.s3_credentials['s3_provider'] == 'aws':
+            session = aioboto3.Session()
+            self.s3_client = await session.client(
+                's3',
+                aws_access_key_id=self.s3_credentials['aws_access_key_id'],
+                aws_secret_access_key=self.s3_credentials['aws_secret_access_key'],
+                region_name=self.s3_credentials['region_name']
+            ).__aenter__()
+        else:
+            raise ValueError("S3 Provider not supported yet. Please use another provider or email johnfriedman@datamule.xyz to add support.")
+            
+        return self
+    
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        if hasattr(self, 'session') and self.session:
+            await self.session.close()
+        if hasattr(self, 's3_client') and self.s3_client:
+            await self.s3_client.__aexit__(exc_type, exc_val, exc_tb)
+
+    async def transfer_single_file(self, semaphore, url, retry_errors=3):
+        """Transfer a single file with retry logic and preserve metadata"""
+        async with semaphore:
+            filename = urlparse(url).path.split('/')[-1]
+            s3_key = filename
+            bucket_name = self.s3_credentials['bucket_name']
+            
+            last_error = None
+            
+            for attempt in range(retry_errors + 1):
+                try:
+                    async with self.session.get(url) as response:
+                        if response.status == 200:
+                            # Capture source metadata from response headers
+                            content_length = response.headers.get('Content-Length')
+                            size_bytes = int(content_length) if content_length else 0
+                            content_type = response.headers.get('Content-Type', 'application/octet-stream')
+                            last_modified = response.headers.get('Last-Modified')
+                            
+                            # Read response content
+                            content = await response.read()
+                            
+                            # Prepare S3 upload parameters with preserved metadata
+                            upload_params = {
+                                'Bucket': bucket_name,
+                                'Key': s3_key,
+                                'Body': content,
+                                'ContentType': content_type,
+                                'StorageClass': 'STANDARD',
+                                'Metadata': {
+                                    'source-url': url,
+                                    'original-size': str(size_bytes),
+                                    'transfer-date': datetime.utcnow().isoformat()
+                                }
+                            }
+                            
+                            # Add last modified if available
+                            if last_modified:
+                                upload_params['Metadata']['original-last-modified'] = last_modified
+                            
+                            # Upload to S3 with metadata
+                            await self.s3_client.put_object(**upload_params)
+                            
+                            return {
+                                'success': True,
+                                'url': url,
+                                'message': f"Copied: {url} -> s3://{bucket_name}/{s3_key}",
+                                'size_bytes': size_bytes,
+                                's3_key': s3_key,
+                                'content_type': content_type,
+                                'last_modified': last_modified
+                            }
+                        else:
+                            raise aiohttp.ClientResponseError(
+                                request_info=response.request_info,
+                                history=response.history,
+                                status=response.status
+                            )
+                                
+                except Exception as e:
+                    print(e)
+                    last_error = e
+                    if attempt < retry_errors:
+                        await asyncio.sleep(2 ** attempt)  # Exponential backoff
+            
+            # All attempts failed
+            return {
+                'success': False,
+                'url': url,
+                'error': str(last_error),
+                'message': f"Failed to copy {url} after {retry_errors + 1} attempts: {last_error}",
+                'size_bytes': 0
+            }
+
+    async def transfer_batch(self, urls, retry_errors=3):
+        """Transfer multiple files concurrently"""
+        semaphore = asyncio.Semaphore(self.max_workers)
+        failed_files = []
+        total_bytes = 0
+        start_time = time.time()
+        
+        # Create tasks for all transfers
+        tasks = [
+            self.transfer_single_file(semaphore, url, retry_errors)
+            for url in urls
+        ]
+        
+        # Process with progress bar
+        with tqdm(total=len(urls), desc="Transferring files", unit="file") as pbar:
+            for coro in asyncio.as_completed(tasks):
+                result = await coro
+                
+                if result['success']:
+                    total_bytes += result.get('size_bytes', 0)
+                else:
+                    failed_files.append(result)
+                
+                # Update progress bar with total GB transferred
+                total_gb = total_bytes / (1024 ** 3)
+                pbar.set_postfix({'Total': f'{total_gb:.2f} GB'})
+                
+                pbar.update(1)
+        
+        return failed_files, total_bytes
+
+
+async def async_transfer_cached_urls_to_s3(urls, s3_credentials, max_workers=4, 
+                                         errors_json_filename='s3_transfer_errors.json', 
+                                         retry_errors=3):
+    """Async version of transfer_cached_urls_to_s3"""
+    failed_files = []
+    total_bytes = 0
+    
+    async with AsyncS3Transfer(s3_credentials, max_workers) as transfer:
+        failed_files, total_bytes = await transfer.transfer_batch(urls, retry_errors)
+        
+        # Save errors to JSON if filename provided and there are errors
+        if errors_json_filename and failed_files:
+            with open(errors_json_filename, 'w') as f:
+                json.dump(failed_files, f, indent=2)
+            print(f"Saved {len(failed_files)} errors to {errors_json_filename}")
+        
+        print(f"Transfer complete: {len(urls) - len(failed_files)}/{len(urls)} files successful")
+
+
+def transfer_cached_urls_to_s3(urls, s3_credentials, max_workers=4, errors_json_filename='s3_transfer_errors.json', retry_errors=3):
+    """Wrapper to run async transfer in sync context"""
+    asyncio.run(async_transfer_cached_urls_to_s3(urls, s3_credentials, max_workers, errors_json_filename, retry_errors))
+
+
+def s3_transfer(datamule_bucket, s3_credentials, max_workers=4, errors_json_filename='s3_transfer_errors.json', retry_errors=3,
+                force_daily=True, cik=None, submission_type=None, filing_date=None, datamule_api_key=None,accession_number=None):
+
+    if datamule_bucket == 'filings_sgml_r2':
+
+
+        if accession_number is not None:
+            if any(param is not None for param in [cik, submission_type, filing_date]):
+                raise ValueError('If accession is provided, then cik, type, and date must be None')
+            urls = get_filings_sgml_r2_urls(datamule_api_key=datamule_api_key,accession_number=accession_number)
+            transfer_cached_urls_to_s3(urls=urls, s3_credentials=s3_credentials, max_workers=max_workers, errors_json_filename=errors_json_filename, retry_errors=retry_errors)
+        else:
+            if not force_daily:
+                urls = get_filings_sgml_r2_urls(submission_type=submission_type, cik=cik, datamule_api_key=datamule_api_key,
+                                                filing_date=filing_date)
+                transfer_cached_urls_to_s3(urls=urls, s3_credentials=s3_credentials, max_workers=max_workers, errors_json_filename=errors_json_filename, retry_errors=retry_errors)
+            else:
+                if isinstance(filing_date, str):
+                    urls = get_filings_sgml_r2_urls(submission_type=submission_type, cik=cik, datamule_api_key=datamule_api_key,
+                                                filing_date=filing_date)
+                    transfer_cached_urls_to_s3(urls=urls, s3_credentials=s3_credentials, max_workers=max_workers, errors_json_filename=errors_json_filename, retry_errors=retry_errors)
+                elif isinstance(filing_date, list):
+                    for date in filing_date:
+                        print(f"Transferring {date}")
+                        urls = get_filings_sgml_r2_urls(submission_type=submission_type, cik=cik, datamule_api_key=datamule_api_key,
+                                                filing_date=date)
+                        transfer_cached_urls_to_s3(urls=urls, s3_credentials=s3_credentials, max_workers=max_workers, errors_json_filename=errors_json_filename, retry_errors=retry_errors)
+                elif isinstance(filing_date, tuple):
+                    dates = generate_date_range(filing_date[0], filing_date[1])
+                    for date in dates:
+                        print(f"Transferring {date}")
+                        urls = get_filings_sgml_r2_urls(submission_type=submission_type, cik=cik, datamule_api_key=datamule_api_key,
+                                                filing_date=date)
+                        transfer_cached_urls_to_s3(urls=urls, s3_credentials=s3_credentials, max_workers=max_workers, errors_json_filename=errors_json_filename, retry_errors=retry_errors) 
+                else:
+                    raise ValueError('filing_date can only be string, list, or (startdt,enddt)')
+            
+    else:
+        raise ValueError('Datamule S3 bucket not found.')

datamule/datamule/downloader.py

@@ -228,7 +228,7 @@ class Downloader:
                 headers = {
                     'Connection': 'keep-alive',
                     'Accept-Encoding': 'gzip, deflate, br',
-                    'Authorization': f'Bearer {api_key}'
+                    #'Authorization': f'Bearer {api_key}'
                 }
                 
                 async with session.get(url, headers=headers) as response:

datamule/document/document.py

@@ -1,10 +1,9 @@
 import json
 import csv
 import re
-from doc2dict import xml2dict, txt2dict, dict2dict
-from doc2dict.mapping import flatten_hierarchy
+from doc2dict import xml2dict, txt2dict
 from doc2dict import html2dict, visualize_dict, get_title, unnest_dict, pdf2dict, flatten_dict
-from ..mapping_dicts.txt_mapping_dicts import dict_10k, dict_10q, dict_8k, dict_13d, dict_13g
+from ..mapping_dicts.txt_mapping_dicts import dict_13d, dict_13g
 from ..mapping_dicts.xml_mapping_dicts import dict_345
 from ..mapping_dicts.html_mapping_dicts import *
 from pathlib import Path

datamule/mapping_dicts/html_mapping_dicts.py

@@ -7,7 +7,7 @@ dict_10q_html = dict_10k_html
 
 dict_8k_html = {
     ('signatures',r'^signatures?\.*$') : 0,
-    ('item',r'^item\s*(\d+\.\d+)') : 0,
+    ('item',r'^item\s*(\d+(?:\.\d+)?)') : 0,
 }
 
 dict_sd_html = {

{datamule-2.3.0.dist-info → datamule-2.3.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datamule
-Version: 2.3.0
+Version: 2.3.3
 Summary: Work with SEC submissions at scale.
 Home-page: https://github.com/john-friedman/datamule-python
 Author: John Friedman
@@ -20,4 +20,5 @@ Requires-Dist: secsgml
 Requires-Dist: websocket-client
 Requires-Dist: company-fundamentals
 Requires-Dist: flashtext
+Requires-Dist: aioboto3
 

{datamule-2.3.0.dist-info → datamule-2.3.3.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datamule/__init__.py,sha256=sY9rYx9z4LADjOLmwjL3BXssIzHs8MQM6gt9IWMS85U,1192
+datamule/__init__.py,sha256=gsWTW0emwGtM-KVtwe2OICVmW7ImvLvP0SORULTPe-Y,1220
 datamule/config.py,sha256=Y--CVv7JcgrjJkMOSLrvm2S8B9ost6RMSkGviP-MKtg,883
 datamule/datasets.py,sha256=-2_5kTRS3mxlkKbXwBg8aiistYljLYRnZjDLZNhV8bk,1867
 datamule/helper.py,sha256=KqhAmTMdvATEh3I-O4xLcAcrHB9zXQERBuwzue7zyQw,3674
@@ -8,14 +8,17 @@ datamule/portfolio.py,sha256=0-E1ZSEjJ8hba7HxF8oCrRneNuF_KKISOY6K4dRg0Cg,12282
 datamule/portfolio_compression_utils.py,sha256=8OPYEN5zAdV1FiTxgVN3S7cTKs99Elv74bwgoIJP4QY,12654
 datamule/sheet.py,sha256=KD7yAgSB8BE-Z4GDuH58IV-2DJ673nMcEsrCyJbeYp8,10707
 datamule/submission.py,sha256=phHmi9ScjWHtVLjEoEdAO7RieUSKN5gPr0onfg5R8wE,16139
+datamule/book/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+datamule/book/book.py,sha256=Vw33JHhmulNDWRN2AQpUQrf8wgVqqUYg5QJgbKhBNak,773
+datamule/book/s3transfer.py,sha256=4Zpw5daAH05u1dppv2ARXG_VSBIdsHnlEWC9xZgBfZM,12590
 datamule/data/listed_filer_metadata.csv,sha256=dT9fQ8AC5P1-Udf_UF0ZkdXJ88jNxJb_tuhi5YYL1rc,2426827
 datamule/datamule/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datamule/datamule/datamule_lookup.py,sha256=e8djAg-ctSyHiKk7BjbtgugZ3p8roUjzsym5z3AihUg,9468
 datamule/datamule/datamule_mysql_rds.py,sha256=Q6_h24-SNECWK60RnM6UQjUIp5dhJmfn3SSKzTITB3o,12317
-datamule/datamule/downloader.py,sha256=B22ULAuYzclxxVCH4DsLWUIyFUC5Iep-Hl1W3RgCfeg,18580
+datamule/datamule/downloader.py,sha256=Ss9mz0Jf5UAd-CZJ6oO96o9hN04xMQIF3-e1wahokdM,18581
 datamule/datamule/sec_connector.py,sha256=VwOaODpHoAWy8JIky6kLR1-orW_PB61RHw7pIGRpkow,3288
 datamule/document/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datamule/document/document.py,sha256=NrMqhY_u_X7gyvraxY0hzZEDJddqSJDgiHFzkaRTBVA,23102
+datamule/document/document.py,sha256=ooTbMpB_cBeONhtic8bNE4ISWltQIxQz4LLuXcGe8xc,23015
 datamule/document/tables/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datamule/document/tables/tables.py,sha256=uEMDYg7c4iHjVtIjNQgCgZOGp6j9aFWVB05agpVsNOI,5727
 datamule/document/tables/tables_13fhr.py,sha256=-6tWcaTyNsb0XuW0WMBrYir9Zn1wLZL0laKxRYfPNyg,4265
@@ -28,7 +31,7 @@ datamule/document/tables/tables_sbsef.py,sha256=X6VKVnAdWxn2TgRmaAd1WWlxPhcLPQ-5
 datamule/document/tables/tables_sdr.py,sha256=BwHRJvtijiYvNJ2lIc_30kct6VEmLimIzX28JjZBBqo,4924
 datamule/document/tables/utils.py,sha256=2-X_1NsiWj_XsD9djxCXwTeIVlg-ip78gG11xACJiDs,738
 datamule/mapping_dicts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datamule/mapping_dicts/html_mapping_dicts.py,sha256=OmelylkccxcPcz6Qv28r6rjbwOhUGnz5Vmzy_BYC0Pg,5406
+datamule/mapping_dicts/html_mapping_dicts.py,sha256=pba3utMr2KldPeEGnMRkHyVw7D2WHSDpg_5u36pHMII,5411
 datamule/mapping_dicts/txt_mapping_dicts.py,sha256=DQPrGYbAPQxomRUtt4iiMGrwuF7BHc_LeFBQuYBzU9o,6311
 datamule/mapping_dicts/xml_mapping_dicts.py,sha256=Z22yDVwKYonUfM5foQP00dVDE8EHhhMKp0CLqVKV5OI,438
 datamule/sec/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -58,7 +61,7 @@ datamule/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datamule/utils/construct_submissions_data.py,sha256=NB_hvfxlRXPyt4Fgc-5qA8vJRItkLhBedCSTaxwW7Jg,5887
 datamule/utils/format_accession.py,sha256=60RtqoNqoT9zSKVb1DeOv1gncJxzPTFMNW4SNOVmC_g,476
 datamule/utils/pdf.py,sha256=Z9xrdVhKex2YdvjYsaPaygRE_J6P_JNiUGkwflz2Hw0,735
-datamule-2.3.0.dist-info/METADATA,sha256=jUra4jM6LMxAS3IKnrF9urlK6ZI4ZAcl6yimnsD67pk,585
-datamule-2.3.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-datamule-2.3.0.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
-datamule-2.3.0.dist-info/RECORD,,
+datamule-2.3.3.dist-info/METADATA,sha256=JMcgYr82lya0HVcKBUOsyALZu4-5J9qwQOVihtduou8,609
+datamule-2.3.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+datamule-2.3.3.dist-info/top_level.txt,sha256=iOfgmtSMFVyr7JGl_bYSTDry79JbmsG4p8zKq89ktKk,9
+datamule-2.3.3.dist-info/RECORD,,