- version bump

- Replace /suggest REST endpoint with GraphQL Search_suggestions query
- Use search_location field instead of individual city/county/state/postal_code fields
- Fix coordinate order to [lon, lat] (GeoJSON standard) for radius searches
- Extract mpr_id from addr: prefix for single address lookups

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

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

README.md

@@ -2,11 +2,18 @@
 
 **HomeHarvest** is a real estate scraping library that extracts and formats data in the style of MLS listings.
 
+- 🚀 [HomeHarvest MCP](https://smithery.ai/server/@ZacharyHampton/homeharvest-mcp) - Easily get property data in your agent.
+- 🏠 [Zillow API](https://rapidapi.com/zachary-l1izVlvs2/api/zillow-com9) - Get Zillow data with ease.
+
 ## 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)
 
@@ -23,43 +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
+
+#### Time-Based Filtering
+```py
+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,  # 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
+)
+```
+
+#### Property Filters
+```py
+# Combine any filters: beds, baths, sqft, price, lot_sqft, year_built
+properties = scrape_property(
+    location="San Francisco, CA",
+    listing_type="for_sale",
+    beds_min=3, beds_max=5,
+    baths_min=2.0,
+    sqft_min=1500, sqft_max=3000,
+    price_min=300000, price_max=800000,
+    year_built_min=2000,
+    lot_sqft_min=5000
+)
+```
+
+#### Sorting & Listing Types
+```py
+# 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", "pending"],  # Single string, list, or None
+    sort_by="list_price",  # Sort field
+    sort_direction="asc",  # "asc" or "desc"
+    limit=100
+)
+```
+
+#### Pagination Control
+```py
+# Sequential mode with early termination (more efficient for narrow filters)
+properties = scrape_property(
+    location="Los Angeles, CA",
+    listing_type="for_sale",
+    updated_in_past_hours=2,  # Narrow time window
+    parallel=False  # Fetch pages sequentially, stop when filters no longer match
 )
 ```
 
@@ -98,30 +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)
@@ -134,10 +184,54 @@ 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 | timedelta): Number of past hours to filter properties (more precise than past_days). Uses client-side filtering.
+│    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"
+│
+├── updated_since (datetime | str): Filter properties updated since a specific date/time (based on last_update_date field)
+│    Accepts datetime objects or ISO 8601 strings
+│    Example: updated_since=datetime(2025, 11, 10, 9, 0) or "2025-11-10T09:00:00"
+│
+├── 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)
+│
+├── baths_min, baths_max (float): Filter by number of bathrooms
+│    Example: baths_min=2.0, baths_max=3.5 (2-3.5 bathrooms)
+│
+├── sqft_min, sqft_max (integer): Filter by square footage
+│    Example: sqft_min=1000, sqft_max=2500 (1,000-2,500 sq ft)
+│
+├── price_min, price_max (integer): Filter by listing price
+│    Example: price_min=200000, price_max=500000 ($200k-$500k)
+│
+├── lot_sqft_min, lot_sqft_max (integer): Filter by lot size in square feet
+│    Example: lot_sqft_min=5000, lot_sqft_max=10000 (5,000-10,000 sq ft lot)
+│
+├── year_built_min, year_built_max (integer): Filter by year built
+│    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', 'last_update_date'
+│    Example: sort_by='list_price'
+│
+├── sort_direction (string): Sort direction, default is 'desc'
+│    Options: 'asc' (ascending), 'desc' (descending)
+│    Example: sort_direction='asc' (cheapest first)
 │
 ├── mls_only (True/False): If set, fetches only MLS listings (mainly applicable to 'sold' listings)
 │
@@ -149,7 +243,11 @@ Optional
 │
 ├── exclude_pending (True/False): If set, excludes 'pending' properties from the 'for_sale' results unless listing_type is 'pending'
 │
-└── limit (integer): Limit the number of properties to fetch. Max & default is 10000.
+├── 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.
+│
+└── 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
@@ -191,10 +289,12 @@ Property
 │ ├── list_price
 │ ├── list_price_min
 │ ├── list_price_max
-│ ├── list_date  # datetime
+│ ├── list_date  # datetime (full timestamp: YYYY-MM-DD HH:MM:SS)
-│ ├── pending_date  # datetime
+│ ├── pending_date  # datetime (full timestamp: YYYY-MM-DD HH:MM:SS)
 │ ├── sold_price
-│ ├── last_sold_date  # datetime
+│ ├── 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 +1,63 @@
 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
+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,  #: TODO: Switch to one parameter, Date, with date_from and date_to, pydantic validation
+    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
+    limit: int = 10000,
+    offset: int = 0,
+    # New date/time filtering parameters
+    past_hours: int | timedelta = None,
+    # New last_update_date filtering parameters
+    updated_since: datetime | str = None,
+    updated_in_past_hours: int | timedelta = None,
+    # New property filtering parameters
+    beds_min: int = None,
+    beds_max: int = None,
+    baths_min: float = None,
+    baths_max: float = None,
+    sqft_min: int = None,
+    sqft_max: int = None,
+    price_min: int = None,
+    price_max: int = None,
+    lot_sqft_min: int = None,
+    lot_sqft_max: int = None,
+    year_built_min: int = None,
+    year_built_max: int = None,
+    # 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.
@@ -35,31 +67,136 @@ 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.
     :param limit: Limit the number of results returned. Maximum is 10,000.
+    :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). Accepts int or timedelta.
+    :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, 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_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=converted_past_hours,
+        # New last_update_date filtering
+        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,
+        baths_min=baths_min,
+        baths_max=baths_max,
+        sqft_min=sqft_min,
+        sqft_max=sqft_max,
+        price_min=price_min,
+        price_max=price_max,
+        lot_sqft_min=lot_sqft_min,
+        lot_sqft_max=lot_sqft_max,
+        year_built_min=year_built_min,
+        year_built_max=year_built_max,
+        # 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

@@ -13,7 +13,7 @@ from pydantic import BaseModel
 
 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
@@ -21,12 +21,43 @@ 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
     limit: int = 10000
+    offset: int = 0
     return_type: ReturnType = ReturnType.pandas
 
+    # New date/time filtering parameters
+    past_hours: int | 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
+    beds_max: int | None = None
+    baths_min: float | None = None
+    baths_max: float | None = None
+    sqft_min: int | None = None
+    sqft_max: int | None = None
+    price_min: int | None = None
+    price_max: int | None = None
+    lot_sqft_min: int | None = None
+    lot_sqft_max: int | None = None
+    year_built_min: int | None = None
+    year_built_max: int | None = None
+
+    # New sorting parameters
+    sort_by: str | None = None
+    sort_direction: str = "desc"
+
+    # Pagination control
+    parallel: bool = True
+
 
 class Scraper:
     session = None
@@ -50,21 +81,21 @@ class Scraper:
             Scraper.session.mount("https://", adapter)
             Scraper.session.headers.update(
                 {
-                    "accept": "application/json, text/javascript",
+                    'sec-ch-ua-platform': '"macOS"',
-                    "accept-language": "en-US,en;q=0.9",
+                    'rdc-client-name': 'rdc-search-for-sale-desktop',
-                    "cache-control": "no-cache",
+                    'sec-ch-ua': '"Chromium";v="142", "Google Chrome";v="142", "Not_A Brand";v="99"',
-                    "content-type": "application/json",
+                    'sec-ch-ua-mobile': '?0',
-                    "origin": "https://www.realtor.com",
+                    'rdc-client-version': '0.1.0',
-                    "pragma": "no-cache",
+                    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36',
-                    "priority": "u=1, i",
+                    'accept': 'application/json',
-                    "rdc-ab-tests": "commute_travel_time_variation:v1",
+                    'content-type': 'application/json',
-                    "sec-ch-ua": '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
+                    'origin': 'https://www.realtor.com',
-                    "sec-ch-ua-mobile": "?0",
+                    'sec-fetch-site': 'same-site',
-                    "sec-ch-ua-platform": '"Windows"',
+                    'sec-fetch-mode': 'cors',
-                    "sec-fetch-dest": "empty",
+                    'sec-fetch-dest': 'empty',
-                    "sec-fetch-mode": "cors",
+                    'referer': 'https://www.realtor.com/',
-                    "sec-fetch-site": "same-origin",
+                    'accept-language': 'en-US,en;q=0.9',
-                    "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",
+                    'priority': 'u=1, i',
                 }
             )
 
@@ -79,12 +110,43 @@ 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.exclude_pending = scraper_input.exclude_pending
         self.limit = scraper_input.limit
+        self.offset = scraper_input.offset
         self.return_type = scraper_input.return_type
 
+        # New date/time filtering
+        self.past_hours = scraper_input.past_hours
+
+        # 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
+        self.beds_max = scraper_input.beds_max
+        self.baths_min = scraper_input.baths_min
+        self.baths_max = scraper_input.baths_max
+        self.sqft_min = scraper_input.sqft_min
+        self.sqft_max = scraper_input.sqft_max
+        self.price_min = scraper_input.price_min
+        self.price_max = scraper_input.price_max
+        self.lot_sqft_min = scraper_input.lot_sqft_min
+        self.lot_sqft_max = scraper_input.lot_sqft_max
+        self.year_built_min = scraper_input.year_built_min
+        self.year_built_max = scraper_input.year_built_max
+
+        # New sorting
+        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):
@@ -192,6 +196,8 @@ class Property(BaseModel):
     list_date: datetime | None = Field(None, description="The time this Home entered Move system")
     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

@@ -35,10 +35,7 @@ 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://api.frontdoor.realtor.com/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
 
@@ -46,25 +43,70 @@ class RealtorScraper(Scraper):
         super().__init__(scraper_input)
 
     def handle_location(self):
-        params = {
+        query = """query Search_suggestions($searchInput: SearchSuggestionsInput!) {
-            "input": self.location,
+            search_suggestions(search_input: $searchInput) {
-            "client_id": self.listing_type.value.lower().replace("_", "-"),
+                geo_results {
-            "limit": "1",
+                    type
-            "area_types": "city,state,county,postal_code,address,street,neighborhood,school,school_district,university,park",
+                    text
+                    geo {
+                        _id
+                        area_type
+                        city
+                        state_code
+                        postal_code
+                        county
+                        centroid { lat lon }
+                        slug_id
+                        geo_id
+                    }
+                }
+            }
+        }"""
+
+        variables = {
+            "searchInput": {
+                "search_term": self.location
+            }
         }
 
-        response = self.session.get(
+        payload = {
-            self.ADDRESS_AUTOCOMPLETE_URL,
+            "query": query,
-            params=params,
+            "variables": variables,
-        )
+        }
+
+        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
         response_json = response.json()
 
-        result = response_json["autocomplete"]
+        if (
-
+            response_json is None
-        if not result:
+            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"]
+        ):
             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":
+            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!) {
@@ -100,6 +142,7 @@ 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!) {
                     home(property_id: $property_id) %s
@@ -108,23 +151,33 @@ class RealtorScraper(Scraper):
         )
 
         variables = {"property_id": property_id}
-        payload = {
+        payload = {"query": query, "variables": variables}
-            "query": query,
-            "variables": variables,
-        }
 
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
+        try:
-        response_json = response.json()
+            response = self.session.post(self.SEARCH_GQL_URL, json=payload)
+            data = response.json()
 
-        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]]]]:
         """
@@ -132,37 +185,187 @@ class RealtorScraper(Scraper):
         """
 
         date_param = ""
-        if self.listing_type == ListingType.SOLD:
+
-            if self.date_from and self.date_to:
+        # Determine date field based on listing type
-                date_param = f'sold_date: {{ min: "{self.date_from}", max: "{self.date_to}" }}'
+        # Convert listing_type to list for uniform handling
-            elif self.last_x_days:
+        if self.listing_type is None:
-                date_param = f'sold_date: {{ min: "$today-{self.last_x_days}D" }}'
+            # When None, return all common listing types as documented
-        elif self.listing_type == ListingType.PENDING:
+            # Note: NEW_COMMUNITY, OTHER, and READY_TO_BUILD are excluded as they typically return no results
-            # Skip server-side date filtering for PENDING as both pending_date and contract_date 
+            listing_types = [
-            # filters are broken in the API. Client-side filtering will be applied later.
+                ListingType.FOR_SALE,
-            pass
+                ListingType.FOR_RENT,
+                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:
-            if self.date_from and self.date_to:
+            listing_types = [self.listing_type]
-                date_param = f'list_date: {{ min: "{self.date_from}", max: "{self.date_to}" }}'
+            # 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:
+            # 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.date_from:
+                    try:
+                        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.date_to:
+                    try:
+                        dt_to = datetime.fromisoformat(self.date_to.replace('Z', '+00:00'))
+                        max_date = dt_to.strftime("%Y-%m-%d")
+                    except (ValueError, AttributeError):
+                        pass
+
+                if min_date and max_date:
+                    date_param = f'{date_field}: {{ min: "{min_date}", max: "{max_date}" }}'
+                elif min_date:
+                    date_param = f'{date_field}: {{ min: "{min_date}" }}'
+                elif max_date:
+                    date_param = f'{date_field}: {{ max: "{max_date}" }}'
+
+            elif self.past_hours:
+                # Query API for past N days (minimum 1 day), client-side filter by hours
+                days = max(1, int(self.past_hours / 24) + 1)  # Round up to cover the full period
+                date_param = f'{date_field}: {{ min: "$today-{days}D" }}'
+
+            elif self.date_from and self.date_to:
+                date_param = f'{date_field}: {{ min: "{self.date_from}", max: "{self.date_to}" }}'
             elif self.last_x_days:
-                date_param = f'list_date: {{ min: "$today-{self.last_x_days}D" }}'
+                date_param = f'{date_field}: {{ min: "$today-{self.last_x_days}D" }}'
 
         property_type_param = ""
         if self.property_type:
             property_types = [pt.value for pt in self.property_type]
             property_type_param = f"type: {json.dumps(property_types)}"
 
-        sort_param = (
+        # Build property filter parameters
-            "sort: [{ field: sold_date, direction: desc }]"
+        property_filters = []
-            if self.listing_type == ListingType.SOLD
-            else ""  #: "sort: [{ field: list_date, direction: desc }]"  #: prioritize normal fractal sort from realtor
-        )
 
+        if self.beds_min is not None or self.beds_max is not None:
+            beds_filter = "beds: {"
+            if self.beds_min is not None:
+                beds_filter += f" min: {self.beds_min}"
+            if self.beds_max is not None:
+                beds_filter += f" max: {self.beds_max}"
+            beds_filter += " }"
+            property_filters.append(beds_filter)
+
+        if self.baths_min is not None or self.baths_max is not None:
+            baths_filter = "baths: {"
+            if self.baths_min is not None:
+                baths_filter += f" min: {self.baths_min}"
+            if self.baths_max is not None:
+                baths_filter += f" max: {self.baths_max}"
+            baths_filter += " }"
+            property_filters.append(baths_filter)
+
+        if self.sqft_min is not None or self.sqft_max is not None:
+            sqft_filter = "sqft: {"
+            if self.sqft_min is not None:
+                sqft_filter += f" min: {self.sqft_min}"
+            if self.sqft_max is not None:
+                sqft_filter += f" max: {self.sqft_max}"
+            sqft_filter += " }"
+            property_filters.append(sqft_filter)
+
+        if self.price_min is not None or self.price_max is not None:
+            price_filter = "list_price: {"
+            if self.price_min is not None:
+                price_filter += f" min: {self.price_min}"
+            if self.price_max is not None:
+                price_filter += f" max: {self.price_max}"
+            price_filter += " }"
+            property_filters.append(price_filter)
+
+        if self.lot_sqft_min is not None or self.lot_sqft_max is not None:
+            lot_sqft_filter = "lot_sqft: {"
+            if self.lot_sqft_min is not None:
+                lot_sqft_filter += f" min: {self.lot_sqft_min}"
+            if self.lot_sqft_max is not None:
+                lot_sqft_filter += f" max: {self.lot_sqft_max}"
+            lot_sqft_filter += " }"
+            property_filters.append(lot_sqft_filter)
+
+        if self.year_built_min is not None or self.year_built_max is not None:
+            year_built_filter = "year_built: {"
+            if self.year_built_min is not None:
+                year_built_filter += f" min: {self.year_built_min}"
+            if self.year_built_max is not None:
+                year_built_filter += f" max: {self.year_built_max}"
+            year_built_filter += " }"
+            property_filters.append(year_built_filter)
+
+        property_filters_param = "\n".join(property_filters)
+
+        # Build sort parameter
+        if self.sort_by:
+            sort_param = f"sort: [{{ field: {self.sort_by}, direction: {self.sort_direction} }}]"
+        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 ""
         )
 
-        listing_type = ListingType.FOR_SALE if self.listing_type == ListingType.PENDING else self.listing_type
+        # Build bucket parameter (only use fractal sort if no custom sort is specified)
+        bucket_param = ""
+        if not self.sort_by:
+            bucket_param = 'bucket: { sort: "fractal_v1.1.3_fr" }'
+
+        # 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:
@@ -183,7 +386,8 @@ class RealtorScraper(Scraper):
                                     coordinates: $coordinates
                                     radius: $radius
                                 }
-                                status: %s
+                                %s
+                                %s
                                 %s
                                 %s
                                 %s
@@ -194,44 +398,42 @@ class RealtorScraper(Scraper):
                     ) %s
                 }""" % (
                 is_foreclosure,
-                listing_type.value.lower(),
+                status_param,
                 date_param,
                 property_type_param,
+                property_filters_param,
                 pending_or_contingent_param,
                 sort_param,
                 GENERAL_RESULTS_QUERY,
             )
         elif search_type == "area":  #: general search, came from a general location
             query = """query Home_search(
-                                $city: String,
+                                $search_location: SearchLocation,
-                                $county: [String],
-                                $state_code: String,
-                                $postal_code: String
                                 $offset: Int,
                             ) {
                                 home_search(
                                     query: {
                                         %s
-                                        city: $city
+                                        search_location: $search_location
-                                        county: $county
+                                        %s
-                                        postal_code: $postal_code
+                                        %s
-                                        state_code: $state_code
-                                        status: %s
                                         %s
                                         %s
                                         %s
                                     }
-                                    bucket: { sort: "fractal_v1.1.3_fr" }
+                                    %s
                                     %s
                                     limit: 200
                                     offset: $offset
                                 ) %s
                             }""" % (
                 is_foreclosure,
-                listing_type.value.lower(),
+                status_param,
                 date_param,
                 property_type_param,
+                property_filters_param,
                 pending_or_contingent_param,
+                bucket_param,
                 sort_param,
                 GENERAL_RESULTS_QUERY,
             )
@@ -298,13 +500,23 @@ class RealtorScraper(Scraper):
 
         if self.return_type != ReturnType.raw:
             with ThreadPoolExecutor(max_workers=self.NUM_PROPERTY_WORKERS) as executor:
-                futures = [executor.submit(process_property, result, self.mls_only, self.extra_property_data, 
+                # Store futures with their indices to maintain sort order
-                                         self.exclude_pending, self.listing_type, get_key, process_extra_property_details) for result in properties_list]
+                futures_with_indices = [
+                    (i, executor.submit(process_property, result, self.mls_only, self.extra_property_data,
+                                       self.exclude_pending, self.listing_type, get_key, process_extra_property_details))
+                    for i, result in enumerate(properties_list)
+                ]
 
-                for future in as_completed(futures):
+                # Collect results and sort by index to preserve API sort order
+                results = []
+                for idx, future in futures_with_indices:
                     result = future.result()
                     if result:
-                        properties.append(result)
+                        results.append((idx, result))
+
+                # Sort by index and extract properties in correct order
+                results.sort(key=lambda x: x[0])
+                properties = [result for idx, result in results]
         else:
             properties = properties_list
 
@@ -321,7 +533,7 @@ class RealtorScraper(Scraper):
         location_type = location_info["area_type"]
 
         search_variables = {
-            "offset": 0,
+            "offset": self.offset,
         }
 
         search_type = (
@@ -338,24 +550,16 @@ 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:
@@ -365,30 +569,185 @@ class RealtorScraper(Scraper):
         total = result["total"]
         homes = result["properties"]
 
-        with ThreadPoolExecutor() as executor:
+        # Fetch remaining pages based on parallel parameter
-            futures = [
+        if self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
-                executor.submit(
+            if self.parallel:
-                    self.general_search,
+                # Parallel mode: Fetch all remaining pages in parallel
-                    variables=search_variables | {"offset": i},
+                with ThreadPoolExecutor() as executor:
-                    search_type=search_type,
+                    futures_with_offsets = [
-                )
+                        (i, executor.submit(
-                for i in range(
+                            self.general_search,
-                    self.DEFAULT_PAGE_SIZE,
+                            variables=search_variables | {"offset": i},
-                    min(total, self.limit),
+                            search_type=search_type,
-                    self.DEFAULT_PAGE_SIZE,
+                        ))
-                )
+                        for i in range(
-            ]
+                            self.offset + self.DEFAULT_PAGE_SIZE,
+                            min(total, self.offset + self.limit),
+                            self.DEFAULT_PAGE_SIZE,
+                        )
+                    ]
 
-            for future in as_completed(futures):
+                    # Collect results and sort by offset to preserve API sort order
-                homes.extend(future.result()["properties"])
+                    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
+
+                    result = self.general_search(
+                        variables=search_variables | {"offset": current_offset},
+                        search_type=search_type,
+                    )
+                    page_properties = result["properties"]
+                    homes.extend(page_properties)
+
+        # Apply client-side hour-based filtering if needed
+        # (API only supports day-level filtering, so we post-filter for hour precision)
+        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)
-        if self.listing_type == ListingType.PENDING and (self.last_x_days or self.date_from):
+        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 or date_from/date_to have hour precision,
+        since the API only supports day-level filtering.
+        """
+        if not homes:
+            return homes
+
+        from datetime import datetime, timedelta
+
+        # Determine date range with hour precision
+        date_range = None
+
+        if self.past_hours:
+            cutoff_datetime = datetime.now() - timedelta(hours=self.past_hours)
+            date_range = {'type': 'since', 'date': cutoff_datetime}
+        elif self.date_from or self.date_to:
+            try:
+                from_datetime = None
+                to_datetime = None
+
+                if self.date_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.date_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:
+                    date_range = {'type': 'range', 'from_date': from_datetime, 'to_date': to_datetime}
+                elif from_datetime:
+                    date_range = {'type': 'since', 'date': from_datetime}
+                elif to_datetime:
+                    date_range = {'type': 'until', 'date': to_datetime}
+            except (ValueError, AttributeError):
+                return homes  # If parsing fails, return unfiltered
+
+        if not date_range:
+            return homes
+
+        # Determine which date field to use based on listing type
+        date_field_name = self._get_date_field_for_listing_type()
+
+        filtered_homes = []
+
+        for home in homes:
+            # Extract the appropriate date for this property
+            property_date = self._extract_date_from_home(home, date_field_name)
+
+            # Handle properties without dates
+            if property_date is None:
+                # For PENDING, include contingent properties without pending_date
+                if self.listing_type == ListingType.PENDING and self._is_contingent(home):
+                    filtered_homes.append(home)
+                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_field_for_listing_type(self):
+        """Get the appropriate date field name for the current listing type."""
+        if self.listing_type == ListingType.SOLD:
+            return 'last_sold_date'
+        elif self.listing_type == ListingType.PENDING:
+            return 'pending_date'
+        else:  # FOR_SALE or FOR_RENT
+            return 'list_date'
+
+    def _extract_date_from_home(self, home, date_field_name):
+        """Extract a date field from a home (handles both dict and Property object).
+
+        Falls back to last_status_change_date if the primary date field is not available,
+        providing more precise filtering for PENDING/SOLD properties.
+        """
+        if isinstance(home, dict):
+            date_value = home.get(date_field_name)
+        else:
+            date_value = getattr(home, date_field_name, None)
+
+        if date_value:
+            return self._parse_date_value(date_value)
+
+        # Fallback to last_status_change_date if primary date field is missing
+        # This is useful for PENDING/SOLD properties where the specific date might be unavailable
+        if isinstance(home, dict):
+            fallback_date = home.get('last_status_change_date')
+        else:
+            fallback_date = getattr(home, 'last_status_change_date', None)
+
+        if fallback_date:
+            return self._parse_date_value(fallback_date)
+
+        return None
+
+    def _is_datetime_in_range(self, date_obj, date_range):
+        """Check if a datetime object falls within the specified date range (with hour precision)."""
+        if date_range['type'] == 'since':
+            return date_obj >= date_range['date']
+        elif date_range['type'] == 'until':
+            return date_obj <= date_range['date']
+        elif date_range['type'] == 'range':
+            return date_range['from_date'] <= date_obj <= date_range['to_date']
+        return False
+
     def _apply_pending_date_filter(self, homes):
         """Apply client-side date filtering for PENDING properties based on pending_date field.
         For contingent properties without pending_date, tries fallback date fields."""
@@ -440,17 +799,66 @@ 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
@@ -502,6 +910,174 @@ 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.
+
+        This is necessary because:
+        1. Multi-page results need to be re-sorted after concatenation
+        2. Filtering operations may disrupt the original sort order
+
+        Args:
+            homes: List of properties (either dicts or Property objects)
+
+        Returns:
+            Sorted list of properties
+        """
+        if not homes or not self.sort_by:
+            return homes
+
+        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:
+                # Property object
+                value = getattr(home, self.sort_by, None)
+
+            # Handle None values - push them to the end
+            if value is None:
+                # Use a sentinel value that sorts to the end
+                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', 'last_update_date']:
+                if isinstance(value, str):
+                    try:
+                        # Handle timezone indicators
+                        date_value = value
+                        if date_value.endswith('Z'):
+                            date_value = date_value[:-1] + '+00:00'
+                        parsed_date = datetime.fromisoformat(date_value)
+                        # 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'))
+                # 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
+
+        # Sort the homes
+        reverse = (self.sort_direction == "desc")
+        sorted_homes = sorted(homes, key=get_sort_key, reverse=reverse)
+
+        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(

homeharvest/core/scrapers/realtor/parsers.py

@@ -250,9 +250,28 @@ def parse_description(result: dict) -> Description | None:
 def calculate_days_on_mls(result: dict) -> Optional[int]:
     """Calculate days on MLS from result data"""
     list_date_str = result.get("list_date")
-    list_date = datetime.strptime(list_date_str.split("T")[0], "%Y-%m-%d") if list_date_str else None
+    list_date = None
+    if list_date_str:
+        try:
+            # Parse full datetime, then use date() for day calculation
+            list_date_str_clean = list_date_str.replace('Z', '+00:00') if list_date_str.endswith('Z') else list_date_str
+            list_date = datetime.fromisoformat(list_date_str_clean).replace(tzinfo=None)
+        except (ValueError, AttributeError):
+            # Fallback for date-only format
+            list_date = datetime.strptime(list_date_str.split("T")[0], "%Y-%m-%d") if "T" in list_date_str else None
+
     last_sold_date_str = result.get("last_sold_date")
-    last_sold_date = datetime.strptime(last_sold_date_str, "%Y-%m-%d") if last_sold_date_str else None
+    last_sold_date = None
+    if last_sold_date_str:
+        try:
+            last_sold_date_str_clean = last_sold_date_str.replace('Z', '+00:00') if last_sold_date_str.endswith('Z') else last_sold_date_str
+            last_sold_date = datetime.fromisoformat(last_sold_date_str_clean).replace(tzinfo=None)
+        except (ValueError, AttributeError):
+            # Fallback for date-only format
+            try:
+                last_sold_date = datetime.strptime(last_sold_date_str, "%Y-%m-%d")
+            except ValueError:
+                last_sold_date = None
     today = datetime.now()
 
     if list_date:

homeharvest/core/scrapers/realtor/processors.py

@@ -121,10 +121,12 @@ def process_property(result: dict, mls_only: bool = False, extra_property_data:
         list_price=result["list_price"],
         list_price_min=result["list_price_min"],
         list_price_max=result["list_price_max"],
-        list_date=(datetime.fromisoformat(result["list_date"].split("T")[0]) if result.get("list_date") else None),
+        list_date=(datetime.fromisoformat(result["list_date"].replace('Z', '+00:00') if result["list_date"].endswith('Z') else result["list_date"]) if result.get("list_date") else None),
         prc_sqft=result.get("price_per_sqft"),
-        last_sold_date=(datetime.fromisoformat(result["last_sold_date"]) if result.get("last_sold_date") else None),
+        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"].split("T")[0]) if result.get("pending_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),
@@ -162,6 +164,25 @@ def process_property(result: dict, mls_only: bool = False, extra_property_data:
         photos=result.get("photos"),
         flags=result.get("flags"),
     )
+
+    # Enhance date precision using last_status_change_date
+    # pending_date and last_sold_date only have day-level precision
+    # last_status_change_date has hour-level precision
+    if realty_property.last_status_change_date:
+        status = realty_property.status.upper() if realty_property.status else None
+
+        # For PENDING/CONTINGENT properties, use last_status_change_date for hour-precision on pending_date
+        if status in ["PENDING", "CONTINGENT"] and realty_property.pending_date:
+            # Only replace if dates are on the same day
+            if realty_property.pending_date.date() == realty_property.last_status_change_date.date():
+                realty_property.pending_date = realty_property.last_status_change_date
+
+        # For SOLD properties, use last_status_change_date for hour-precision on last_sold_date
+        elif status == "SOLD" and realty_property.last_sold_date:
+            # Only replace if dates are on the same day
+            if realty_property.last_sold_date.date() == realty_property.last_status_change_date.date():
+                realty_property.last_sold_date = realty_property.last_status_change_date
+
     return realty_property
 
 

homeharvest/core/scrapers/realtor/queries.py

@@ -9,6 +9,8 @@ _SEARCH_HOMES_DATA_BASE = """{
     mls_status
     last_sold_price
     last_sold_date
+    last_status_change_date
+    last_update_date
     list_price
     list_price_max
     list_price_min

homeharvest/utils.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 import pandas as pd
+import warnings
 from datetime import datetime
 from .core.scrapers.models import Property, ListingType, Advertisers
 from .exceptions import InvalidListingType, InvalidDate
@@ -36,6 +37,8 @@ ordered_properties = [
     "sold_price",
     "last_sold_date",
     "last_sold_price",
+    "last_status_change_date",
+    "last_update_date",
     "assessed_value",
     "estimated_value",
     "tax",
@@ -119,10 +122,10 @@ def process_result(result: Property) -> pd.DataFrame:
     prop_data["nearby_schools"] = filter(None, prop_data["nearby_schools"]) if prop_data["nearby_schools"] else None
     prop_data["nearby_schools"] = ", ".join(set(prop_data["nearby_schools"])) if prop_data["nearby_schools"] else None
     
-    # Convert datetime objects to strings for CSV
+    # Convert datetime objects to strings for CSV (preserve full datetime including time)
-    for date_field in ["list_date", "pending_date", "last_sold_date"]:
+    for date_field in ["list_date", "pending_date", "last_sold_date", "last_status_change_date"]:
         if prop_data.get(date_field):
-            prop_data[date_field] = prop_data[date_field].strftime("%Y-%m-%d") if hasattr(prop_data[date_field], 'strftime') else prop_data[date_field]
+            prop_data[date_field] = prop_data[date_field].strftime("%Y-%m-%d %H:%M:%S") if hasattr(prop_data[date_field], 'strftime') else prop_data[date_field]
     
     # Convert HttpUrl objects to strings for CSV
     if prop_data.get("property_url"):
@@ -154,24 +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:
@@ -179,3 +203,283 @@ def validate_limit(limit: int) -> None:
 
     if limit is not None and (limit < 1 or limit > 10000):
         raise ValueError("Property limit must be between 1 and 10,000.")
+
+
+def validate_offset(offset: int, limit: int = 10000) -> None:
+    """Validate offset parameter for pagination.
+
+    Args:
+        offset: Starting position for results pagination
+        limit: Maximum number of results to fetch
+
+    Raises:
+        ValueError: If offset is invalid or if offset + limit exceeds API limit
+    """
+    if offset is not None and offset < 0:
+        raise ValueError("Offset must be non-negative (>= 0).")
+
+    # Check if offset + limit exceeds API's hard limit of 10,000
+    if offset is not None and limit is not None and (offset + limit) > 10000:
+        raise ValueError(
+            f"offset ({offset}) + limit ({limit}) = {offset + limit} exceeds API maximum of 10,000. "
+            f"The API cannot return results beyond position 10,000. "
+            f"To fetch more results, narrow your search."
+        )
+
+    # Warn if offset is not a multiple of 200 (API page size)
+    if offset is not None and offset > 0 and offset % 200 != 0:
+        warnings.warn(
+            f"Offset should be a multiple of 200 (page size) for optimal performance. "
+            f"Using offset {offset} may result in less efficient pagination.",
+            UserWarning
+        )
+
+
+def validate_datetime(datetime_value) -> None:
+    """Validate datetime value (accepts datetime objects or ISO 8601 strings)."""
+    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_value.replace('Z', '+00:00'))
+    except (ValueError, AttributeError):
+        raise InvalidDate(
+            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,
+    baths_min: float | None = None,
+    baths_max: float | None = None,
+    sqft_min: int | None = None,
+    sqft_max: int | None = None,
+    price_min: int | None = None,
+    price_max: int | None = None,
+    lot_sqft_min: int | None = None,
+    lot_sqft_max: int | None = None,
+    year_built_min: int | None = None,
+    year_built_max: int | None = None,
+) -> None:
+    """Validate that min values are less than max values for range filters."""
+    ranges = [
+        ("beds", beds_min, beds_max),
+        ("baths", baths_min, baths_max),
+        ("sqft", sqft_min, sqft_max),
+        ("price", price_min, price_max),
+        ("lot_sqft", lot_sqft_min, lot_sqft_max),
+        ("year_built", year_built_min, year_built_max),
+    ]
+
+    for name, min_val, max_val in ranges:
+        if min_val is not None and max_val is not None and min_val > max_val:
+            raise ValueError(f"{name}_min ({min_val}) cannot be greater than {name}_max ({max_val}).")
+
+
+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", "last_update_date"]
+    valid_directions = ["asc", "desc"]
+
+    if sort_by and sort_by not in valid_sort_fields:
+        raise ValueError(
+            f"Invalid sort_by value: '{sort_by}'. "
+            f"Valid options: {', '.join(valid_sort_fields)}"
+        )
+
+    if sort_direction and sort_direction not in valid_directions:
+        raise ValueError(
+            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__}"
+    )

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.2.1 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -943,5 +943,5 @@ test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess
 
 [metadata]
 lock-version = "2.1"
-python-versions = ">=3.9,<3.13"
+python-versions = ">=3.9"
-content-hash = "17de7786a5e0bc51f4f42b6703dc41564050f8696a1b5d2e315ceffe6e192309"
+content-hash = "c60c33aa5f054998b90bd1941c825c9ca1867a53e64c07e188b91da49c7741a4"

pyproject.toml

@@ -1,14 +1,11 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.6.1"
+version = "0.8.6b"
 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"