Fix timezone handling for all date parameters

- Treat naive datetimes as local time and convert to UTC automatically
- Support both naive and timezone-aware datetimes for updated_since, date_from, date_to
- Fix timezone comparison bug that caused incorrect filtering with naive datetimes
- Update documentation with clear timezone handling examples
- Add comprehensive timezone tests for naive and aware datetimes
- Bump version to 0.8.3

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Zachary Hampton
2025-11-11 17:40:21 -08:00
parent 7065f8a0d4
commit 9b61a89c77
5 changed files with 133 additions and 24 deletions

View File

@@ -1,3 +1,5 @@
import pytz
from homeharvest import scrape_property, Property
import pandas as pd
@@ -1524,4 +1526,71 @@ def test_pending_date_optimization():
assert dates[i] >= dates[i + 1], \
"PENDING auto-applied sort should order by pending_date descending"
print("PENDING optimization verified ✓")
print("PENDING optimization verified ✓")
def test_basic_last_update_date():
from datetime import datetime, timedelta
# Test with naive datetime (treated as local time)
now = datetime.now()
properties = scrape_property(
"California",
updated_since=now - timedelta(minutes=10),
sort_by="last_update_date",
sort_direction="desc"
)
# Convert now to timezone-aware for comparison with UTC dates in DataFrame
now_utc = now.astimezone(tz=pytz.timezone("UTC"))
# Check all last_update_date values are <= now
assert (properties["last_update_date"] <= now_utc).all()
# Verify we got some results
assert len(properties) > 0
def test_timezone_aware_last_update_date():
"""Test that timezone-aware datetimes work correctly for updated_since"""
from datetime import datetime, timedelta, timezone
# Test with timezone-aware datetime (explicit UTC)
now_utc = datetime.now(timezone.utc)
properties = scrape_property(
"California",
updated_since=now_utc - timedelta(minutes=10),
sort_by="last_update_date",
sort_direction="desc"
)
# Check all last_update_date values are <= now
assert (properties["last_update_date"] <= now_utc).all()
# Verify we got some results
assert len(properties) > 0
def test_timezone_handling_date_range():
"""Test timezone handling for date_from and date_to parameters"""
from datetime import datetime, timedelta
# Test with naive datetimes for date range (PENDING properties)
now = datetime.now()
three_days_ago = now - timedelta(days=3)
properties = scrape_property(
"California",
listing_type="pending",
date_from=three_days_ago,
date_to=now
)
# Verify we got results and they're within the date range
if len(properties) > 0:
# Convert now to UTC for comparison
now_utc = now.astimezone(tz=pytz.timezone("UTC"))
assert (properties["pending_date"] <= now_utc).all()