datamule 2.3.7__tar.gz → 2.3.9__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of datamule might be problematic. Click here for more details.
- {datamule-2.3.7 → datamule-2.3.9}/PKG-INFO +1 -1
- {datamule-2.3.7 → datamule-2.3.9}/datamule/portfolio/portfolio.py +2 -1
- datamule-2.3.9/datamule/providers/providers.py +6 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/submissions/streamer.py +1 -1
- {datamule-2.3.7 → datamule-2.3.9}/datamule/submission/submission.py +6 -0
- datamule-2.3.9/datamule/utils/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule.egg-info/PKG-INFO +1 -1
- {datamule-2.3.7 → datamule-2.3.9}/datamule.egg-info/SOURCES.txt +2 -0
- {datamule-2.3.7 → datamule-2.3.9}/setup.py +1 -1
- {datamule-2.3.7 → datamule-2.3.9}/datamule/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/book/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/book/book.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/book/s3transfer.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/cloud/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/config.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/data/listed_filer_metadata.csv +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datamule/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datamule/datamule_lookup.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datamule/datamule_mysql_rds.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datamule/downloader.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datamule/sec_connector.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/datasets.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/document/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/document/document.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/helper.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/index.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/mapping_dicts/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/mapping_dicts/html_mapping_dicts.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/mapping_dicts/txt_mapping_dicts.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/mapping_dicts/xml_mapping_dicts.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/package_updater.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/portfolio/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/portfolio/portfolio_compression_utils_legacy.py +0 -0
- {datamule-2.3.7/datamule/sec → datamule-2.3.9/datamule/providers}/__init__.py +0 -0
- {datamule-2.3.7/datamule/sec/infrastructure → datamule-2.3.9/datamule/sec}/__init__.py +0 -0
- {datamule-2.3.7/datamule/sec/submissions → datamule-2.3.9/datamule/sec/infrastructure}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/infrastructure/submissions_metadata.py +0 -0
- {datamule-2.3.7/datamule/sec/xbrl → datamule-2.3.9/datamule/sec/submissions}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/submissions/downloader.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/submissions/eftsquery.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/submissions/monitor.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/submissions/textsearch.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/utils.py +0 -0
- {datamule-2.3.7/datamule/seclibrary → datamule-2.3.9/datamule/sec/xbrl}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/xbrl/downloadcompanyfacts.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/xbrl/filter_xbrl.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/xbrl/streamcompanyfacts.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sec/xbrl/xbrlmonitor.py +0 -0
- {datamule-2.3.7/datamule/sheet → datamule-2.3.9/datamule/seclibrary}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/seclibrary/bq.py +0 -0
- {datamule-2.3.7/datamule/submission → datamule-2.3.9/datamule/sheet}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/sheet/sheet.py +0 -0
- {datamule-2.3.7/datamule/tables → datamule-2.3.9/datamule/submission}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/submission/tar_submission.py +0 -0
- {datamule-2.3.7/datamule/tags → datamule-2.3.9/datamule/tables}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_13fhr.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_25nse.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_informationtable.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_npx.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_ownership.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_proxyvotingrecord.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_sbsef.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/tables_sdr.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tables/utils.py +0 -0
- {datamule-2.3.7/datamule/utils → datamule-2.3.9/datamule/tags}/__init__.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tags/config.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tags/dictionaries.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tags/regex.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/tags/utils.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/utils/construct_submissions_data.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/utils/format_accession.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule/utils/pdf.py +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule.egg-info/dependency_links.txt +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule.egg-info/requires.txt +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/datamule.egg-info/top_level.txt +0 -0
- {datamule-2.3.7 → datamule-2.3.9}/setup.cfg +0 -0
|
@@ -34,7 +34,6 @@ class Portfolio:
|
|
|
34
34
|
|
|
35
35
|
if self.path.exists():
|
|
36
36
|
self._load_submissions()
|
|
37
|
-
self.submissions_loaded = True
|
|
38
37
|
else:
|
|
39
38
|
self.path.mkdir(parents=True, exist_ok=True)
|
|
40
39
|
|
|
@@ -81,6 +80,8 @@ class Portfolio:
|
|
|
81
80
|
self.submissions = [s for s in (regular_submissions + batch_submissions) if s is not None]
|
|
82
81
|
print(f"Successfully loaded {len(self.submissions)} submissions")
|
|
83
82
|
|
|
83
|
+
self.submissions_loaded = True
|
|
84
|
+
|
|
84
85
|
def _load_batch_submissions_worker(self, batch_tar_path, pbar):
|
|
85
86
|
"""Worker function to load submissions from one batch tar with progress updates"""
|
|
86
87
|
# Open tar handle and store it
|
|
@@ -82,7 +82,7 @@ class Streamer(EFTSQuery):
|
|
|
82
82
|
if self.accession_numbers is not None and accno_w_dash not in self.accession_numbers:
|
|
83
83
|
return None, None, None
|
|
84
84
|
|
|
85
|
-
if self.skip_accession_numbers is not None and
|
|
85
|
+
if self.skip_accession_numbers is not None and accno_no_dash in self.skip_accession_numbers:
|
|
86
86
|
return None, None, None
|
|
87
87
|
|
|
88
88
|
# Construct the URL
|
|
@@ -12,6 +12,7 @@ from company_fundamentals import construct_fundamentals
|
|
|
12
12
|
from decimal import Decimal
|
|
13
13
|
from ..utils.format_accession import format_accession
|
|
14
14
|
from .tar_submission import tar_submission
|
|
15
|
+
import zstandard as zstd
|
|
15
16
|
|
|
16
17
|
# probably needs rework later
|
|
17
18
|
class FundamentalsAccessor:
|
|
@@ -105,6 +106,10 @@ class Submission:
|
|
|
105
106
|
|
|
106
107
|
if response.getcode() == 200:
|
|
107
108
|
sgml_content=response.read()
|
|
109
|
+
content_type = response.headers.get('Content-Type', '')
|
|
110
|
+
if content_type == 'application/zstd':
|
|
111
|
+
dctx = zstd.ZstdDecompressor()
|
|
112
|
+
sgml_content = dctx.decompress(sgml_content)
|
|
108
113
|
else:
|
|
109
114
|
raise ValueError(f"URL: {url}, Error: {response.getcode()}")
|
|
110
115
|
|
|
@@ -116,6 +121,7 @@ class Submission:
|
|
|
116
121
|
metadata = transform_metadata_string(metadata)
|
|
117
122
|
|
|
118
123
|
self.metadata = Document(type='submission_metadata', content=metadata, extension='.json',filing_date=None,accession=None,path=None)
|
|
124
|
+
|
|
119
125
|
self.filing_date= f"{self.metadata.content['filing-date'][:4]}-{self.metadata.content['filing-date'][4:6]}-{self.metadata.content['filing-date'][6:8]}"
|
|
120
126
|
|
|
121
127
|
self.documents_obj_list = []
|
|
File without changes
|
|
@@ -29,6 +29,8 @@ datamule/mapping_dicts/xml_mapping_dicts.py
|
|
|
29
29
|
datamule/portfolio/__init__.py
|
|
30
30
|
datamule/portfolio/portfolio.py
|
|
31
31
|
datamule/portfolio/portfolio_compression_utils_legacy.py
|
|
32
|
+
datamule/providers/__init__.py
|
|
33
|
+
datamule/providers/providers.py
|
|
32
34
|
datamule/sec/__init__.py
|
|
33
35
|
datamule/sec/utils.py
|
|
34
36
|
datamule/sec/infrastructure/__init__.py
|
|
@@ -32,7 +32,7 @@ if not os.path.exists(file_path):
|
|
|
32
32
|
setup(
|
|
33
33
|
name="datamule",
|
|
34
34
|
author="John Friedman",
|
|
35
|
-
version="2.3.
|
|
35
|
+
version="2.3.9",
|
|
36
36
|
description="Work with SEC submissions at scale.",
|
|
37
37
|
packages=find_packages(include=['datamule', 'datamule.*']),
|
|
38
38
|
url="https://github.com/john-friedman/datamule-python",
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{datamule-2.3.7/datamule/sec/submissions → datamule-2.3.9/datamule/sec/infrastructure}/__init__.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|