ssz223
/
Stock-Tool
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix hedge fund 13F HTML wrapper, field names; fix cache builder rate limiting

This commit is contained in:
Nolan Kovacs 2026-03-26 14:53:14 -04:00
parent c115eee74a
commit 0cad4df12d
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
dist/stock_screener.py vendored
View File

@ -2465,6 +2465,14 @@ def _parse_13f_xml(xml_bytes: bytes) -> list[dict]:
company, class_, cusip, value (USD), shares, shr_type, put_call company, class_, cusip, value (USD), shares, shr_type, put_call
""" """
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
import re as _re
# SEC serves 13F XML wrapped in an HTML document (Content-Type: text/html).
# Strip the HTML wrapper and extract just the <informationTable> block.
if xml_bytes[:500].upper().find(b'<!DOCTYPE HTML') != -1:
m = _re.search(rb'(<informationTable[\s\S]*?</informationTable>)',
xml_bytes, _re.IGNORECASE)
if m:
xml_bytes = m.group(1)
try: try:
root = ET.fromstring(xml_bytes) root = ET.fromstring(xml_bytes)
except ET.ParseError: except ET.ParseError:
@ -2607,9 +2615,10 @@ def fetch_hedge_fund_filings(
src = hit.get("_source", {}) src = hit.get("_source", {})
acc_no = src.get("adsh", "") acc_no = src.get("adsh", "")
ciks = src.get("ciks", []) ciks = src.get("ciks", [])
fund_name = src.get("entity_name", "Unknown Fund") display = src.get("display_names") or src.get("entity_name") or []
filed = (src.get("file_date") or "")[:10] fund_name = display[0].split(" (CIK")[0].strip() if display else "Unknown Fund"
period = (src.get("period_of_report") or "")[:10] filed = (src.get("file_date") or "")[:10]
period = (src.get("period_ending") or src.get("period_of_report") or "")[:10]
if not acc_no or not ciks: if not acc_no or not ciks:
return [] return []