Refactor scraper to use direct requests and bump to 0.8.18

- Replace session-based approach with direct requests calls
- Move headers to module-level DEFAULT_HEADERS constant
- Temporarily disable extra_property_data feature

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

README.md

@@ -7,9 +7,13 @@
 
 ## HomeHarvest Features
 
-- **Source**: Fetches properties directly from **Realtor.com**.
+- **Source**: Fetches properties directly from **Realtor.com**
-- **Data Format**: Structures data to resemble MLS listings.
+- **Data Format**: Structures data to resemble MLS listings
-- **Export Flexibility**: Options to save as either CSV or Excel.
+- **Export Options**: Save as CSV, Excel, or return as Pandas/Pydantic/Raw
+- **Flexible Filtering**: Filter by beds, baths, price, sqft, lot size, year built
+- **Time-Based Queries**: Search by hours, days, or specific date ranges
+- **Multiple Listing Types**: Query for_sale, for_rent, sold, pending, or all at once
+- **Sorting**: Sort results by price, date, size, or last update
 
 ![homeharvest](https://github.com/ZacharyHampton/HomeHarvest/assets/78247585/b3d5d727-e67b-4a9f-85d8-1e65fd18620a)
 
@@ -26,134 +30,78 @@ pip install -U homeharvest
 
 ```py
 from homeharvest import scrape_property
-from datetime import datetime
-
-# Generate filename based on current timestamp
-current_timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-filename = f"HomeHarvest_{current_timestamp}.csv"
 
 properties = scrape_property(
-  location="San Diego, CA",
+    location="San Diego, CA",
-  listing_type="sold",  # or (for_sale, for_rent, pending)
+    listing_type="sold",  # for_sale, for_rent, pending
-  past_days=30,  # sold in last 30 days - listed in last 30 days if (for_sale, for_rent)
+    past_days=30
-
-  # property_type=['single_family','multi_family'],
-  # date_from="2023-05-01", # alternative to past_days
-  # date_to="2023-05-28",
-  # foreclosure=True
-  # mls_only=True,  # only fetch MLS listings
 )
-print(f"Number of properties: {len(properties)}")
 
-# Export to csv
+properties.to_csv("results.csv", index=False)
-properties.to_csv(filename, index=False)
+print(f"Found {len(properties)} properties")
-print(properties.head())
 ```
 
 ### Flexible Location Formats
 ```py
-# HomeHarvest supports any of these location formats:
+# Accepts: zip code, city, "city, state", full address, etc.
-properties = scrape_property(location="92104")  # Just zip code
-properties = scrape_property(location="San Diego")  # Just city  
-properties = scrape_property(location="San Diego, CA")  # City, state
-properties = scrape_property(location="San Diego, California")  # Full state name
-properties = scrape_property(location="1234 Main St, San Diego, CA 92104")  # Full address
-
-# You can also search for properties within a radius of a specific address
 properties = scrape_property(
-    location="1234 Main St, San Diego, CA 92104",
+    location="San Diego, CA",  # or "92104", "San Diego", "1234 Main St, San Diego, CA 92104"
-    radius=5.0  # 5 mile radius
+    radius=5.0  # Optional: search within radius (miles) of address
 )
 ```
 
 ### Advanced Filtering Examples
 
-#### Hour-Based Filtering
+#### Time-Based Filtering
 ```py
-# Get properties listed in the last 24 hours
+from datetime import datetime, timedelta
+
+# Filter by hours or use datetime/timedelta objects
 properties = scrape_property(
     location="Austin, TX",
     listing_type="for_sale",
-    past_hours=24
+    past_hours=24,  # or timedelta(hours=24) for Pythonic approach
-)
+    # date_from=datetime.now() - timedelta(days=7),  # Alternative: datetime objects
-
+    # date_to=datetime.now(),  # Automatic hour precision detection
-# Get properties listed during specific hours (e.g., business hours)
-properties = scrape_property(
-    location="Dallas, TX",
-    listing_type="for_sale",
-    datetime_from="2025-01-20T09:00:00",
-    datetime_to="2025-01-20T17:00:00"
 )
 ```
 
 #### Property Filters
 ```py
-# Filter by bedrooms, bathrooms, and square footage
+# Combine any filters: beds, baths, sqft, price, lot_sqft, year_built
 properties = scrape_property(
     location="San Francisco, CA",
     listing_type="for_sale",
-    beds_min=2,
+    beds_min=3, beds_max=5,
-    beds_max=4,
     baths_min=2.0,
-    sqft_min=1000,
+    sqft_min=1500, sqft_max=3000,
-    sqft_max=2500
+    price_min=300000, price_max=800000,
-)
-
-# Filter by price range
-properties = scrape_property(
-    location="Phoenix, AZ",
-    listing_type="for_sale",
-    price_min=200000,
-    price_max=500000
-)
-
-# Filter by year built
-properties = scrape_property(
-    location="Seattle, WA",
-    listing_type="for_sale",
     year_built_min=2000,
-    beds_min=3
-)
-
-# Combine multiple filters
-properties = scrape_property(
-    location="Denver, CO",
-    listing_type="for_sale",
-    beds_min=3,
-    baths_min=2.0,
-    sqft_min=1500,
-    price_min=300000,
-    price_max=600000,
-    year_built_min=1990,
     lot_sqft_min=5000
 )
 ```
 
-#### Sorting Results
+#### Sorting & Listing Types
 ```py
-# Sort by price (cheapest first)
+# Sort options: list_price, list_date, sqft, beds, baths, last_update_date
+# Listing types: "for_sale", "for_rent", "sold", "pending", "off_market", list, or None (common types)
 properties = scrape_property(
     location="Miami, FL",
-    listing_type="for_sale",
+    listing_type=["for_sale", "pending"],  # Single string, list, or None
-    sort_by="list_price",
+    sort_by="list_price",  # Sort field
-    sort_direction="asc",
+    sort_direction="asc",  # "asc" or "desc"
     limit=100
 )
+```
 
-# Sort by newest listings
+#### Pagination Control
-properties = scrape_property(
+```py
-    location="Boston, MA",
+# Sequential mode with early termination (more efficient for narrow filters)
-    listing_type="for_sale",
-    sort_by="list_date",
-    sort_direction="desc"
-)
-
-# Sort by square footage (largest first)
 properties = scrape_property(
     location="Los Angeles, CA",
     listing_type="for_sale",
-    sort_by="sqft",
+    updated_in_past_hours=2,  # Narrow time window
-    sort_direction="desc"
+    parallel=False  # Fetch pages sequentially, stop when filters no longer match
 )
 ```
 
@@ -192,30 +140,38 @@ for prop in properties[:5]:
 ```
 Required
 ├── location (str): Flexible location search - accepts any of these formats:
-    - ZIP code: "92104"
+│    - ZIP code: "92104"
-    - City: "San Diego" or "San Francisco"
+│    - City: "San Diego" or "San Francisco"
-    - City, State (abbreviated or full): "San Diego, CA" or "San Diego, California"
+│    - City, State (abbreviated or full): "San Diego, CA" or "San Diego, California"
-    - Full address: "1234 Main St, San Diego, CA 92104"
+│    - Full address: "1234 Main St, San Diego, CA 92104"
-    - Neighborhood: "Downtown San Diego"
+│    - Neighborhood: "Downtown San Diego"
-    - County: "San Diego County"
+│    - County: "San Diego County"
-├── listing_type (option): Choose the type of listing.
+│    - State (no support for abbreviated): "California"
-    - 'for_rent'
+│
-    - 'for_sale'
+├── listing_type (str | list[str] | None): Choose the type of listing.
-    - 'sold'
+│    - 'for_sale'
-    - 'pending' (for pending/contingent sales)
+│    - 'for_rent'
-
+│    - 'sold'
+│    - 'pending'
+│    - 'off_market'
+│    - 'new_community'
+│    - 'other'
+│    - 'ready_to_build'
+│    - List of strings returns properties matching ANY status: ['for_sale', 'pending']
+│    - None returns common listing types (for_sale, for_rent, sold, pending, off_market)
+│
 Optional
 ├── property_type (list): Choose the type of properties.
-    - 'single_family'
+│    - 'single_family'
-    - 'multi_family'
+│    - 'multi_family'
-    - 'condos'
+│    - 'condos'
-    - 'condo_townhome_rowhome_coop'
+│    - 'condo_townhome_rowhome_coop'
-    - 'condo_townhome'
+│    - 'condo_townhome'
-    - 'townhomes'
+│    - 'townhomes'
-    - 'duplex_triplex'
+│    - 'duplex_triplex'
-    - 'farm'
+│    - 'farm'
-    - 'land'
+│    - 'land'
-    - 'mobile'
+│    - 'mobile'
 │
 ├── return_type (option): Choose the return type.
 │    - 'pandas' (default)
@@ -228,19 +184,28 @@ Optional
 ├── past_days (integer): Number of past days to filter properties. Utilizes 'last_sold_date' for 'sold' listing types, and 'list_date' for others (for_rent, for_sale).
 │    Example: 30 (fetches properties listed/sold in the last 30 days)
 │
-├── past_hours (integer): Number of past hours to filter properties (more precise than past_days). Uses client-side filtering.
+├── past_hours (integer | timedelta): Number of past hours to filter properties (more precise than past_days). Uses client-side filtering.
-│    Example: 24 (fetches properties from the last 24 hours)
+│    Example: 24 or timedelta(hours=24) (fetches properties from the last 24 hours)
 │    Note: Cannot be used together with past_days or date_from/date_to
 │
 ├── date_from, date_to (string): Start and end dates to filter properties listed or sold, both dates are required.
-|    (use this to get properties in chunks as there's a 10k result limit)
+│    (use this to get properties in chunks as there's a 10k result limit)
-│    Format for both must be "YYYY-MM-DD".
+│    Accepts multiple formats with automatic precision detection:
-│    Example: "2023-05-01", "2023-05-15" (fetches properties listed/sold between these dates)
+│    - Date strings: "YYYY-MM-DD" (day precision)
+│    - Datetime strings: "YYYY-MM-DDTHH:MM:SS" (hour precision, uses client-side filtering)
+│    - date objects: date(2025, 1, 20) (day precision)
+│    - datetime objects: datetime(2025, 1, 20, 9, 0) (hour precision)
+│    Examples:
+│      Day precision: "2023-05-01", "2023-05-15"
+│      Hour precision: "2025-01-20T09:00:00", "2025-01-20T17:00:00"
 │
-├── datetime_from, datetime_to (string): ISO 8601 datetime strings for hour-precise filtering. Uses client-side filtering.
+├── updated_since (datetime | str): Filter properties updated since a specific date/time (based on last_update_date field)
-│    Format: "YYYY-MM-DDTHH:MM:SS" or "YYYY-MM-DD"
+│    Accepts datetime objects or ISO 8601 strings
-│    Example: "2025-01-20T09:00:00", "2025-01-20T17:00:00" (fetches properties between 9 AM and 5 PM)
+│    Example: updated_since=datetime(2025, 11, 10, 9, 0) or "2025-11-10T09:00:00"
-│    Note: Cannot be used together with date_from/date_to
+│
+├── updated_in_past_hours (integer | timedelta): Filter properties updated in the past X hours (based on last_update_date field)
+│    Accepts integer (hours) or timedelta object
+│    Example: updated_in_past_hours=24 or timedelta(hours=24)
 │
 ├── beds_min, beds_max (integer): Filter by number of bedrooms
 │    Example: beds_min=2, beds_max=4 (2-4 bedrooms)
@@ -261,7 +226,7 @@ Optional
 │    Example: year_built_min=2000, year_built_max=2024 (built between 2000-2024)
 │
 ├── sort_by (string): Sort results by field
-│    Options: 'list_date', 'sold_date', 'list_price', 'sqft', 'beds', 'baths'
+│    Options: 'list_date', 'sold_date', 'list_price', 'sqft', 'beds', 'baths', 'last_update_date'
 │    Example: sort_by='list_price'
 │
 ├── sort_direction (string): Sort direction, default is 'desc'
@@ -280,7 +245,9 @@ Optional
 │
 ├── limit (integer): Limit the number of properties to fetch. Max & default is 10000.
 │
-└── offset (integer): Starting position for pagination within the 10k limit. Use with limit to fetch results in chunks.
+├── offset (integer): Starting position for pagination within the 10k limit. Use with limit to fetch results in chunks.
+│
+└── parallel (True/False): Controls pagination strategy. Default is True (fetch pages in parallel for speed). Set to False for sequential fetching with early termination (useful for rate limiting or narrow time windows).
 ```
 
 ### Property Schema
@@ -327,6 +294,7 @@ Property
 │ ├── sold_price
 │ ├── last_sold_date  # datetime (full timestamp: YYYY-MM-DD HH:MM:SS)
 │ ├── last_status_change_date  # datetime (full timestamp: YYYY-MM-DD HH:MM:SS)
+│ ├── last_update_date  # datetime (full timestamp: YYYY-MM-DD HH:MM:SS)
 │ ├── last_sold_price
 │ ├── price_per_sqft
 │ ├── new_construction

homeharvest/__init__.py

@@ -1,31 +1,37 @@
 import warnings
 import pandas as pd
+from datetime import datetime, timedelta, date
 from .core.scrapers import ScraperInput
-from .utils import process_result, ordered_properties, validate_input, validate_dates, validate_limit, validate_offset, validate_datetime, validate_filters, validate_sort
+from .utils import (
+    process_result, ordered_properties, validate_input, validate_dates, validate_limit,
+    validate_offset, validate_datetime, validate_filters, validate_sort, validate_last_update_filters,
+    convert_to_datetime_string, extract_timedelta_hours, extract_timedelta_days, detect_precision_and_convert
+)
 from .core.scrapers.realtor import RealtorScraper
 from .core.scrapers.models import ListingType, SearchPropertyType, ReturnType, Property
 from typing import Union, Optional, List
 
 def scrape_property(
     location: str,
-    listing_type: str = "for_sale",
+    listing_type: str | list[str] | None = None,
     return_type: str = "pandas",
     property_type: Optional[List[str]] = None,
     radius: float = None,
     mls_only: bool = False,
-    past_days: int = None,
+    past_days: int | timedelta = None,
     proxy: str = None,
-    date_from: str = None,
+    date_from: datetime | date | str = None,
-    date_to: str = None,
+    date_to: datetime | date | str = None,
     foreclosure: bool = None,
     extra_property_data: bool = True,
     exclude_pending: bool = False,
     limit: int = 10000,
     offset: int = 0,
     # New date/time filtering parameters
-    past_hours: int = None,
+    past_hours: int | timedelta = None,
-    datetime_from: str = None,
+    # New last_update_date filtering parameters
-    datetime_to: str = None,
+    updated_since: datetime | str = None,
+    updated_in_past_hours: int | timedelta = None,
     # New property filtering parameters
     beds_min: int = None,
     beds_max: int = None,
@@ -42,12 +48,16 @@ def scrape_property(
     # New sorting parameters
     sort_by: str = None,
     sort_direction: str = "desc",
+    # Pagination control
+    parallel: bool = True,
 ) -> Union[pd.DataFrame, list[dict], list[Property]]:
     """
     Scrape properties from Realtor.com based on a given location and listing type.
 
     :param location: Location to search (e.g. "Dallas, TX", "85281", "2530 Al Lipscomb Way")
-    :param listing_type: Listing Type (for_sale, for_rent, sold, pending)
+    :param listing_type: Listing Type - can be a string, list of strings, or None.
+        Options: for_sale, for_rent, sold, pending, off_market, new_community, other, ready_to_build
+        Examples: "for_sale", ["for_sale", "pending"], None (returns all types)
     :param return_type: Return type (pandas, pydantic, raw)
     :param property_type: Property Type (single_family, multi_family, condos, condo_townhome_rowhome_coop, condo_townhome, townhomes, duplex_triplex, farm, land, mobile)
     :param radius: Get properties within _ (e.g. 1.0) miles. Only applicable for individual addresses.
@@ -57,7 +67,15 @@ def scrape_property(
         - PENDING: Filters by pending_date. Contingent properties without pending_date are included.
         - SOLD: Filters by sold_date (when property was sold)
         - FOR_SALE/FOR_RENT: Filters by list_date (when property was listed)
-    :param date_from, date_to: Get properties sold or listed (dependent on your listing_type) between these dates. format: 2021-01-28
+    :param date_from, date_to: Get properties sold or listed (dependent on your listing_type) between these dates.
+        Accepts multiple formats for flexible precision:
+        - Date strings: "2025-01-20" (day-level precision)
+        - Datetime strings: "2025-01-20T14:30:00" (hour-level precision)
+        - date objects: date(2025, 1, 20) (day-level precision)
+        - datetime objects: datetime(2025, 1, 20, 14, 30) (hour-level precision)
+        The precision is automatically detected based on the input format.
+        Timezone handling: Naive datetimes are treated as local time and automatically converted to UTC.
+        Timezone-aware datetimes are converted to UTC. For best results, use timezone-aware datetimes.
     :param foreclosure: If set, fetches only foreclosure listings.
     :param extra_property_data: Increases requests by O(n). If set, this fetches additional property data (e.g. agent, broker, property evaluations etc.)
     :param exclude_pending: If true, this excludes pending or contingent properties from the results, unless listing type is pending.
@@ -65,49 +83,102 @@ def scrape_property(
     :param offset: Starting position for pagination within the 10k limit (offset + limit cannot exceed 10,000). Use with limit to fetch results in chunks (e.g., offset=200, limit=200 fetches results 200-399). Should be a multiple of 200 (page size) for optimal performance. Default is 0. Note: Cannot be used to bypass the 10k API limit - use date ranges (date_from/date_to) to narrow searches and fetch more data.
 
     New parameters:
-    :param past_hours: Get properties in the last _ hours (requires client-side filtering)
+    :param past_hours: Get properties in the last _ hours (requires client-side filtering). Accepts int or timedelta.
-    :param datetime_from, datetime_to: ISO 8601 datetime strings for precise time filtering (e.g. "2025-01-20T14:30:00")
+    :param updated_since: Filter by last_update_date (when property was last updated). Accepts datetime object or ISO 8601 string (client-side filtering).
+        Timezone handling: Naive datetimes (like datetime.now()) are treated as local time and automatically converted to UTC.
+        Timezone-aware datetimes are converted to UTC. Examples:
+        - datetime.now() - uses your local timezone
+        - datetime.now(timezone.utc) - uses UTC explicitly
+    :param updated_in_past_hours: Filter by properties updated in the last _ hours. Accepts int or timedelta (client-side filtering)
     :param beds_min, beds_max: Filter by number of bedrooms
     :param baths_min, baths_max: Filter by number of bathrooms
     :param sqft_min, sqft_max: Filter by square footage
     :param price_min, price_max: Filter by listing price
     :param lot_sqft_min, lot_sqft_max: Filter by lot size
     :param year_built_min, year_built_max: Filter by year built
-    :param sort_by: Sort results by field (list_date, sold_date, list_price, sqft, beds, baths)
+    :param sort_by: Sort results by field (list_date, sold_date, list_price, sqft, beds, baths, last_update_date)
     :param sort_direction: Sort direction (asc, desc)
+    :param parallel: Controls pagination strategy. True (default) = fetch all pages in parallel for maximum speed.
+        False = fetch pages sequentially with early termination checks (useful for rate limiting or narrow time windows).
+        Sequential mode will stop paginating as soon as time-based filters indicate no more matches are possible.
+
+    Note: past_days and past_hours also accept timedelta objects for more Pythonic usage.
     """
     validate_input(listing_type)
-    validate_dates(date_from, date_to)
     validate_limit(limit)
     validate_offset(offset, limit)
-    validate_datetime(datetime_from)
-    validate_datetime(datetime_to)
     validate_filters(
         beds_min, beds_max, baths_min, baths_max, sqft_min, sqft_max,
         price_min, price_max, lot_sqft_min, lot_sqft_max, year_built_min, year_built_max
     )
     validate_sort(sort_by, sort_direction)
 
+    # Validate new last_update_date filtering parameters
+    validate_last_update_filters(
+        convert_to_datetime_string(updated_since),
+        extract_timedelta_hours(updated_in_past_hours)
+    )
+
+    # Convert listing_type to appropriate format
+    if listing_type is None:
+        converted_listing_type = None
+    elif isinstance(listing_type, list):
+        converted_listing_type = [ListingType(lt.upper()) for lt in listing_type]
+    else:
+        converted_listing_type = ListingType(listing_type.upper())
+
+    # Convert date_from/date_to with precision detection
+    converted_date_from, date_from_precision = detect_precision_and_convert(date_from)
+    converted_date_to, date_to_precision = detect_precision_and_convert(date_to)
+
+    # Validate converted dates
+    validate_dates(converted_date_from, converted_date_to)
+
+    # Convert datetime/timedelta objects to appropriate formats
+    converted_past_days = extract_timedelta_days(past_days)
+    converted_past_hours = extract_timedelta_hours(past_hours)
+    converted_updated_since = convert_to_datetime_string(updated_since)
+    converted_updated_in_past_hours = extract_timedelta_hours(updated_in_past_hours)
+
+    # Auto-apply optimal sort for time-based filters (unless user specified different sort)
+    if (converted_updated_since or converted_updated_in_past_hours) and not sort_by:
+        sort_by = "last_update_date"
+        if not sort_direction:
+            sort_direction = "desc"  # Most recent first
+
+    # Auto-apply optimal sort for PENDING listings with date filters
+    # PENDING API filtering is broken, so we rely on client-side filtering
+    # Sorting by pending_date ensures efficient pagination with early termination
+    elif (converted_listing_type == ListingType.PENDING and
+          (converted_past_days or converted_past_hours or converted_date_from) and
+          not sort_by):
+        sort_by = "pending_date"
+        if not sort_direction:
+            sort_direction = "desc"  # Most recent first
+
     scraper_input = ScraperInput(
         location=location,
-        listing_type=ListingType(listing_type.upper()),
+        listing_type=converted_listing_type,
         return_type=ReturnType(return_type.lower()),
         property_type=[SearchPropertyType[prop.upper()] for prop in property_type] if property_type else None,
         proxy=proxy,
         radius=radius,
         mls_only=mls_only,
-        last_x_days=past_days,
+        last_x_days=converted_past_days,
-        date_from=date_from,
+        date_from=converted_date_from,
-        date_to=date_to,
+        date_to=converted_date_to,
+        date_from_precision=date_from_precision,
+        date_to_precision=date_to_precision,
         foreclosure=foreclosure,
         extra_property_data=extra_property_data,
         exclude_pending=exclude_pending,
         limit=limit,
         offset=offset,
         # New date/time filtering
-        past_hours=past_hours,
+        past_hours=converted_past_hours,
-        datetime_from=datetime_from,
+        # New last_update_date filtering
-        datetime_to=datetime_to,
+        updated_since=converted_updated_since,
+        updated_in_past_hours=converted_updated_in_past_hours,
         # New property filtering
         beds_min=beds_min,
         beds_max=beds_max,
@@ -124,6 +195,8 @@ def scrape_property(
         # New sorting
         sort_by=sort_by,
         sort_direction=sort_direction,
+        # Pagination control
+        parallel=parallel,
     )
 
     site = RealtorScraper(scraper_input)

homeharvest/cli.py

@@ -1,85 +0,0 @@
-import argparse
-import datetime
-from homeharvest import scrape_property
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Home Harvest Property Scraper")
-    parser.add_argument("location", type=str, help="Location to scrape (e.g., San Francisco, CA)")
-
-    parser.add_argument(
-        "-l",
-        "--listing_type",
-        type=str,
-        default="for_sale",
-        choices=["for_sale", "for_rent", "sold", "pending"],
-        help="Listing type to scrape",
-    )
-
-    parser.add_argument(
-        "-o",
-        "--output",
-        type=str,
-        default="excel",
-        choices=["excel", "csv"],
-        help="Output format",
-    )
-
-    parser.add_argument(
-        "-f",
-        "--filename",
-        type=str,
-        default=None,
-        help="Name of the output file (without extension)",
-    )
-
-    parser.add_argument("-p", "--proxy", type=str, default=None, help="Proxy to use for scraping")
-    parser.add_argument(
-        "-d",
-        "--days",
-        type=int,
-        default=None,
-        help="Sold/listed in last _ days filter.",
-    )
-
-    parser.add_argument(
-        "-r",
-        "--radius",
-        type=float,
-        default=None,
-        help="Get comparable properties within _ (eg. 0.0) miles. Only applicable for individual addresses.",
-    )
-    parser.add_argument(
-        "-m",
-        "--mls_only",
-        action="store_true",
-        help="If set, fetches only MLS listings.",
-    )
-
-    args = parser.parse_args()
-
-    result = scrape_property(
-        args.location,
-        args.listing_type,
-        radius=args.radius,
-        proxy=args.proxy,
-        mls_only=args.mls_only,
-        past_days=args.days,
-    )
-
-    if not args.filename:
-        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
-        args.filename = f"HomeHarvest_{timestamp}"
-
-    if args.output == "excel":
-        output_filename = f"{args.filename}.xlsx"
-        result.to_excel(output_filename, index=False)
-        print(f"Excel file saved as {output_filename}")
-    elif args.output == "csv":
-        output_filename = f"{args.filename}.csv"
-        result.to_csv(output_filename, index=False)
-        print(f"CSV file saved as {output_filename}")
-
-
-if __name__ == "__main__":
-    main()

homeharvest/core/scrapers/__init__.py

@@ -2,8 +2,6 @@ from __future__ import annotations
 from typing import Union
 
 import requests
-from requests.adapters import HTTPAdapter
-from urllib3.util.retry import Retry
 import uuid
 from ...exceptions import AuthenticationError
 from .models import Property, ListingType, SiteName, SearchPropertyType, ReturnType
@@ -11,9 +9,30 @@ import json
 from pydantic import BaseModel
 
 
+DEFAULT_HEADERS = {
+    'Content-Type': 'application/json',
+    'Accept': '*/*',
+    'Accept-Language': 'en-US,en;q=0.9',
+    'Cache-Control': 'no-cache',
+    'Origin': 'https://www.realtor.com',
+    'Pragma': 'no-cache',
+    'Referer': 'https://www.realtor.com/',
+    'rdc-client-name': 'RDC_WEB_SRP_FS_PAGE',
+    'rdc-client-version': '3.0.2515',
+    'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+    'sec-ch-ua-mobile': '?0',
+    'sec-ch-ua-platform': '"macOS"',
+    'sec-fetch-dest': 'empty',
+    'sec-fetch-mode': 'cors',
+    'sec-fetch-site': 'same-site',
+    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36',
+    'x-is-bot': 'false',
+}
+
+
 class ScraperInput(BaseModel):
     location: str
-    listing_type: ListingType
+    listing_type: ListingType | list[ListingType] | None
     property_type: list[SearchPropertyType] | None = None
     radius: float | None = None
     mls_only: bool | None = False
@@ -21,6 +40,8 @@ class ScraperInput(BaseModel):
     last_x_days: int | None = None
     date_from: str | None = None
     date_to: str | None = None
+    date_from_precision: str | None = None  # "day" or "hour"
+    date_to_precision: str | None = None    # "day" or "hour"
     foreclosure: bool | None = False
     extra_property_data: bool | None = True
     exclude_pending: bool | None = False
@@ -30,8 +51,10 @@ class ScraperInput(BaseModel):
 
     # New date/time filtering parameters
     past_hours: int | None = None
-    datetime_from: str | None = None
+
-    datetime_to: str | None = None
+    # New last_update_date filtering parameters
+    updated_since: str | None = None
+    updated_in_past_hours: int | None = None
 
     # New property filtering parameters
     beds_min: int | None = None
@@ -51,10 +74,11 @@ class ScraperInput(BaseModel):
     sort_by: str | None = None
     sort_direction: str = "desc"
 
+    # Pagination control
+    parallel: bool = True
+
 
 class Scraper:
-    session = None
-
     def __init__(
         self,
         scraper_input: ScraperInput,
@@ -62,40 +86,8 @@ class Scraper:
         self.location = scraper_input.location
         self.listing_type = scraper_input.listing_type
         self.property_type = scraper_input.property_type
-
+        self.proxy = scraper_input.proxy
-        if not self.session:
+        self.proxies = {"http": self.proxy, "https": self.proxy} if self.proxy else None
-            Scraper.session = requests.Session()
-            retries = Retry(
-                total=3, backoff_factor=4, status_forcelist=[429, 403], allowed_methods=frozenset(["GET", "POST"])
-            )
-
-            adapter = HTTPAdapter(max_retries=retries)
-            Scraper.session.mount("http://", adapter)
-            Scraper.session.mount("https://", adapter)
-            Scraper.session.headers.update(
-                {
-                    "accept": "application/json, text/javascript",
-                    "accept-language": "en-US,en;q=0.9",
-                    "cache-control": "no-cache",
-                    "content-type": "application/json",
-                    "origin": "https://www.realtor.com",
-                    "pragma": "no-cache",
-                    "priority": "u=1, i",
-                    "rdc-ab-tests": "commute_travel_time_variation:v1",
-                    "sec-ch-ua": '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
-                    "sec-ch-ua-mobile": "?0",
-                    "sec-ch-ua-platform": '"Windows"',
-                    "sec-fetch-dest": "empty",
-                    "sec-fetch-mode": "cors",
-                    "sec-fetch-site": "same-origin",
-                    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
-                }
-            )
-
-        if scraper_input.proxy:
-            proxy_url = scraper_input.proxy
-            proxies = {"http": proxy_url, "https": proxy_url}
-            self.session.proxies.update(proxies)
 
         self.listing_type = scraper_input.listing_type
         self.radius = scraper_input.radius
@@ -103,8 +95,10 @@ class Scraper:
         self.mls_only = scraper_input.mls_only
         self.date_from = scraper_input.date_from
         self.date_to = scraper_input.date_to
+        self.date_from_precision = scraper_input.date_from_precision
+        self.date_to_precision = scraper_input.date_to_precision
         self.foreclosure = scraper_input.foreclosure
-        self.extra_property_data = scraper_input.extra_property_data
+        self.extra_property_data = False  # TODO: temporarily disabled
         self.exclude_pending = scraper_input.exclude_pending
         self.limit = scraper_input.limit
         self.offset = scraper_input.offset
@@ -112,8 +106,10 @@ class Scraper:
 
         # New date/time filtering
         self.past_hours = scraper_input.past_hours
-        self.datetime_from = scraper_input.datetime_from
+
-        self.datetime_to = scraper_input.datetime_to
+        # New last_update_date filtering
+        self.updated_since = scraper_input.updated_since
+        self.updated_in_past_hours = scraper_input.updated_in_past_hours
 
         # New property filtering
         self.beds_min = scraper_input.beds_min
@@ -133,6 +129,9 @@ class Scraper:
         self.sort_by = scraper_input.sort_by
         self.sort_direction = scraper_input.sort_direction
 
+        # Pagination control
+        self.parallel = scraper_input.parallel
+
     def search(self) -> list[Union[Property | dict]]: ...
 
     @staticmethod

homeharvest/core/scrapers/models.py

@@ -43,6 +43,10 @@ class ListingType(Enum):
     FOR_RENT = "FOR_RENT"
     PENDING = "PENDING"
     SOLD = "SOLD"
+    OFF_MARKET = "OFF_MARKET"
+    NEW_COMMUNITY = "NEW_COMMUNITY"
+    OTHER = "OTHER"
+    READY_TO_BUILD = "READY_TO_BUILD"
 
 
 class PropertyType(Enum):
@@ -193,6 +197,7 @@ class Property(BaseModel):
     pending_date: datetime | None = Field(None, description="The date listing went into pending state")
     last_sold_date: datetime | None = Field(None, description="Last time the Home was sold")
     last_status_change_date: datetime | None = Field(None, description="Last time the status of the listing changed")
+    last_update_date: datetime | None = Field(None, description="Last time the home was updated")
     prc_sqft: int | None = None
     new_construction: bool | None = Field(None, description="Search for new construction homes")
     hoa_fee: int | None = Field(None, description="Search for homes where HOA fee is known and falls within specified range")

homeharvest/core/scrapers/realtor/__init__.py

@@ -8,25 +8,27 @@ This module implements the scraper for realtor.com
 from __future__ import annotations
 
 import json
+import requests
 from concurrent.futures import ThreadPoolExecutor, as_completed
-from datetime import datetime
 from json import JSONDecodeError
 from typing import Dict, Union
 
 from tenacity import (
     retry,
     retry_if_exception_type,
+    retry_if_not_exception_type,
     wait_exponential,
     stop_after_attempt,
 )
 
-from .. import Scraper
+from .. import Scraper, DEFAULT_HEADERS
+from ....exceptions import AuthenticationError
 from ..models import (
     Property,
     ListingType,
     ReturnType
 )
-from .queries import GENERAL_RESULTS_QUERY, SEARCH_HOMES_DATA, HOMES_DATA, HOME_FRAGMENT
+from .queries import GENERAL_RESULTS_QUERY, HOMES_DATA, SEARCH_SUGGESTIONS_QUERY
 from .processors import (
     process_property,
     process_extra_property_details,
@@ -35,56 +37,127 @@ from .processors import (
 
 
 class RealtorScraper(Scraper):
-    SEARCH_GQL_URL = "https://www.realtor.com/api/v1/rdc_search_srp?client_id=rdc-search-new-communities&schema=vesta"
+    SEARCH_GQL_URL = "https://www.realtor.com/frontdoor/graphql"
-    PROPERTY_URL = "https://www.realtor.com/realestateandhomes-detail/"
-    PROPERTY_GQL = "https://graph.realtor.com/graphql"
-    ADDRESS_AUTOCOMPLETE_URL = "https://parser-external.geo.moveaws.com/suggest"
     NUM_PROPERTY_WORKERS = 20
     DEFAULT_PAGE_SIZE = 200
 
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
 
-    def handle_location(self):
+    @staticmethod
-        params = {
+    def _minify_query(query: str) -> str:
-            "input": self.location,
+        """Minify GraphQL query by collapsing whitespace to single spaces."""
-            "client_id": self.listing_type.value.lower().replace("_", "-"),
+        # Split on whitespace, filter empty strings, join with single space
-            "limit": "1",
+        return ' '.join(query.split())
-            "area_types": "city,state,county,postal_code,address,street,neighborhood,school,school_district,university,park",
+
+    def _graphql_post(self, query: str, variables: dict, operation_name: str) -> dict:
+        """
+        Execute a GraphQL query.
+
+        Args:
+            query: GraphQL query string (must include operationName matching operation_name param)
+            variables: Query variables dictionary
+            operation_name: Name of the GraphQL operation
+
+        Returns:
+            Response JSON dictionary
+        """
+        payload = {
+            "operationName": operation_name,
+            "query": self._minify_query(query),
+            "variables": variables,
         }
 
-        response = self.session.get(
+        response = requests.post(
-            self.ADDRESS_AUTOCOMPLETE_URL,
+            self.SEARCH_GQL_URL,
-            params=params,
+            headers=DEFAULT_HEADERS,
+            data=json.dumps(payload, separators=(',', ':')),
+            proxies=self.proxies
         )
-        response_json = response.json()
 
-        result = response_json["autocomplete"]
+        if response.status_code == 403:
+            if not self.proxy:
+                raise AuthenticationError(
+                    "Received 403 Forbidden from Realtor.com API.",
+                    response=response
+                )
+            else:
+                raise Exception("Received 403 Forbidden, retrying...")
 
-        if not result:
+        return response.json()
+
+    @retry(
+        retry=retry_if_exception_type(Exception),
+        wait=wait_exponential(multiplier=1, min=1, max=4),
+        stop=stop_after_attempt(3),
+    )
+    def handle_location(self):
+        variables = {
+            "searchInput": {
+                "search_term": self.location
+            }
+        }
+
+        response_json = self._graphql_post(SEARCH_SUGGESTIONS_QUERY, variables, "Search_suggestions")
+
+        if (
+            response_json is None
+            or "data" not in response_json
+            or response_json["data"] is None
+            or "search_suggestions" not in response_json["data"]
+            or response_json["data"]["search_suggestions"] is None
+            or "geo_results" not in response_json["data"]["search_suggestions"]
+            or not response_json["data"]["search_suggestions"]["geo_results"]
+        ):
+            # If we got a 400 error with "Required parameter is missing", raise to trigger retry
+            if response_json and "errors" in response_json:
+                error_msgs = [e.get("message", "") for e in response_json.get("errors", [])]
+                if any("Required parameter is missing" in msg for msg in error_msgs):
+                    raise Exception(f"Transient API error: {error_msgs}")
             return None
 
-        return result[0]
+        geo_result = response_json["data"]["search_suggestions"]["geo_results"][0]
+        geo = geo_result.get("geo", {})
+
+        result = {
+            "text": geo_result.get("text"),
+            "area_type": geo.get("area_type"),
+            "city": geo.get("city"),
+            "state_code": geo.get("state_code"),
+            "postal_code": geo.get("postal_code"),
+            "county": geo.get("county"),
+            "centroid": geo.get("centroid"),
+        }
+
+        if geo.get("area_type") == "address":
+            # Try to get mpr_id directly from API response first
+            if geo.get("mpr_id"):
+                result["mpr_id"] = geo.get("mpr_id")
+            else:
+                # Fallback: extract from _id field if it has addr: prefix
+                geo_id = geo.get("_id", "")
+                if geo_id.startswith("addr:"):
+                    result["mpr_id"] = geo_id.replace("addr:", "")
+
+        return result
 
     def get_latest_listing_id(self, property_id: str) -> str | None:
-        query = """query Property($property_id: ID!) {
+        query = """
+                fragment ListingFragment on Listing {
+                    listing_id
+                    primary
+                }
+                query GetPropertyListingId($property_id: ID!) {
                     property(id: $property_id) {
                         listings {
-                            listing_id
+                            ...ListingFragment
-                            primary
                         }
                     }
                 }
                 """
 
         variables = {"property_id": property_id}
-        payload = {
+        response_json = self._graphql_post(query, variables, "GetPropertyListingId")
-            "query": query,
-            "variables": variables,
-        }
-
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
 
         property_info = response_json["data"]["property"]
         if property_info["listings"] is None:
@@ -100,31 +173,40 @@ class RealtorScraper(Scraper):
             return property_info["listings"][0]["listing_id"]
 
     def handle_home(self, property_id: str) -> list[Property]:
+        """Fetch single home with proper error handling."""
         query = (
-            """query Home($property_id: ID!) {
+            """query GetHomeDetails($property_id: ID!) {
                     home(property_id: $property_id) %s
                 }"""
             % HOMES_DATA
         )
 
         variables = {"property_id": property_id}
-        payload = {
-            "query": query,
-            "variables": variables,
-        }
 
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
+        try:
-        response_json = response.json()
+            data = self._graphql_post(query, variables, "GetHomeDetails")
 
-        property_info = response_json["data"]["home"]
+            # Check for errors or missing data
+            if "errors" in data or "data" not in data:
+                return []
 
-        if self.return_type != ReturnType.raw:
+            if data["data"] is None or "home" not in data["data"]:
-            return [process_property(property_info, self.mls_only, self.extra_property_data, 
+                return []
-                                   self.exclude_pending, self.listing_type, get_key, process_extra_property_details)]
-        else:
-            return [property_info]
 
+            property_info = data["data"]["home"]
+            if property_info is None:
+                return []
 
+            # Process based on return type
+            if self.return_type != ReturnType.raw:
+                return [process_property(property_info, self.mls_only, self.extra_property_data,
+                                       self.exclude_pending, self.listing_type, get_key,
+                                       process_extra_property_details)]
+            else:
+                return [property_info]
+
+        except Exception:
+            return []
 
     def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, Union[list[Property], list[dict]]]]:
         """
@@ -134,34 +216,56 @@ class RealtorScraper(Scraper):
         date_param = ""
 
         # Determine date field based on listing type
-        if self.listing_type == ListingType.SOLD:
+        # Convert listing_type to list for uniform handling
-            date_field = "sold_date"
+        if self.listing_type is None:
-        elif self.listing_type in [ListingType.FOR_SALE, ListingType.FOR_RENT]:
+            # When None, return all common listing types as documented
-            date_field = "list_date"
+            # Note: NEW_COMMUNITY, OTHER, and READY_TO_BUILD are excluded as they typically return no results
-        else:  # PENDING
+            listing_types = [
-            # Skip server-side date filtering for PENDING as both pending_date and contract_date
+                ListingType.FOR_SALE,
-            # filters are broken in the API. Client-side filtering will be applied later.
+                ListingType.FOR_RENT,
-            date_field = None
+                ListingType.SOLD,
+                ListingType.PENDING,
+                ListingType.OFF_MARKET,
+            ]
+            date_field = None  # When no listing_type is specified, skip date filtering
+        elif isinstance(self.listing_type, list):
+            listing_types = self.listing_type
+            # For multiple types, we'll use a general date field or skip
+            date_field = None  # Skip date filtering for mixed types
+        else:
+            listing_types = [self.listing_type]
+            # Determine date field for single type
+            if self.listing_type == ListingType.SOLD:
+                date_field = "sold_date"
+            elif self.listing_type in [ListingType.FOR_SALE, ListingType.FOR_RENT]:
+                date_field = "list_date"
+            else:  # PENDING or other types
+                # Skip server-side date filtering for PENDING as both pending_date and contract_date
+                # filters are broken in the API. Client-side filtering will be applied later.
+                date_field = None
 
         # Build date parameter (expand to full days if hour-based filtering is used)
         if date_field:
-            if self.datetime_from or self.datetime_to:
+            # Check if we have hour precision (need to extract date part for API, then filter client-side)
+            has_hour_precision = (self.date_from_precision == "hour" or self.date_to_precision == "hour")
+
+            if has_hour_precision and (self.date_from or self.date_to):
                 # Hour-based datetime filtering: extract date parts for API, client-side filter by hours
                 from datetime import datetime
 
                 min_date = None
                 max_date = None
 
-                if self.datetime_from:
+                if self.date_from:
                     try:
-                        dt_from = datetime.fromisoformat(self.datetime_from.replace('Z', '+00:00'))
+                        dt_from = datetime.fromisoformat(self.date_from.replace('Z', '+00:00'))
                         min_date = dt_from.strftime("%Y-%m-%d")
                     except (ValueError, AttributeError):
                         pass
 
-                if self.datetime_to:
+                if self.date_to:
                     try:
-                        dt_to = datetime.fromisoformat(self.datetime_to.replace('Z', '+00:00'))
+                        dt_to = datetime.fromisoformat(self.date_to.replace('Z', '+00:00'))
                         max_date = dt_to.strftime("%Y-%m-%d")
                     except (ValueError, AttributeError):
                         pass
@@ -250,13 +354,19 @@ class RealtorScraper(Scraper):
         # Build sort parameter
         if self.sort_by:
             sort_param = f"sort: [{{ field: {self.sort_by}, direction: {self.sort_direction} }}]"
-        elif self.listing_type == ListingType.SOLD:
+        elif isinstance(self.listing_type, ListingType) and self.listing_type == ListingType.SOLD:
             sort_param = "sort: [{ field: sold_date, direction: desc }]"
         else:
             sort_param = ""  #: prioritize normal fractal sort from realtor
 
+        # Handle PENDING with or_filters
+        # Only use or_filters when PENDING is the only type or mixed only with FOR_SALE
+        # Using or_filters with other types (SOLD, FOR_RENT, etc.) will exclude those types
+        has_pending = ListingType.PENDING in listing_types
+        other_types = [lt for lt in listing_types if lt not in [ListingType.PENDING, ListingType.FOR_SALE]]
+        use_or_filters = has_pending and len(other_types) == 0
         pending_or_contingent_param = (
-            "or_filters: { contingent: true, pending: true }" if self.listing_type == ListingType.PENDING else ""
+            "or_filters: { contingent: true, pending: true }" if use_or_filters else ""
         )
 
         # Build bucket parameter (only use fractal sort if no custom sort is specified)
@@ -264,7 +374,27 @@ class RealtorScraper(Scraper):
         if not self.sort_by:
             bucket_param = 'bucket: { sort: "fractal_v1.1.3_fr" }'
 
-        listing_type = ListingType.FOR_SALE if self.listing_type == ListingType.PENDING else self.listing_type
+        # Build status parameter
+        # For PENDING, we need to query as FOR_SALE with or_filters for pending/contingent
+        status_types = []
+        for lt in listing_types:
+            if lt == ListingType.PENDING:
+                if ListingType.FOR_SALE not in status_types:
+                    status_types.append(ListingType.FOR_SALE)
+            else:
+                if lt not in status_types:
+                    status_types.append(lt)
+
+        # Build status parameter string
+        if status_types:
+            status_values = [st.value.lower() for st in status_types]
+            if len(status_values) == 1:
+                status_param = f"status: {status_values[0]}"
+            else:
+                status_param = f"status: [{', '.join(status_values)}]"
+        else:
+            status_param = ""  # No status parameter means return all types
+
         is_foreclosure = ""
 
         if variables.get("foreclosure") is True:
@@ -273,19 +403,19 @@ class RealtorScraper(Scraper):
             is_foreclosure = "foreclosure: false"
 
         if search_type == "comps":  #: comps search, came from an address
-            query = """query Property_search(
+            query = """query GetHomeSearch(
                     $coordinates: [Float]!
                     $radius: String!
                     $offset: Int!,
                     ) {
-                        home_search(
+                        homeSearch: home_search(
                             query: {
                                 %s
                                 nearby: {
                                     coordinates: $coordinates
                                     radius: $radius
                                 }
-                                status: %s
+                                %s
                                 %s
                                 %s
                                 %s
@@ -297,7 +427,7 @@ class RealtorScraper(Scraper):
                     ) %s
                 }""" % (
                 is_foreclosure,
-                listing_type.value.lower(),
+                status_param,
                 date_param,
                 property_type_param,
                 property_filters_param,
@@ -306,21 +436,15 @@ class RealtorScraper(Scraper):
                 GENERAL_RESULTS_QUERY,
             )
         elif search_type == "area":  #: general search, came from a general location
-            query = """query Home_search(
+            query = """query GetHomeSearch(
-                                $city: String,
+                                $search_location: SearchLocation,
-                                $county: [String],
+                                $offset: Int
-                                $state_code: String,
-                                $postal_code: String
-                                $offset: Int,
                             ) {
-                                home_search(
+                                homeSearch: home_search(
                                     query: {
                                         %s
-                                        city: $city
+                                        search_location: $search_location
-                                        county: $county
+                                        %s
-                                        postal_code: $postal_code
-                                        state_code: $state_code
-                                        status: %s
                                         %s
                                         %s
                                         %s
@@ -333,7 +457,7 @@ class RealtorScraper(Scraper):
                                 ) %s
                             }""" % (
                 is_foreclosure,
-                listing_type.value.lower(),
+                status_param,
                 date_param,
                 property_type_param,
                 property_filters_param,
@@ -344,11 +468,11 @@ class RealtorScraper(Scraper):
             )
         else:  #: general search, came from an address
             query = (
-                """query Property_search(
+                """query GetHomeSearch(
                         $property_id: [ID]!
                         $offset: Int!,
                     ) {
-                        home_search(
+                        homeSearch: home_search(
                             query: {
                                 property_id: $property_id
                             }
@@ -359,14 +483,8 @@ class RealtorScraper(Scraper):
                 % GENERAL_RESULTS_QUERY
             )
 
-        payload = {
+        response_json = self._graphql_post(query, variables, "GetHomeSearch")
-            "query": query,
+        search_key = "homeSearch"
-            "variables": variables,
-        }
-
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
-        search_key = "home_search" if "home_search" in query else "property_search"
 
         properties: list[Union[Property, dict]] = []
 
@@ -455,24 +573,16 @@ class RealtorScraper(Scraper):
                 if not location_info.get("centroid"):
                     return []
 
-                coordinates = list(location_info["centroid"].values())
+                centroid = location_info["centroid"]
+                coordinates = [centroid["lon"], centroid["lat"]]  # GeoJSON order: [lon, lat]
                 search_variables |= {
                     "coordinates": coordinates,
                     "radius": "{}mi".format(self.radius),
                 }
 
-        elif location_type == "postal_code":
+        else:  #: general search (city, county, postal_code, etc.)
             search_variables |= {
-                "postal_code": location_info.get("postal_code"),
+                "search_location": {"location": location_info.get("text")},
-            }
-
-        else:  #: general search, location
-            search_variables |= {
-                "city": location_info.get("city"),
-                "county": location_info.get("county"),
-                "state_code": location_info.get("state_code"),
-                "postal_code": location_info.get("postal_code"),
-
             }
 
         if self.foreclosure:
@@ -482,52 +592,80 @@ class RealtorScraper(Scraper):
         total = result["total"]
         homes = result["properties"]
 
-        with ThreadPoolExecutor() as executor:
+        # Fetch remaining pages based on parallel parameter
-            # Store futures with their offsets to maintain proper sort order
+        if self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
-            # Start from offset + page_size and go up to offset + limit
+            if self.parallel:
-            futures_with_offsets = [
+                # Parallel mode: Fetch all remaining pages in parallel
-                (i, executor.submit(
+                with ThreadPoolExecutor() as executor:
-                    self.general_search,
+                    futures_with_offsets = [
-                    variables=search_variables | {"offset": i},
+                        (i, executor.submit(
-                    search_type=search_type,
+                            self.general_search,
-                ))
+                            variables=search_variables | {"offset": i},
-                for i in range(
+                            search_type=search_type,
+                        ))
+                        for i in range(
+                            self.offset + self.DEFAULT_PAGE_SIZE,
+                            min(total, self.offset + self.limit),
+                            self.DEFAULT_PAGE_SIZE,
+                        )
+                    ]
+
+                    # Collect results and sort by offset to preserve API sort order
+                    results = []
+                    for offset, future in futures_with_offsets:
+                        results.append((offset, future.result()["properties"]))
+
+                    results.sort(key=lambda x: x[0])
+                    for offset, properties in results:
+                        homes.extend(properties)
+            else:
+                # Sequential mode: Fetch pages one by one with early termination checks
+                for current_offset in range(
                     self.offset + self.DEFAULT_PAGE_SIZE,
                     min(total, self.offset + self.limit),
                     self.DEFAULT_PAGE_SIZE,
-                )
+                ):
-            ]
+                    # Check if we should continue based on time-based filters
+                    if not self._should_fetch_more_pages(homes):
+                        break
 
-            # Collect results and sort by offset to preserve API sort order across pages
+                    result = self.general_search(
-            results = []
+                        variables=search_variables | {"offset": current_offset},
-            for offset, future in futures_with_offsets:
+                        search_type=search_type,
-                results.append((offset, future.result()["properties"]))
+                    )
-
+                    page_properties = result["properties"]
-            # Sort by offset and concatenate in correct order
+                    homes.extend(page_properties)
-            results.sort(key=lambda x: x[0])
-            for offset, properties in results:
-                homes.extend(properties)
 
         # Apply client-side hour-based filtering if needed
         # (API only supports day-level filtering, so we post-filter for hour precision)
-        if self.past_hours or self.datetime_from or self.datetime_to:
+        has_hour_precision = (self.date_from_precision == "hour" or self.date_to_precision == "hour")
+        if self.past_hours or has_hour_precision:
             homes = self._apply_hour_based_date_filter(homes)
         # Apply client-side date filtering for PENDING properties
         # (server-side filters are broken in the API)
         elif self.listing_type == ListingType.PENDING and (self.last_x_days or self.date_from):
             homes = self._apply_pending_date_filter(homes)
 
+        # Apply client-side filtering by last_update_date if specified
+        if self.updated_since or self.updated_in_past_hours:
+            homes = self._apply_last_update_date_filter(homes)
+
         # Apply client-side sort to ensure results are properly ordered
         # This is necessary after filtering and to guarantee sort order across page boundaries
         if self.sort_by:
             homes = self._apply_sort(homes)
 
+        # Apply raw data filters (exclude_pending and mls_only) for raw return type
+        # These filters are normally applied in process_property() but are bypassed for raw data
+        if self.return_type == ReturnType.raw:
+            homes = self._apply_raw_data_filters(homes)
+
         return homes
 
     def _apply_hour_based_date_filter(self, homes):
         """Apply client-side hour-based date filtering for all listing types.
 
-        This is used when past_hours, datetime_from, or datetime_to are specified,
+        This is used when past_hours or date_from/date_to have hour precision,
         since the API only supports day-level filtering.
         """
         if not homes:
@@ -541,17 +679,17 @@ class RealtorScraper(Scraper):
         if self.past_hours:
             cutoff_datetime = datetime.now() - timedelta(hours=self.past_hours)
             date_range = {'type': 'since', 'date': cutoff_datetime}
-        elif self.datetime_from or self.datetime_to:
+        elif self.date_from or self.date_to:
             try:
                 from_datetime = None
                 to_datetime = None
 
-                if self.datetime_from:
+                if self.date_from:
-                    from_datetime_str = self.datetime_from.replace('Z', '+00:00') if self.datetime_from.endswith('Z') else self.datetime_from
+                    from_datetime_str = self.date_from.replace('Z', '+00:00') if self.date_from.endswith('Z') else self.date_from
                     from_datetime = datetime.fromisoformat(from_datetime_str).replace(tzinfo=None)
 
-                if self.datetime_to:
+                if self.date_to:
-                    to_datetime_str = self.datetime_to.replace('Z', '+00:00') if self.datetime_to.endswith('Z') else self.datetime_to
+                    to_datetime_str = self.date_to.replace('Z', '+00:00') if self.date_to.endswith('Z') else self.date_to
                     to_datetime = datetime.fromisoformat(to_datetime_str).replace(tzinfo=None)
 
                 if from_datetime and to_datetime:
@@ -684,17 +822,66 @@ class RealtorScraper(Scraper):
                 return getattr(home.flags, 'is_contingent', False)
             return False
 
+    def _apply_last_update_date_filter(self, homes):
+        """Apply client-side filtering by last_update_date.
+
+        This is used when updated_since or updated_in_past_hours are specified.
+        Filters properties based on when they were last updated.
+        """
+        if not homes:
+            return homes
+
+        from datetime import datetime, timedelta, timezone
+
+        # Determine date range for last_update_date filtering
+        date_range = None
+
+        if self.updated_in_past_hours:
+            # Use UTC now, strip timezone to match naive property dates
+            cutoff_datetime = (datetime.now(timezone.utc) - timedelta(hours=self.updated_in_past_hours)).replace(tzinfo=None)
+            date_range = {'type': 'since', 'date': cutoff_datetime}
+        elif self.updated_since:
+            try:
+                since_datetime_str = self.updated_since.replace('Z', '+00:00') if self.updated_since.endswith('Z') else self.updated_since
+                since_datetime = datetime.fromisoformat(since_datetime_str).replace(tzinfo=None)
+                date_range = {'type': 'since', 'date': since_datetime}
+            except (ValueError, AttributeError):
+                return homes  # If parsing fails, return unfiltered
+
+        if not date_range:
+            return homes
+
+        filtered_homes = []
+
+        for home in homes:
+            # Extract last_update_date from the property
+            property_date = self._extract_date_from_home(home, 'last_update_date')
+
+            # Skip properties without last_update_date
+            if property_date is None:
+                continue
+
+            # Check if property date falls within the specified range
+            if self._is_datetime_in_range(property_date, date_range):
+                filtered_homes.append(home)
+
+        return filtered_homes
+
     def _get_date_range(self):
         """Get the date range for filtering based on instance parameters."""
-        from datetime import datetime, timedelta
+        from datetime import datetime, timedelta, timezone
 
         if self.last_x_days:
-            cutoff_date = datetime.now() - timedelta(days=self.last_x_days)
+            # Use UTC now, strip timezone to match naive property dates
+            cutoff_date = (datetime.now(timezone.utc) - timedelta(days=self.last_x_days)).replace(tzinfo=None)
             return {'type': 'since', 'date': cutoff_date}
         elif self.date_from and self.date_to:
             try:
-                from_date = datetime.fromisoformat(self.date_from)
+                # Parse and strip timezone to match naive property dates
-                to_date = datetime.fromisoformat(self.date_to)
+                from_date_str = self.date_from.replace('Z', '+00:00') if self.date_from.endswith('Z') else self.date_from
+                to_date_str = self.date_to.replace('Z', '+00:00') if self.date_to.endswith('Z') else self.date_to
+                from_date = datetime.fromisoformat(from_date_str).replace(tzinfo=None)
+                to_date = datetime.fromisoformat(to_date_str).replace(tzinfo=None)
                 return {'type': 'range', 'from_date': from_date, 'to_date': to_date}
             except ValueError:
                 return None
@@ -746,6 +933,74 @@ class RealtorScraper(Scraper):
             return date_range['from_date'] <= date_obj <= date_range['to_date']
         return False
 
+    def _should_fetch_more_pages(self, first_page):
+        """Determine if we should continue pagination based on first page results.
+
+        This optimization prevents unnecessary API calls when using time-based filters
+        with date sorting. If the last property on page 1 is already outside the time
+        window, all future pages will also be outside (due to sort order).
+
+        Args:
+            first_page: List of properties from the first page
+
+        Returns:
+            bool: True if we should continue pagination, False to stop early
+        """
+        from datetime import datetime, timedelta, timezone
+
+        # Check for last_update_date filters
+        if (self.updated_since or self.updated_in_past_hours) and self.sort_by == "last_update_date":
+            if not first_page:
+                return False
+
+            last_property = first_page[-1]
+            last_date = self._extract_date_from_home(last_property, 'last_update_date')
+
+            if not last_date:
+                return True
+
+            # Build date range for last_update_date filter
+            if self.updated_since:
+                try:
+                    cutoff_datetime = datetime.fromisoformat(self.updated_since.replace('Z', '+00:00') if self.updated_since.endswith('Z') else self.updated_since)
+                    # Strip timezone to match naive datetimes from _parse_date_value
+                    cutoff_datetime = cutoff_datetime.replace(tzinfo=None)
+                    date_range = {'type': 'since', 'date': cutoff_datetime}
+                except ValueError:
+                    return True
+            elif self.updated_in_past_hours:
+                # Use UTC now, strip timezone to match naive property dates
+                cutoff_datetime = (datetime.now(timezone.utc) - timedelta(hours=self.updated_in_past_hours)).replace(tzinfo=None)
+                date_range = {'type': 'since', 'date': cutoff_datetime}
+            else:
+                return True
+
+            return self._is_datetime_in_range(last_date, date_range)
+
+        # Check for PENDING date filters
+        if (self.listing_type == ListingType.PENDING and
+            (self.last_x_days or self.past_hours or self.date_from) and
+            self.sort_by == "pending_date"):
+
+            if not first_page:
+                return False
+
+            last_property = first_page[-1]
+            last_date = self._extract_date_from_home(last_property, 'pending_date')
+
+            if not last_date:
+                return True
+
+            # Build date range for pending date filter
+            date_range = self._get_date_range()
+            if not date_range:
+                return True
+
+            return self._is_datetime_in_range(last_date, date_range)
+
+        # No optimization applicable, continue pagination
+        return True
+
     def _apply_sort(self, homes):
         """Apply client-side sorting to ensure results are properly ordered.
 
@@ -764,6 +1019,8 @@ class RealtorScraper(Scraper):
 
         def get_sort_key(home):
             """Extract the sort field value from a home (handles both dict and Property object)."""
+            from datetime import datetime
+
             if isinstance(home, dict):
                 value = home.get(self.sort_by)
             else:
@@ -776,23 +1033,26 @@ class RealtorScraper(Scraper):
                 return (1, 0) if self.sort_direction == "desc" else (1, float('inf'))
 
             # For datetime fields, convert string to datetime for proper sorting
-            if self.sort_by in ['list_date', 'sold_date', 'pending_date']:
+            if self.sort_by in ['list_date', 'sold_date', 'pending_date', 'last_update_date']:
                 if isinstance(value, str):
                     try:
-                        from datetime import datetime
                         # Handle timezone indicators
                         date_value = value
                         if date_value.endswith('Z'):
                             date_value = date_value[:-1] + '+00:00'
                         parsed_date = datetime.fromisoformat(date_value)
-                        return (0, parsed_date)
+                        # Normalize to timezone-naive for consistent comparison
+                        return 0, parsed_date.replace(tzinfo=None)
                     except (ValueError, AttributeError):
                         # If parsing fails, treat as None
                         return (1, 0) if self.sort_direction == "desc" else (1, float('inf'))
-                return (0, value)
+                # Handle datetime objects directly (normalize timezone)
+                if isinstance(value, datetime):
+                    return 0, value.replace(tzinfo=None)
+                return 0, value
 
             # For numeric fields, ensure we can compare
-            return (0, value)
+            return 0, value
 
         # Sort the homes
         reverse = (self.sort_direction == "desc")
@@ -800,11 +1060,52 @@ class RealtorScraper(Scraper):
 
         return sorted_homes
 
+    def _apply_raw_data_filters(self, homes):
+        """Apply exclude_pending and mls_only filters for raw data returns.
+
+        These filters are normally applied in process_property(), but that function
+        is bypassed when return_type="raw", so we need to apply them here instead.
+
+        Args:
+            homes: List of properties (either dicts or Property objects)
+
+        Returns:
+            Filtered list of properties
+        """
+        if not homes:
+            return homes
+
+        # Only filter raw data (dict objects)
+        # Property objects have already been filtered in process_property()
+        if homes and not isinstance(homes[0], dict):
+            return homes
+
+        filtered_homes = []
+
+        for home in homes:
+            # Apply exclude_pending filter
+            if self.exclude_pending and self.listing_type != ListingType.PENDING:
+                flags = home.get('flags', {})
+                is_pending = flags.get('is_pending', False)
+                is_contingent = flags.get('is_contingent', False)
+
+                if is_pending or is_contingent:
+                    continue  # Skip this property
+
+            # Apply mls_only filter
+            if self.mls_only:
+                source = home.get('source', {})
+                if not source or not source.get('id'):
+                    continue  # Skip this property
+
+            filtered_homes.append(home)
+
+        return filtered_homes
 
 
     @retry(
-        retry=retry_if_exception_type(JSONDecodeError),
+        retry=retry_if_exception_type((JSONDecodeError, Exception)) & retry_if_not_exception_type(AuthenticationError),
-        wait=wait_exponential(min=4, max=10),
+        wait=wait_exponential(multiplier=1, min=1, max=10),
         stop=stop_after_attempt(3),
     )
     def get_bulk_prop_details(self, property_ids: list[str]) -> dict:
@@ -817,24 +1118,25 @@ class RealtorScraper(Scraper):
 
         property_ids = list(set(property_ids))
 
-        # Construct the bulk query
         fragments = "\n".join(
-            f'home_{property_id}: home(property_id: {property_id}) {{ ...HomeData }}'
+            f'home_{property_id}: home(property_id: {property_id}) {HOMES_DATA}'
             for property_id in property_ids
         )
-        query = f"""{HOME_FRAGMENT}
+        query = f"""query GetHome {{
+    {fragments}
+}}"""
 
-        query GetHomes {{
+        data = self._graphql_post(query, {}, "GetHome")
-            {fragments}
-        }}"""
 
-        response = self.session.post(self.SEARCH_GQL_URL, json={"query": query})
+        if "data" not in data or data["data"] is None:
-        data = response.json()
+            # If we got a 400 error with "Required parameter is missing", raise to trigger retry
-
+            if data and "errors" in data:
-        if "data" not in data:
+                error_msgs = [e.get("message", "") for e in data.get("errors", [])]
+                if any("Required parameter is missing" in msg for msg in error_msgs):
+                    raise Exception(f"Transient API error: {error_msgs}")
             return {}
 
         properties = data["data"]
-        return {data.replace('home_', ''): properties[data] for data in properties if properties[data]}
+        return {key.replace('home_', ''): properties[key] for key in properties if properties[key]}
 
 

homeharvest/core/scrapers/realtor/processors.py

@@ -126,6 +126,7 @@ def process_property(result: dict, mls_only: bool = False, extra_property_data:
         last_sold_date=(datetime.fromisoformat(result["last_sold_date"].replace('Z', '+00:00') if result["last_sold_date"].endswith('Z') else result["last_sold_date"]) if result.get("last_sold_date") else None),
         pending_date=(datetime.fromisoformat(result["pending_date"].replace('Z', '+00:00') if result["pending_date"].endswith('Z') else result["pending_date"]) if result.get("pending_date") else None),
         last_status_change_date=(datetime.fromisoformat(result["last_status_change_date"].replace('Z', '+00:00') if result["last_status_change_date"].endswith('Z') else result["last_status_change_date"]) if result.get("last_status_change_date") else None),
+        last_update_date=(datetime.fromisoformat(result["last_update_date"].replace('Z', '+00:00') if result["last_update_date"].endswith('Z') else result["last_update_date"]) if result.get("last_update_date") else None),
         new_construction=result["flags"].get("is_new_construction") is True,
         hoa_fee=(result["hoa"]["fee"] if result.get("hoa") and isinstance(result["hoa"], dict) else None),
         latitude=(result["location"]["address"]["coordinate"].get("lat") if able_to_get_lat_long else None),

homeharvest/core/scrapers/realtor/queries.py

@@ -1,3 +1,193 @@
+SEARCH_RESULTS_FRAGMENT = """
+fragment PropertyResult on SearchHome {
+    __typename
+    pending_date
+    listing_id
+    property_id
+    href
+    permalink
+    list_date
+    status
+    mls_status
+    last_sold_price
+    last_sold_date
+    last_status_change_date
+    last_update_date
+    list_price
+    list_price_max
+    list_price_min
+    price_per_sqft
+    tags
+    open_houses {
+        start_date
+        end_date
+        description
+        time_zone
+        dst
+        href
+        methods
+    }
+    details {
+        category
+        text
+        parent_category
+    }
+    pet_policy {
+        cats
+        dogs
+        dogs_small
+        dogs_large
+        __typename
+    }
+    units {
+        availability {
+          date
+          __typename
+        }
+        description {
+          baths_consolidated
+          baths
+          beds
+          sqft
+          __typename
+        }
+        photos(https: true) {
+            title
+            href
+            tags {
+                label
+            }
+        }
+        list_price
+        __typename
+    }
+    flags {
+        is_contingent
+        is_pending
+        is_new_construction
+    }
+    description {
+        type
+        sqft
+        beds
+        baths_full
+        baths_half
+        lot_sqft
+        year_built
+        garage
+        type
+        name
+        stories
+        text
+    }
+    source {
+        id
+        listing_id
+    }
+    hoa {
+        fee
+    }
+    location {
+        address {
+            street_direction
+            street_number
+            street_name
+            street_suffix
+            line
+            unit
+            city
+            state_code
+            postal_code
+            coordinate {
+                lon
+                lat
+            }
+        }
+        county {
+            name
+            fips_code
+        }
+        neighborhoods {
+            name
+        }
+    }
+    tax_record {
+        cl_id
+        public_record_id
+        last_update_date
+        apn
+        tax_parcel_id
+    }
+    primary_photo(https: true) {
+        href
+    }
+    advertisers {
+        email
+        broker {
+            name
+            fulfillment_id
+        }
+        type
+        name
+        fulfillment_id
+        builder {
+            name
+            fulfillment_id
+        }
+        phones {
+            ext
+            primary
+            type
+            number
+        }
+        office {
+            name
+            email
+            fulfillment_id
+            href
+            phones {
+                number
+                type
+                primary
+                ext
+            }
+            mls_set
+        }
+        corporation {
+            specialties
+            name
+            bio
+            href
+            fulfillment_id
+        }
+        mls_set
+        nrds_id
+        state_license
+        rental_corporation {
+            fulfillment_id
+        }
+        rental_management {
+            name
+            href
+            fulfillment_id
+        }
+    }
+    current_estimates {
+        __typename
+        source {
+            __typename
+            type
+            name
+        }
+        estimate
+        estimateHigh: estimate_high
+        estimateLow: estimate_low
+        date
+        isBestHomeValue: isbest_homevalue
+    }
+}
+"""
+
 _SEARCH_HOMES_DATA_BASE = """{
     pending_date
     listing_id
@@ -10,6 +200,7 @@ _SEARCH_HOMES_DATA_BASE = """{
     last_sold_price
     last_sold_date
     last_status_change_date
+    last_update_date
     list_price
     list_price_max
     list_price_min
@@ -180,8 +371,189 @@ _SEARCH_HOMES_DATA_BASE = """{
 
 
 HOME_FRAGMENT = """
-fragment HomeData on Home {
+fragment PropertyResult on Home {
+    __typename
+    pending_date
+    listing_id
     property_id
+    href
+    permalink
+    list_date
+    status
+    mls_status
+    last_sold_price
+    last_sold_date
+    last_status_change_date
+    last_update_date
+    list_price
+    list_price_max
+    list_price_min
+    price_per_sqft
+    tags
+    open_houses {
+        start_date
+        end_date
+        description
+        time_zone
+        dst
+        href
+        methods
+    }
+    details {
+        category
+        text
+        parent_category
+    }
+    pet_policy {
+        cats
+        dogs
+        dogs_small
+        dogs_large
+        __typename
+    }
+    units {
+        availability {
+          date
+          __typename
+        }
+        description {
+          baths_consolidated
+          baths
+          beds
+          sqft
+          __typename
+        }
+        photos(https: true) {
+            title
+            href
+            tags {
+                label
+            }
+        }
+        list_price
+        __typename
+    }
+    flags {
+        is_contingent
+        is_pending
+        is_new_construction
+    }
+    description {
+        type
+        sqft
+        beds
+        baths_full
+        baths_half
+        lot_sqft
+        year_built
+        garage
+        type
+        name
+        stories
+        text
+    }
+    source {
+        id
+        listing_id
+    }
+    hoa {
+        fee
+    }
+    location {
+        address {
+            street_direction
+            street_number
+            street_name
+            street_suffix
+            line
+            unit
+            city
+            state_code
+            postal_code
+            coordinate {
+                lon
+                lat
+            }
+        }
+        county {
+            name
+            fips_code
+        }
+        neighborhoods {
+            name
+        }
+        parcel {
+            parcel_id
+        }
+    }
+    tax_record {
+        cl_id
+        public_record_id
+        last_update_date
+        apn
+        tax_parcel_id
+    }
+    primary_photo(https: true) {
+        href
+    }
+    photos(https: true) {
+        title
+        href
+        tags {
+            label
+        }
+    }
+    advertisers {
+        email
+        broker {
+            name
+            fulfillment_id
+        }
+        type
+        name
+        fulfillment_id
+        builder {
+            name
+            fulfillment_id
+        }
+        phones {
+            ext
+            primary
+            type
+            number
+        }
+        office {
+            name
+            email
+            fulfillment_id
+            href
+            phones {
+                number
+                type
+                primary
+                ext
+            }
+            mls_set
+        }
+        corporation {
+            specialties
+            name
+            bio
+            href
+            fulfillment_id
+        }
+        mls_set
+        nrds_id
+        state_license
+        rental_corporation {
+            fulfillment_id
+        }
+        rental_management {
+            name
+            href
+            fulfillment_id
+        }
+    }
     nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) {
         __typename schools { district { __typename id name } }
     }
@@ -197,11 +569,6 @@ fragment HomeData on Home {
             last_n_days
         }
     }
-    location {
-        parcel {
-            parcel_id
-        }
-    }
     taxHistory: tax_history { __typename tax year assessment { __typename building land total } }
     property_history {
         date
@@ -226,6 +593,18 @@ fragment HomeData on Home {
         text
         category
     }
+    estimates {
+        __typename
+        currentValues: current_values {
+            __typename
+            source { __typename type name }
+            estimate
+            estimateHigh: estimate_high
+            estimateLow: estimate_low
+            date
+            isBestHomeValue: isbest_homevalue
+        }
+    }
 }
 """
 
@@ -299,8 +678,128 @@ current_estimates {
 }
 }""" % _SEARCH_HOMES_DATA_BASE
 
-GENERAL_RESULTS_QUERY = """{
+# Query body using inline fields (kept for backward compatibility)
+GENERAL_RESULTS_QUERY_BODY = """{
                             count
                             total
                             results %s
                         }""" % SEARCH_HOMES_DATA
+
+GENERAL_RESULTS_QUERY = """{
+                            __typename
+                            count
+                            total
+                            results %s
+                        }""" % SEARCH_HOMES_DATA
+
+LISTING_PHOTOS_FRAGMENT = """
+fragment ListingPhotosFragment on SearchHome {
+    __typename
+    photos(https: true) {
+        __typename
+        title
+        href
+        tags {
+            __typename
+            label
+            probability
+        }
+    }
+}
+"""
+
+SEARCH_SUGGESTIONS_QUERY = """query Search_suggestions($searchInput: SearchSuggestionsInput!) {
+  search_suggestions(search_input: $searchInput) {
+    raw_input_parser_result
+    typeahead_results {
+      display_string
+      display_geo
+      geo {
+        _id
+        _score
+        mpr_id
+        area_type
+        city
+        state_code
+        state
+        postal_code
+        country
+        lat
+        lon
+        county
+        counties {
+          name
+          fips
+          state_code
+        }
+        slug_id
+        geo_id
+        score
+        name
+        city_slug_id
+        centroid {
+          lat
+          lon
+        }
+        county_needed_for_uniq
+        street
+        line
+        school
+        school_id
+        school_district
+        has_catchment
+        university
+        university_id
+        neighborhood
+        park
+      }
+      url
+    }
+    geo_results {
+      type
+      text
+      geo {
+        _id
+        _score
+        mpr_id
+        area_type
+        city
+        state_code
+        state
+        postal_code
+        country
+        lat
+        lon
+        county
+        counties {
+          name
+          fips
+          state_code
+        }
+        slug_id
+        geo_id
+        score
+        name
+        city_slug_id
+        centroid {
+          lat
+          lon
+        }
+        county_needed_for_uniq
+        street
+        line
+        school
+        school_id
+        school_district
+        has_catchment
+        university
+        university_id
+        neighborhood
+        park
+      }
+    }
+    no_matches
+    has_results
+    original_string
+  }
+}"""

homeharvest/utils.py

@@ -38,6 +38,7 @@ ordered_properties = [
     "last_sold_date",
     "last_sold_price",
     "last_status_change_date",
+    "last_update_date",
     "assessed_value",
     "estimated_value",
     "tax",
@@ -156,24 +157,45 @@ def process_result(result: Property) -> pd.DataFrame:
     return properties_df[ordered_properties]
 
 
-def validate_input(listing_type: str) -> None:
+def validate_input(listing_type: str | list[str] | None) -> None:
-    if listing_type.upper() not in ListingType.__members__:
+    if listing_type is None:
-        raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
+        return  # None is valid - returns all types
+
+    if isinstance(listing_type, list):
+        for lt in listing_type:
+            if lt.upper() not in ListingType.__members__:
+                raise InvalidListingType(f"Provided listing type, '{lt}', does not exist.")
+    else:
+        if listing_type.upper() not in ListingType.__members__:
+            raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
 
 
 def validate_dates(date_from: str | None, date_to: str | None) -> None:
-    if isinstance(date_from, str) != isinstance(date_to, str):
+    # Allow either date_from or date_to individually, or both together
-        raise InvalidDate("Both date_from and date_to must be provided.")
+    try:
+        # Validate and parse date_from if provided
+        date_from_obj = None
+        if date_from:
+            date_from_str = date_from.replace('Z', '+00:00') if date_from.endswith('Z') else date_from
+            date_from_obj = datetime.fromisoformat(date_from_str)
 
-    if date_from and date_to:
+        # Validate and parse date_to if provided
-        try:
+        date_to_obj = None
-            date_from_obj = datetime.strptime(date_from, "%Y-%m-%d")
+        if date_to:
-            date_to_obj = datetime.strptime(date_to, "%Y-%m-%d")
+            date_to_str = date_to.replace('Z', '+00:00') if date_to.endswith('Z') else date_to
+            date_to_obj = datetime.fromisoformat(date_to_str)
 
-            if date_to_obj < date_from_obj:
+        # If both provided, ensure date_to is after date_from
-                raise InvalidDate("date_to must be after date_from.")
+        if date_from_obj and date_to_obj and date_to_obj < date_from_obj:
-        except ValueError:
+            raise InvalidDate(f"date_to ('{date_to}') must be after date_from ('{date_from}').")
-            raise InvalidDate(f"Invalid date format or range")
+
+    except ValueError as e:
+        # Provide specific guidance on the expected format
+        raise InvalidDate(
+            f"Invalid date format. Expected ISO 8601 format. "
+            f"Examples: '2025-01-20' (date only) or '2025-01-20T14:30:00' (with time). "
+            f"Got: date_from='{date_from}', date_to='{date_to}'. Error: {e}"
+        )
 
 
 def validate_limit(limit: int) -> None:
@@ -213,21 +235,53 @@ def validate_offset(offset: int, limit: int = 10000) -> None:
         )
 
 
-def validate_datetime(datetime_str: str | None) -> None:
+def validate_datetime(datetime_value) -> None:
-    """Validate ISO 8601 datetime format."""
+    """Validate datetime value (accepts datetime objects or ISO 8601 strings)."""
-    if not datetime_str:
+    if datetime_value is None:
         return
 
+    # Already a datetime object - valid
+    from datetime import datetime as dt, date
+    if isinstance(datetime_value, (dt, date)):
+        return
+
+    # Must be a string - validate ISO 8601 format
+    if not isinstance(datetime_value, str):
+        raise InvalidDate(
+            f"Invalid datetime value. Expected datetime object, date object, or ISO 8601 string. "
+            f"Got: {type(datetime_value).__name__}"
+        )
+
     try:
         # Try parsing as ISO 8601 datetime
-        datetime.fromisoformat(datetime_str.replace('Z', '+00:00'))
+        datetime.fromisoformat(datetime_value.replace('Z', '+00:00'))
     except (ValueError, AttributeError):
         raise InvalidDate(
-            f"Invalid datetime format: '{datetime_str}'. "
+            f"Invalid datetime format: '{datetime_value}'. "
             f"Expected ISO 8601 format (e.g., '2025-01-20T14:30:00' or '2025-01-20')."
         )
 
 
+def validate_last_update_filters(updated_since: str | None, updated_in_past_hours: int | None) -> None:
+    """Validate last_update_date filtering parameters."""
+    if updated_since and updated_in_past_hours:
+        raise ValueError(
+            "Cannot use both 'updated_since' and 'updated_in_past_hours' parameters together. "
+            "Please use only one method to filter by last_update_date."
+        )
+
+    # Validate updated_since format if provided
+    if updated_since:
+        validate_datetime(updated_since)
+
+    # Validate updated_in_past_hours range if provided
+    if updated_in_past_hours is not None:
+        if updated_in_past_hours < 1:
+            raise ValueError(
+                f"updated_in_past_hours must be at least 1. Got: {updated_in_past_hours}"
+            )
+
+
 def validate_filters(
     beds_min: int | None = None,
     beds_max: int | None = None,
@@ -259,7 +313,7 @@ def validate_filters(
 
 def validate_sort(sort_by: str | None, sort_direction: str | None = "desc") -> None:
     """Validate sort parameters."""
-    valid_sort_fields = ["list_date", "sold_date", "list_price", "sqft", "beds", "baths"]
+    valid_sort_fields = ["list_date", "sold_date", "list_price", "sqft", "beds", "baths", "last_update_date"]
     valid_directions = ["asc", "desc"]
 
     if sort_by and sort_by not in valid_sort_fields:
@@ -273,3 +327,159 @@ def validate_sort(sort_by: str | None, sort_direction: str | None = "desc") -> N
             f"Invalid sort_direction value: '{sort_direction}'. "
             f"Valid options: {', '.join(valid_directions)}"
         )
+
+
+def convert_to_datetime_string(value) -> str | None:
+    """
+    Convert datetime object or string to ISO 8601 string format with UTC timezone.
+
+    Accepts:
+    - datetime.datetime objects (naive or timezone-aware)
+      - Naive datetimes are treated as local time and converted to UTC
+      - Timezone-aware datetimes are converted to UTC
+    - datetime.date objects (treated as midnight UTC)
+    - ISO 8601 strings (returned as-is)
+    - None (returns None)
+
+    Returns ISO 8601 formatted string with UTC timezone or None.
+
+    Examples:
+        >>> # Naive datetime (treated as local time)
+        >>> convert_to_datetime_string(datetime(2025, 1, 20, 14, 30))
+        '2025-01-20T22:30:00+00:00'  # Assuming PST (UTC-8)
+
+        >>> # Timezone-aware datetime
+        >>> convert_to_datetime_string(datetime(2025, 1, 20, 14, 30, tzinfo=timezone.utc))
+        '2025-01-20T14:30:00+00:00'
+    """
+    if value is None:
+        return None
+
+    # Already a string - return as-is
+    if isinstance(value, str):
+        return value
+
+    # datetime.datetime object
+    from datetime import datetime, date, timezone
+    if isinstance(value, datetime):
+        # Handle naive datetime - treat as local time and convert to UTC
+        if value.tzinfo is None:
+            # Convert naive datetime to aware local time, then to UTC
+            local_aware = value.astimezone()
+            utc_aware = local_aware.astimezone(timezone.utc)
+            return utc_aware.isoformat()
+        else:
+            # Already timezone-aware, convert to UTC
+            utc_aware = value.astimezone(timezone.utc)
+            return utc_aware.isoformat()
+
+    # datetime.date object (convert to datetime at midnight UTC)
+    if isinstance(value, date):
+        utc_datetime = datetime.combine(value, datetime.min.time()).replace(tzinfo=timezone.utc)
+        return utc_datetime.isoformat()
+
+    raise ValueError(
+        f"Invalid datetime value. Expected datetime object, date object, or ISO 8601 string. "
+        f"Got: {type(value).__name__}"
+    )
+
+
+def extract_timedelta_hours(value) -> int | None:
+    """
+    Extract hours from int or timedelta object.
+
+    Accepts:
+    - int (returned as-is)
+    - timedelta objects (converted to total hours)
+    - None (returns None)
+
+    Returns integer hours or None.
+    """
+    if value is None:
+        return None
+
+    # Already an int - return as-is
+    if isinstance(value, int):
+        return value
+
+    # timedelta object - convert to hours
+    from datetime import timedelta
+    if isinstance(value, timedelta):
+        return int(value.total_seconds() / 3600)
+
+    raise ValueError(
+        f"Invalid past_hours value. Expected int or timedelta object. "
+        f"Got: {type(value).__name__}"
+    )
+
+
+def extract_timedelta_days(value) -> int | None:
+    """
+    Extract days from int or timedelta object.
+
+    Accepts:
+    - int (returned as-is)
+    - timedelta objects (converted to total days)
+    - None (returns None)
+
+    Returns integer days or None.
+    """
+    if value is None:
+        return None
+
+    # Already an int - return as-is
+    if isinstance(value, int):
+        return value
+
+    # timedelta object - convert to days
+    from datetime import timedelta
+    if isinstance(value, timedelta):
+        return int(value.total_seconds() / 86400)  # 86400 seconds in a day
+
+    raise ValueError(
+        f"Invalid past_days value. Expected int or timedelta object. "
+        f"Got: {type(value).__name__}"
+    )
+
+
+def detect_precision_and_convert(value):
+    """
+    Detect if input has time precision and convert to ISO string.
+
+    Accepts:
+    - datetime.datetime objects → (ISO string, "hour")
+    - datetime.date objects → (ISO string at midnight, "day")
+    - ISO 8601 datetime strings with time → (string as-is, "hour")
+    - Date-only strings "YYYY-MM-DD" → (string as-is, "day")
+    - None → (None, None)
+
+    Returns:
+        tuple: (iso_string, precision) where precision is "day" or "hour"
+    """
+    if value is None:
+        return (None, None)
+
+    from datetime import datetime as dt, date
+
+    # datetime.datetime object - has time precision
+    if isinstance(value, dt):
+        return (value.isoformat(), "hour")
+
+    # datetime.date object - day precision only
+    if isinstance(value, date):
+        # Convert to datetime at midnight
+        return (dt.combine(value, dt.min.time()).isoformat(), "day")
+
+    # String - detect if it has time component
+    if isinstance(value, str):
+        # ISO 8601 datetime with time component (has 'T' and time)
+        if 'T' in value:
+            return (value, "hour")
+        # Date-only string
+        else:
+            return (value, "day")
+
+    raise ValueError(
+        f"Invalid date value. Expected datetime object, date object, or ISO 8601 string. "
+        f"Got: {type(value).__name__}"
+    )

pyproject.toml

@@ -1,14 +1,11 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.7.2"
+version = "0.8.18"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/ZacharyHampton/HomeHarvest"
 readme = "README.md"
 
-[tool.poetry.scripts]
-homeharvest = "homeharvest.cli:main"
-
 [tool.poetry.dependencies]
 python = ">=3.9"
 requests = "^2.32.4"

tests/test_realtor.py

@@ -1,3 +1,6 @@
+import pytz
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
 from homeharvest import scrape_property, Property
 import pandas as pd
 
@@ -85,6 +88,25 @@ def test_realtor_date_range_sold():
     )
 
 
+def test_listing_type_none_includes_sold():
+    """Test that listing_type=None includes sold listings (issue #142)"""
+    # Get properties with listing_type=None (should include all common types)
+    result_none = scrape_property(
+        location="Warren, MI",
+        listing_type=None
+    )
+
+    # Verify we got results
+    assert result_none is not None and len(result_none) > 0
+
+    # Verify sold listings are included
+    status_types = set(result_none['status'].unique())
+    assert 'SOLD' in status_types, "SOLD listings should be included when listing_type=None"
+
+    # Verify we get multiple listing types (not just one)
+    assert len(status_types) > 1, "Should return multiple listing types when listing_type=None"
+
+
 def test_realtor_single_property():
     results = [
         scrape_property(
@@ -169,7 +191,13 @@ def test_realtor_without_extra_details():
         ),
     ]
 
-    assert not results[0].equals(results[1])
+    # When extra_property_data=False, these fields should be None
+    extra_fields = ["nearby_schools", "assessed_value", "tax", "tax_history"]
+
+    # Check that all extra fields are None when extra_property_data=False
+    for field in extra_fields:
+        if field in results[0].columns:
+            assert results[0][field].isna().all(), f"Field '{field}' should be None when extra_property_data=False"
 
 
 def test_pr_zip_code():
@@ -280,13 +308,37 @@ def test_phone_number_matching():
     assert row["agent_phones"].values[0] == matching_row["agent_phones"].values[0]
 
 
+def test_parallel_search_consistency():
+    """Test that the same search executed 3 times in parallel returns consistent results"""
+    def search_task():
+        return scrape_property(
+            location="Phoenix, AZ",
+            listing_type="for_sale",
+            limit=100
+        )
+
+    with ThreadPoolExecutor(max_workers=3) as executor:
+        futures = [executor.submit(search_task) for _ in range(3)]
+        results = [future.result() for future in as_completed(futures)]
+
+    # Verify all results are valid
+    assert all([result is not None for result in results])
+    assert all([isinstance(result, pd.DataFrame) for result in results])
+    assert all([len(result) > 0 for result in results])
+
+    # Verify all results have the same length (primary consistency check)
+    lengths = [len(result) for result in results]
+    assert len(set(lengths)) == 1, \
+        f"All parallel searches should return same number of results, got lengths: {lengths}"
+
+
 def test_return_type():
     results = {
         "pandas": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100)],
         "pydantic": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="pydantic")],
         "raw": [
             scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100, return_type="raw"),
-            scrape_property(location="66642", listing_type="for_rent", limit=100, return_type="raw"),
+            scrape_property(location="85281", listing_type="for_rent", limit=100, return_type="raw"),
         ],
     }
 
@@ -607,7 +659,7 @@ def test_past_hours_all_listing_types():
 
 
 def test_datetime_filtering():
-    """Test datetime_from and datetime_to parameters with hour precision"""
+    """Test date_from and date_to parameters with hour precision"""
     from datetime import datetime, timedelta
 
     # Get a recent date range (e.g., yesterday)
@@ -618,28 +670,28 @@ def test_datetime_filtering():
     result = scrape_property(
         location="Dallas, TX",
         listing_type="for_sale",
-        datetime_from=f"{date_str}T09:00:00",
+        date_from=f"{date_str}T09:00:00",
-        datetime_to=f"{date_str}T17:00:00",
+        date_to=f"{date_str}T17:00:00",
         limit=30
     )
 
     assert result is not None
 
-    # Test with only datetime_from
+    # Test with only date_from
     result_from_only = scrape_property(
         location="Houston, TX",
         listing_type="for_sale",
-        datetime_from=f"{date_str}T00:00:00",
+        date_from=f"{date_str}T00:00:00",
         limit=30
     )
 
     assert result_from_only is not None
 
-    # Test with only datetime_to
+    # Test with only date_to
     result_to_only = scrape_property(
         location="Austin, TX",
         listing_type="for_sale",
-        datetime_to=f"{date_str}T23:59:59",
+        date_to=f"{date_str}T23:59:59",
         limit=30
     )
 
@@ -1106,8 +1158,10 @@ def test_last_status_change_date_field():
     )
 
     assert result_pending is not None
-    assert "last_status_change_date" in result_pending.columns, \
+    # Only check columns if we have results (empty DataFrame has no columns)
-        "last_status_change_date column should be present in PENDING results"
+    if len(result_pending) > 0:
+        assert "last_status_change_date" in result_pending.columns, \
+            "last_status_change_date column should be present in PENDING results"
 
     # Test 3: Field is present in FOR_SALE listings
     result_for_sale = scrape_property(
@@ -1270,3 +1324,317 @@ def test_last_status_change_date_hour_filtering():
                         f"PENDING property pending_date {pending_date} should be within 48 hours of {cutoff_time}"
                 except (ValueError, TypeError):
                     pass  # Skip if parsing fails
+
+
+def test_exclude_pending_with_raw_data():
+    """Test that exclude_pending parameter works correctly with return_type='raw'"""
+
+    # Query for sale properties with exclude_pending=True and raw data
+    result = scrape_property(
+        location="Phoenix, AZ",
+        listing_type="for_sale",
+        exclude_pending=True,
+        return_type="raw",
+        limit=50
+    )
+
+    assert result is not None and len(result) > 0
+
+    # Verify that no pending or contingent properties are in the results
+    for prop in result:
+        flags = prop.get('flags', {})
+        is_pending = flags.get('is_pending', False)
+        is_contingent = flags.get('is_contingent', False)
+
+        assert not is_pending, f"Property {prop.get('property_id')} should not be pending when exclude_pending=True"
+        assert not is_contingent, f"Property {prop.get('property_id')} should not be contingent when exclude_pending=True"
+
+
+def test_mls_only_with_raw_data():
+    """Test that mls_only parameter works correctly with return_type='raw'"""
+
+    # Query with mls_only=True and raw data
+    result = scrape_property(
+        location="Dallas, TX",
+        listing_type="for_sale",
+        mls_only=True,
+        return_type="raw",
+        limit=50
+    )
+
+    assert result is not None and len(result) > 0
+
+    # Verify that all properties have MLS IDs (stored in source.id)
+    for prop in result:
+        source = prop.get('source', {})
+        mls_id = source.get('id') if source else None
+
+        assert mls_id is not None and mls_id != "", \
+            f"Property {prop.get('property_id')} should have an MLS ID (source.id) when mls_only=True, got: {mls_id}"
+
+
+def test_combined_filters_with_raw_data():
+    """Test that both exclude_pending and mls_only work together with return_type='raw'"""
+
+    # Query with both filters enabled and raw data
+    result = scrape_property(
+        location="Austin, TX",
+        listing_type="for_sale",
+        exclude_pending=True,
+        mls_only=True,
+        return_type="raw",
+        limit=30
+    )
+
+    assert result is not None and len(result) > 0
+
+    # Verify both filters are applied
+    for prop in result:
+        # Check exclude_pending filter
+        flags = prop.get('flags', {})
+        is_pending = flags.get('is_pending', False)
+        is_contingent = flags.get('is_contingent', False)
+
+        assert not is_pending, f"Property {prop.get('property_id')} should not be pending"
+        assert not is_contingent, f"Property {prop.get('property_id')} should not be contingent"
+
+        # Check mls_only filter
+        source = prop.get('source', {})
+        mls_id = source.get('id') if source else None
+
+        assert mls_id is not None and mls_id != "", \
+            f"Property {prop.get('property_id')} should have an MLS ID (source.id)"
+
+
+def test_updated_since_filtering():
+    """Test the updated_since parameter for filtering by last_update_date"""
+    from datetime import datetime, timedelta
+
+    # Test 1: Filter by last update in past 10 minutes (user's example)
+    cutoff_time = datetime.now() - timedelta(minutes=10)
+    result_10min = scrape_property(
+        location="California",
+        updated_since=cutoff_time,
+        sort_by="last_update_date",
+        sort_direction="desc",
+        limit=100
+    )
+
+    assert result_10min is not None
+    print(f"\n10-minute window returned {len(result_10min)} properties")
+
+    # Test 2: Verify all results have last_update_date within range
+    if len(result_10min) > 0:
+        for idx in range(min(10, len(result_10min))):
+            update_date_str = result_10min.iloc[idx]["last_update_date"]
+            if pd.notna(update_date_str):
+                try:
+                    # Handle timezone-aware datetime strings
+                    date_str = str(update_date_str)
+                    if '+' in date_str or date_str.endswith('Z'):
+                        # Remove timezone for comparison with naive cutoff_time
+                        date_str = date_str.replace('+00:00', '').replace('Z', '')
+                    update_date = datetime.strptime(date_str, "%Y-%m-%d %H:%M:%S")
+
+                    assert update_date >= cutoff_time, \
+                        f"Property last_update_date {update_date} should be >= {cutoff_time}"
+                    print(f"Property {idx}: last_update_date = {update_date} (valid)")
+                except (ValueError, TypeError) as e:
+                    print(f"Warning: Could not parse date {update_date_str}: {e}")
+
+    # Test 3: Compare different time windows
+    result_1hour = scrape_property(
+        location="California",
+        updated_since=datetime.now() - timedelta(hours=1),
+        limit=50
+    )
+
+    result_24hours = scrape_property(
+        location="California",
+        updated_since=datetime.now() - timedelta(hours=24),
+        limit=50
+    )
+
+    print(f"1-hour window: {len(result_1hour)} properties")
+    print(f"24-hour window: {len(result_24hours)} properties")
+
+    # Longer time window should return same or more results
+    if len(result_1hour) > 0 and len(result_24hours) > 0:
+        assert len(result_1hour) <= len(result_24hours), \
+            "1-hour filter should return <= 24-hour results"
+
+    # Test 4: Verify sorting works with filtering
+    if len(result_10min) > 1:
+        # Get non-null dates
+        dates = []
+        for idx in range(len(result_10min)):
+            date_str = result_10min.iloc[idx]["last_update_date"]
+            if pd.notna(date_str):
+                try:
+                    # Handle timezone-aware datetime strings
+                    clean_date_str = str(date_str)
+                    if '+' in clean_date_str or clean_date_str.endswith('Z'):
+                        clean_date_str = clean_date_str.replace('+00:00', '').replace('Z', '')
+                    dates.append(datetime.strptime(clean_date_str, "%Y-%m-%d %H:%M:%S"))
+                except (ValueError, TypeError):
+                    pass
+
+        if len(dates) > 1:
+            # Check if sorted descending
+            for i in range(len(dates) - 1):
+                assert dates[i] >= dates[i + 1], \
+                    f"Results should be sorted by last_update_date descending: {dates[i]} >= {dates[i+1]}"
+
+
+def test_updated_since_optimization():
+    """Test that updated_since optimization works (auto-sort + early termination)"""
+    from datetime import datetime, timedelta
+    import time
+
+    # Test 1: Verify auto-sort is applied when using updated_since without explicit sort
+    start_time = time.time()
+    result = scrape_property(
+        location="California",
+        updated_since=datetime.now() - timedelta(minutes=5),
+        # NO sort_by specified - should auto-apply sort_by="last_update_date"
+        limit=50
+    )
+    elapsed_time = time.time() - start_time
+
+    print(f"\nAuto-sort test: {len(result)} properties in {elapsed_time:.2f}s")
+
+    # Should complete quickly due to early termination optimization (<5 seconds)
+    assert elapsed_time < 5.0, f"Query should be fast with optimization, took {elapsed_time:.2f}s"
+
+    # Verify results are sorted by last_update_date (proving auto-sort worked)
+    if len(result) > 1:
+        dates = []
+        for idx in range(min(10, len(result))):
+            date_str = result.iloc[idx]["last_update_date"]
+            if pd.notna(date_str):
+                try:
+                    clean_date_str = str(date_str)
+                    if '+' in clean_date_str or clean_date_str.endswith('Z'):
+                        clean_date_str = clean_date_str.replace('+00:00', '').replace('Z', '')
+                    dates.append(datetime.strptime(clean_date_str, "%Y-%m-%d %H:%M:%S"))
+                except (ValueError, TypeError):
+                    pass
+
+        if len(dates) > 1:
+            # Verify descending order (most recent first)
+            for i in range(len(dates) - 1):
+                assert dates[i] >= dates[i + 1], \
+                    "Auto-applied sort should order by last_update_date descending"
+
+    print("Auto-sort optimization verified ✓")
+
+
+def test_pending_date_optimization():
+    """Test that PENDING + date filters get auto-sort and early termination"""
+    from datetime import datetime, timedelta
+    import time
+
+    # Test: Verify auto-sort is applied for PENDING with past_days
+    start_time = time.time()
+    result = scrape_property(
+        location="California",
+        listing_type="pending",
+        past_days=7,
+        # NO sort_by specified - should auto-apply sort_by="pending_date"
+        limit=50
+    )
+    elapsed_time = time.time() - start_time
+
+    print(f"\nPENDING auto-sort test: {len(result)} properties in {elapsed_time:.2f}s")
+
+    # Should complete quickly due to optimization (<10 seconds)
+    assert elapsed_time < 10.0, f"PENDING query should be fast with optimization, took {elapsed_time:.2f}s"
+
+    # Verify results are sorted by pending_date (proving auto-sort worked)
+    if len(result) > 1:
+        dates = []
+        for idx in range(min(10, len(result))):
+            date_str = result.iloc[idx]["pending_date"]
+            if pd.notna(date_str):
+                try:
+                    clean_date_str = str(date_str)
+                    if '+' in clean_date_str or clean_date_str.endswith('Z'):
+                        clean_date_str = clean_date_str.replace('+00:00', '').replace('Z', '')
+                    dates.append(datetime.strptime(clean_date_str, "%Y-%m-%d %H:%M:%S"))
+                except (ValueError, TypeError):
+                    pass
+
+        if len(dates) > 1:
+            # Verify descending order (most recent first)
+            for i in range(len(dates) - 1):
+                assert dates[i] >= dates[i + 1], \
+                    "PENDING auto-applied sort should order by pending_date descending"
+
+    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()
+