38 lines
1.4 KiB
Python
38 lines
1.4 KiB
Python
|
"""Inspect the HTML structure to find test period / sections."""
|
||
|
|
from pathlib import Path
|
||
|
|
from lxml import html
|
||
|
|
|
||
|
|
for label, fn in [("IS", "IS-ReportTester-52845377.html"), ("OOS", "OOS-ReportTester-52845377.html")]:
|
||
|
|
p = Path("reports") / fn
|
||
|
|
raw = p.read_bytes()
|
||
|
|
text = raw.decode("utf-16") if raw[:2] in (b"\xff\xfe", b"\xfe\xff") else raw.decode("utf-8", errors="replace")
|
||
|
|
tree = html.fromstring(text)
|
||
|
|
|
||
|
|
print(f"=== {label} ({fn}) ===")
|
||
|
|
|
||
|
|
# Find the test period row
|
||
|
|
for row in tree.iter("tr"):
|
||
|
|
cells = row.findall("td") or row.findall("th")
|
||
|
|
if len(cells) < 2:
|
||
|
|
continue
|
||
|
|
label_t = cells[0].text_content().strip()
|
||
|
|
if any(k in label_t for k in ["期间", "Period", "建模", "Model",
|
||
|
|
"前向", "Forward", "起止", "Date"]):
|
||
|
|
value = cells[1].text_content().strip()
|
||
|
|
print(f" {label_t}: {value}")
|
||
|
|
|
||
|
|
# Look for big section headers
|
||
|
|
print(f" -- h1/h2/h3 headers --")
|
||
|
|
for tag in ("h1", "h2", "h3", "h4"):
|
||
|
|
for el in tree.iter(tag):
|
||
|
|
t = (el.text_content() or "").strip()
|
||
|
|
if t:
|
||
|
|
print(f" <{tag}>: {t}")
|
||
|
|
|
||
|
|
# Count tables and tr
|
||
|
|
tables = tree.findall(".//table")
|
||
|
|
print(f" tables: {len(tables)}")
|
||
|
|
total_tr = sum(len(t.findall(".//tr")) for t in tables)
|
||
|
|
print(f" total <tr>: {total_tr}")
|
||
|
|
print()
|