Version bump to 0.8.17

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

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

README.md

@@ -84,7 +84,7 @@ properties = scrape_property(
 #### Sorting & Listing Types
 ```py
 # Sort options: list_price, list_date, sqft, beds, baths, last_update_date
-# Listing types: "for_sale", "for_rent", "sold", "pending", list, or None (all)
+# 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
@@ -94,6 +94,17 @@ properties = scrape_property(
 )
 ```
 
+#### 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
+)
+```
+
 ## Output
 ```plaintext
 >>> properties.head()
@@ -147,7 +158,7 @@ Required
 │    - 'other'
 │    - 'ready_to_build'
 │    - List of strings returns properties matching ANY status: ['for_sale', 'pending']
-│    - None returns all listing types
+│    - None returns common listing types (for_sale, for_rent, sold, pending, off_market)
 │
 Optional
 ├── property_type (list): Choose the type of properties.
@@ -234,7 +245,9 @@ Optional
 │
 ├── limit (integer): Limit the number of properties to fetch. Max & default is 10000.
 │
-└── offset (integer): Starting position for pagination within the 10k limit. Use with limit to fetch results in chunks.
+├── offset (integer): Starting position for pagination within the 10k limit. Use with limit to fetch results in chunks.
+│
+└── parallel (True/False): Controls pagination strategy. Default is True (fetch pages in parallel for speed). Set to False for sequential fetching with early termination (useful for rate limiting or narrow time windows).
 ```
 
 ### Property Schema

homeharvest/__init__.py

@@ -48,6 +48,8 @@ def scrape_property(
     # New sorting parameters
     sort_by: str = None,
     sort_direction: str = "desc",
+    # Pagination control
+    parallel: bool = True,
 ) -> Union[pd.DataFrame, list[dict], list[Property]]:
     """
     Scrape properties from Realtor.com based on a given location and listing type.
@@ -72,6 +74,8 @@ def scrape_property(
         - 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.
@@ -80,7 +84,11 @@ def scrape_property(
 
     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)
+    :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
@@ -90,6 +98,9 @@ def scrape_property(
     :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.
     """
@@ -184,6 +195,8 @@ def scrape_property(
         # New sorting
         sort_by=sort_by,
         sort_direction=sort_direction,
+        # Pagination control
+        parallel=parallel,
     )
 
     site = RealtorScraper(scraper_input)

homeharvest/core/scrapers/__init__.py

@@ -55,6 +55,9 @@ class ScraperInput(BaseModel):
     sort_by: str | None = None
     sort_direction: str = "desc"
 
+    # Pagination control
+    parallel: bool = True
+
 
 class Scraper:
     session = None
@@ -70,35 +73,37 @@ class Scraper:
         if not self.session:
             Scraper.session = requests.Session()
             retries = Retry(
-                total=3, backoff_factor=4, status_forcelist=[429, 403], allowed_methods=frozenset(["GET", "POST"])
+                total=3, backoff_factor=4, status_forcelist=[429], allowed_methods=frozenset(["GET", "POST"])
             )
 
-            adapter = HTTPAdapter(max_retries=retries)
+            adapter = HTTPAdapter(max_retries=retries, pool_connections=10, pool_maxsize=20)
             Scraper.session.mount("http://", adapter)
             Scraper.session.mount("https://", adapter)
             Scraper.session.headers.update(
                 {
-                    "accept": "application/json, text/javascript",
-                    "accept-language": "en-US,en;q=0.9",
-                    "cache-control": "no-cache",
-                    "content-type": "application/json",
-                    "origin": "https://www.realtor.com",
-                    "pragma": "no-cache",
-                    "priority": "u=1, i",
-                    "rdc-ab-tests": "commute_travel_time_variation:v1",
-                    "sec-ch-ua": '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
-                    "sec-ch-ua-mobile": "?0",
-                    "sec-ch-ua-platform": '"Windows"',
-                    "sec-fetch-dest": "empty",
-                    "sec-fetch-mode": "cors",
-                    "sec-fetch-site": "same-origin",
-                    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
+                    'Content-Type': 'application/json',
+                    'Accept': '*/*',
+                    'Accept-Language': 'en-US,en;q=0.9',
+                    'Cache-Control': 'no-cache',
+                    'Origin': 'https://www.realtor.com',
+                    'Pragma': 'no-cache',
+                    'Referer': 'https://www.realtor.com/',
+                    'rdc-client-name': 'RDC_WEB_SRP_FS_PAGE',
+                    'rdc-client-version': '3.0.2515',
+                    'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+                    'sec-ch-ua-mobile': '?0',
+                    'sec-ch-ua-platform': '"macOS"',
+                    'sec-fetch-dest': 'empty',
+                    'sec-fetch-mode': 'cors',
+                    'sec-fetch-site': 'same-site',
+                    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36',
+                    'x-is-bot': 'false',
                 }
             )
 
-        if scraper_input.proxy:
-            proxy_url = scraper_input.proxy
-            proxies = {"http": proxy_url, "https": proxy_url}
+        self.proxy = scraper_input.proxy
+        if self.proxy:
+            proxies = {"http": self.proxy, "https": self.proxy}
             self.session.proxies.update(proxies)
 
         self.listing_type = scraper_input.listing_type
@@ -141,6 +146,9 @@ class Scraper:
         self.sort_by = scraper_input.sort_by
         self.sort_direction = scraper_input.sort_direction
 
+        # Pagination control
+        self.parallel = scraper_input.parallel
+
     def search(self) -> list[Union[Property | dict]]: ...
 
     @staticmethod

homeharvest/core/scrapers/realtor/__init__.py

@@ -8,6 +8,7 @@ This module implements the scraper for realtor.com
 from __future__ import annotations
 
 import json
+import re
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime
 from json import JSONDecodeError
@@ -16,17 +17,19 @@ from typing import Dict, Union
 from tenacity import (
     retry,
     retry_if_exception_type,
+    retry_if_not_exception_type,
     wait_exponential,
     stop_after_attempt,
 )
 
 from .. import Scraper
+from ....exceptions import AuthenticationError
 from ..models import (
     Property,
     ListingType,
     ReturnType
 )
-from .queries import GENERAL_RESULTS_QUERY, SEARCH_HOMES_DATA, HOMES_DATA, HOME_FRAGMENT
+from .queries import GENERAL_RESULTS_QUERY, HOMES_DATA, SEARCH_SUGGESTIONS_QUERY
 from .processors import (
     process_property,
     process_extra_property_details,
@@ -35,64 +38,122 @@ 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"
-    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"
+    SEARCH_GQL_URL = "https://www.realtor.com/frontdoor/graphql"
     NUM_PROPERTY_WORKERS = 20
     DEFAULT_PAGE_SIZE = 200
 
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
 
-    def handle_location(self):
-        # Get client_id from listing_type
-        if self.listing_type is None:
-            client_id = "for-sale"
-        elif isinstance(self.listing_type, list):
-            client_id = self.listing_type[0].value.lower().replace("_", "-") if self.listing_type else "for-sale"
-        else:
-            client_id = self.listing_type.value.lower().replace("_", "-")
+    @staticmethod
+    def _minify_query(query: str) -> str:
+        """Minify GraphQL query by collapsing whitespace to single spaces."""
+        # Split on whitespace, filter empty strings, join with single space
+        return ' '.join(query.split())
 
-        params = {
-            "input": self.location,
-            "client_id": client_id,
-            "limit": "1",
-            "area_types": "city,state,county,postal_code,address,street,neighborhood,school,school_district,university,park",
+    def _graphql_post(self, query: str, variables: dict, operation_name: str) -> dict:
+        """
+        Execute a GraphQL query.
+
+        Args:
+            query: GraphQL query string (must include operationName matching operation_name param)
+            variables: Query variables dictionary
+            operation_name: Name of the GraphQL operation
+
+        Returns:
+            Response JSON dictionary
+        """
+        payload = {
+            "operationName": operation_name,
+            "query": self._minify_query(query),
+            "variables": variables,
         }
 
-        response = self.session.get(
-            self.ADDRESS_AUTOCOMPLETE_URL,
-            params=params,
-        )
-        response_json = response.json()
+        response = self.session.post(self.SEARCH_GQL_URL, data=json.dumps(payload, separators=(',', ':')))
 
-        result = response_json["autocomplete"]
+        if response.status_code == 403:
+            if not self.proxy:
+                raise AuthenticationError(
+                    "Received 403 Forbidden from Realtor.com API.",
+                    response=response
+                )
+            else:
+                raise Exception("Received 403 Forbidden, retrying...")
 
-        if not result:
+        return response.json()
+
+    @retry(
+        retry=retry_if_exception_type(Exception),
+        wait=wait_exponential(multiplier=1, min=1, max=4),
+        stop=stop_after_attempt(3),
+    )
+    def handle_location(self):
+        variables = {
+            "searchInput": {
+                "search_term": self.location
+            }
+        }
+
+        response_json = self._graphql_post(SEARCH_SUGGESTIONS_QUERY, variables, "Search_suggestions")
+
+        if (
+            response_json is None
+            or "data" not in response_json
+            or response_json["data"] is None
+            or "search_suggestions" not in response_json["data"]
+            or response_json["data"]["search_suggestions"] is None
+            or "geo_results" not in response_json["data"]["search_suggestions"]
+            or not response_json["data"]["search_suggestions"]["geo_results"]
+        ):
+            # If we got a 400 error with "Required parameter is missing", raise to trigger retry
+            if response_json and "errors" in response_json:
+                error_msgs = [e.get("message", "") for e in response_json.get("errors", [])]
+                if any("Required parameter is missing" in msg for msg in error_msgs):
+                    raise Exception(f"Transient API error: {error_msgs}")
             return None
 
-        return result[0]
+        geo_result = response_json["data"]["search_suggestions"]["geo_results"][0]
+        geo = geo_result.get("geo", {})
+
+        result = {
+            "text": geo_result.get("text"),
+            "area_type": geo.get("area_type"),
+            "city": geo.get("city"),
+            "state_code": geo.get("state_code"),
+            "postal_code": geo.get("postal_code"),
+            "county": geo.get("county"),
+            "centroid": geo.get("centroid"),
+        }
+
+        if geo.get("area_type") == "address":
+            # Try to get mpr_id directly from API response first
+            if geo.get("mpr_id"):
+                result["mpr_id"] = geo.get("mpr_id")
+            else:
+                # Fallback: extract from _id field if it has addr: prefix
+                geo_id = geo.get("_id", "")
+                if geo_id.startswith("addr:"):
+                    result["mpr_id"] = geo_id.replace("addr:", "")
+
+        return result
 
     def get_latest_listing_id(self, property_id: str) -> str | None:
-        query = """query Property($property_id: ID!) {
+        query = """
+                fragment ListingFragment on Listing {
+                    listing_id
+                    primary
+                }
+                query GetPropertyListingId($property_id: ID!) {
                     property(id: $property_id) {
                         listings {
-                            listing_id
-                            primary
+                            ...ListingFragment
                         }
                     }
                 }
                 """
 
         variables = {"property_id": property_id}
-        payload = {
-            "query": query,
-            "variables": variables,
-        }
-
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
+        response_json = self._graphql_post(query, variables, "GetPropertyListingId")
 
         property_info = response_json["data"]["property"]
         if property_info["listings"] is None:
@@ -108,31 +169,40 @@ class RealtorScraper(Scraper):
             return property_info["listings"][0]["listing_id"]
 
     def handle_home(self, property_id: str) -> list[Property]:
+        """Fetch single home with proper error handling."""
         query = (
-            """query Home($property_id: ID!) {
+            """query GetHomeDetails($property_id: ID!) {
                     home(property_id: $property_id) %s
                 }"""
             % HOMES_DATA
         )
 
         variables = {"property_id": property_id}
-        payload = {
-            "query": query,
-            "variables": variables,
-        }
 
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
+        try:
+            data = self._graphql_post(query, variables, "GetHomeDetails")
 
-        property_info = response_json["data"]["home"]
+            # Check for errors or missing data
+            if "errors" in data or "data" not in data:
+                return []
 
-        if self.return_type != ReturnType.raw:
-            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]
+            if data["data"] is None or "home" not in data["data"]:
+                return []
 
+            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]]]]:
         """
@@ -144,7 +214,15 @@ class RealtorScraper(Scraper):
         # Determine date field based on listing type
         # Convert listing_type to list for uniform handling
         if self.listing_type is None:
-            listing_types = []
+            # When None, return all common listing types as documented
+            # Note: NEW_COMMUNITY, OTHER, and READY_TO_BUILD are excluded as they typically return no results
+            listing_types = [
+                ListingType.FOR_SALE,
+                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
@@ -277,10 +355,14 @@ class RealtorScraper(Scraper):
         else:
             sort_param = ""  #: prioritize normal fractal sort from realtor
 
-        # Handle PENDING with or_filters (applies if PENDING is in the list or is the single type)
+        # 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 has_pending else ""
+            "or_filters: { contingent: true, pending: true }" if use_or_filters else ""
         )
 
         # Build bucket parameter (only use fractal sort if no custom sort is specified)
@@ -317,12 +399,12 @@ class RealtorScraper(Scraper):
             is_foreclosure = "foreclosure: false"
 
         if search_type == "comps":  #: comps search, came from an address
-            query = """query Property_search(
+            query = """query GetHomeSearch(
                     $coordinates: [Float]!
                     $radius: String!
                     $offset: Int!,
                     ) {
-                        home_search(
+                        homeSearch: home_search(
                             query: {
                                 %s
                                 nearby: {
@@ -350,20 +432,14 @@ class RealtorScraper(Scraper):
                 GENERAL_RESULTS_QUERY,
             )
         elif search_type == "area":  #: general search, came from a general location
-            query = """query Home_search(
-                                $city: String,
-                                $county: [String],
-                                $state_code: String,
-                                $postal_code: String
-                                $offset: Int,
+            query = """query GetHomeSearch(
+                                $search_location: SearchLocation,
+                                $offset: Int
                             ) {
-                                home_search(
+                                homeSearch: home_search(
                                     query: {
                                         %s
-                                        city: $city
-                                        county: $county
-                                        postal_code: $postal_code
-                                        state_code: $state_code
+                                        search_location: $search_location
                                         %s
                                         %s
                                         %s
@@ -388,11 +464,11 @@ class RealtorScraper(Scraper):
             )
         else:  #: general search, came from an address
             query = (
-                """query Property_search(
+                """query GetHomeSearch(
                         $property_id: [ID]!
                         $offset: Int!,
                     ) {
-                        home_search(
+                        homeSearch: home_search(
                             query: {
                                 property_id: $property_id
                             }
@@ -403,14 +479,8 @@ class RealtorScraper(Scraper):
                 % GENERAL_RESULTS_QUERY
             )
 
-        payload = {
-            "query": query,
-            "variables": variables,
-        }
-
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
-        search_key = "home_search" if "home_search" in query else "property_search"
+        response_json = self._graphql_post(query, variables, "GetHomeSearch")
+        search_key = "homeSearch"
 
         properties: list[Union[Property, dict]] = []
 
@@ -499,24 +569,16 @@ 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"),
-            }
-
-        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"),
-
+                "search_location": {"location": location_info.get("text")},
             }
 
         if self.foreclosure:
@@ -526,39 +588,49 @@ class RealtorScraper(Scraper):
         total = result["total"]
         homes = result["properties"]
 
-        # Pre-check: Should we continue pagination?
-        # This optimization prevents unnecessary API calls when using time-based filters
-        # with date sorting. If page 1's last property is outside the time window,
-        # all future pages will also be outside (due to sort order).
-        should_continue_pagination = self._should_fetch_more_pages(homes)
+        # Fetch remaining pages based on parallel parameter
+        if self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
+            if self.parallel:
+                # Parallel mode: Fetch all remaining pages in parallel
+                with ThreadPoolExecutor() as executor:
+                    futures_with_offsets = [
+                        (i, executor.submit(
+                            self.general_search,
+                            variables=search_variables | {"offset": i},
+                            search_type=search_type,
+                        ))
+                        for i in range(
+                            self.offset + self.DEFAULT_PAGE_SIZE,
+                            min(total, self.offset + self.limit),
+                            self.DEFAULT_PAGE_SIZE,
+                        )
+                    ]
 
-        # Only launch parallel pagination if needed
-        if should_continue_pagination and self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
-            with ThreadPoolExecutor() as executor:
-                # Store futures with their offsets to maintain proper sort order
-                # Start from offset + page_size and go up to offset + limit
-                futures_with_offsets = [
-                    (i, executor.submit(
-                        self.general_search,
-                        variables=search_variables | {"offset": i},
+                    # Collect results and sort by offset to preserve API sort order
+                    results = []
+                    for offset, future in futures_with_offsets:
+                        results.append((offset, future.result()["properties"]))
+
+                    results.sort(key=lambda x: x[0])
+                    for offset, properties in results:
+                        homes.extend(properties)
+            else:
+                # Sequential mode: Fetch pages one by one with early termination checks
+                for current_offset in range(
+                    self.offset + self.DEFAULT_PAGE_SIZE,
+                    min(total, self.offset + self.limit),
+                    self.DEFAULT_PAGE_SIZE,
+                ):
+                    # Check if we should continue based on time-based filters
+                    if not self._should_fetch_more_pages(homes):
+                        break
+
+                    result = self.general_search(
+                        variables=search_variables | {"offset": current_offset},
                         search_type=search_type,
-                    ))
-                    for i in range(
-                        self.offset + self.DEFAULT_PAGE_SIZE,
-                        min(total, self.offset + self.limit),
-                        self.DEFAULT_PAGE_SIZE,
                     )
-                ]
-
-                # Collect results and sort by offset to preserve API sort order across pages
-                results = []
-                for offset, future in futures_with_offsets:
-                    results.append((offset, future.result()["properties"]))
-
-                # Sort by offset and concatenate in correct order
-                results.sort(key=lambda x: x[0])
-                for offset, properties in results:
-                    homes.extend(properties)
+                    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)
@@ -755,13 +827,14 @@ class RealtorScraper(Scraper):
         if not homes:
             return homes
 
-        from datetime import datetime, timedelta
+        from datetime import datetime, timedelta, timezone
 
         # Determine date range for last_update_date filtering
         date_range = None
 
         if self.updated_in_past_hours:
-            cutoff_datetime = datetime.now() - timedelta(hours=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:
@@ -792,15 +865,19 @@ class RealtorScraper(Scraper):
 
     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)
-                to_date = datetime.fromisoformat(self.date_to)
+                # Parse and strip timezone to match naive property dates
+                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
@@ -865,7 +942,7 @@ class RealtorScraper(Scraper):
         Returns:
             bool: True if we should continue pagination, False to stop early
         """
-        from datetime import datetime, timedelta
+        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":
@@ -882,11 +959,14 @@ class RealtorScraper(Scraper):
             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:
-                cutoff_datetime = datetime.now() - timedelta(hours=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
@@ -935,6 +1015,8 @@ class RealtorScraper(Scraper):
 
         def get_sort_key(home):
             """Extract the sort field value from a home (handles both dict and Property object)."""
+            from datetime import datetime
+
             if isinstance(home, dict):
                 value = home.get(self.sort_by)
             else:
@@ -950,20 +1032,23 @@ class RealtorScraper(Scraper):
             if self.sort_by in ['list_date', 'sold_date', 'pending_date', 'last_update_date']:
                 if isinstance(value, str):
                     try:
-                        from datetime import datetime
                         # Handle timezone indicators
                         date_value = value
                         if date_value.endswith('Z'):
                             date_value = date_value[:-1] + '+00:00'
                         parsed_date = datetime.fromisoformat(date_value)
-                        return (0, parsed_date)
+                        # Normalize to timezone-naive for consistent comparison
+                        return 0, parsed_date.replace(tzinfo=None)
                     except (ValueError, AttributeError):
                         # If parsing fails, treat as None
                         return (1, 0) if self.sort_direction == "desc" else (1, float('inf'))
-                return (0, value)
+                # Handle datetime objects directly (normalize timezone)
+                if isinstance(value, datetime):
+                    return 0, value.replace(tzinfo=None)
+                return 0, value
 
             # For numeric fields, ensure we can compare
-            return (0, value)
+            return 0, value
 
         # Sort the homes
         reverse = (self.sort_direction == "desc")
@@ -1015,8 +1100,8 @@ class RealtorScraper(Scraper):
 
 
     @retry(
-        retry=retry_if_exception_type(JSONDecodeError),
-        wait=wait_exponential(min=4, max=10),
+        retry=retry_if_exception_type((JSONDecodeError, Exception)) & retry_if_not_exception_type(AuthenticationError),
+        wait=wait_exponential(multiplier=1, min=1, max=10),
         stop=stop_after_attempt(3),
     )
     def get_bulk_prop_details(self, property_ids: list[str]) -> dict:
@@ -1029,24 +1114,25 @@ class RealtorScraper(Scraper):
 
         property_ids = list(set(property_ids))
 
-        # Construct the bulk query
         fragments = "\n".join(
-            f'home_{property_id}: home(property_id: {property_id}) {{ ...HomeData }}'
+            f'home_{property_id}: home(property_id: {property_id}) {HOMES_DATA}'
             for property_id in property_ids
         )
-        query = f"""{HOME_FRAGMENT}
-        
-        query GetHomes {{
-            {fragments}
-        }}"""
+        query = f"""query GetHome {{
+    {fragments}
+}}"""
 
-        response = self.session.post(self.SEARCH_GQL_URL, json={"query": query})
-        data = response.json()
+        data = self._graphql_post(query, {}, "GetHome")
 
-        if "data" not in data:
+        if "data" not in data or data["data"] is None:
+            # If we got a 400 error with "Required parameter is missing", raise to trigger retry
+            if data and "errors" in data:
+                error_msgs = [e.get("message", "") for e in data.get("errors", [])]
+                if any("Required parameter is missing" in msg for msg in error_msgs):
+                    raise Exception(f"Transient API error: {error_msgs}")
             return {}
 
         properties = data["data"]
-        return {data.replace('home_', ''): properties[data] for data in properties if properties[data]}
+        return {key.replace('home_', ''): properties[key] for key in properties if properties[key]}
 
 

homeharvest/core/scrapers/realtor/queries.py

@@ -1,3 +1,193 @@
+SEARCH_RESULTS_FRAGMENT = """
+fragment PropertyResult on SearchHome {
+    __typename
+    pending_date
+    listing_id
+    property_id
+    href
+    permalink
+    list_date
+    status
+    mls_status
+    last_sold_price
+    last_sold_date
+    last_status_change_date
+    last_update_date
+    list_price
+    list_price_max
+    list_price_min
+    price_per_sqft
+    tags
+    open_houses {
+        start_date
+        end_date
+        description
+        time_zone
+        dst
+        href
+        methods
+    }
+    details {
+        category
+        text
+        parent_category
+    }
+    pet_policy {
+        cats
+        dogs
+        dogs_small
+        dogs_large
+        __typename
+    }
+    units {
+        availability {
+          date
+          __typename
+        }
+        description {
+          baths_consolidated
+          baths
+          beds
+          sqft
+          __typename
+        }
+        photos(https: true) {
+            title
+            href
+            tags {
+                label
+            }
+        }
+        list_price
+        __typename
+    }
+    flags {
+        is_contingent
+        is_pending
+        is_new_construction
+    }
+    description {
+        type
+        sqft
+        beds
+        baths_full
+        baths_half
+        lot_sqft
+        year_built
+        garage
+        type
+        name
+        stories
+        text
+    }
+    source {
+        id
+        listing_id
+    }
+    hoa {
+        fee
+    }
+    location {
+        address {
+            street_direction
+            street_number
+            street_name
+            street_suffix
+            line
+            unit
+            city
+            state_code
+            postal_code
+            coordinate {
+                lon
+                lat
+            }
+        }
+        county {
+            name
+            fips_code
+        }
+        neighborhoods {
+            name
+        }
+    }
+    tax_record {
+        cl_id
+        public_record_id
+        last_update_date
+        apn
+        tax_parcel_id
+    }
+    primary_photo(https: true) {
+        href
+    }
+    advertisers {
+        email
+        broker {
+            name
+            fulfillment_id
+        }
+        type
+        name
+        fulfillment_id
+        builder {
+            name
+            fulfillment_id
+        }
+        phones {
+            ext
+            primary
+            type
+            number
+        }
+        office {
+            name
+            email
+            fulfillment_id
+            href
+            phones {
+                number
+                type
+                primary
+                ext
+            }
+            mls_set
+        }
+        corporation {
+            specialties
+            name
+            bio
+            href
+            fulfillment_id
+        }
+        mls_set
+        nrds_id
+        state_license
+        rental_corporation {
+            fulfillment_id
+        }
+        rental_management {
+            name
+            href
+            fulfillment_id
+        }
+    }
+    current_estimates {
+        __typename
+        source {
+            __typename
+            type
+            name
+        }
+        estimate
+        estimateHigh: estimate_high
+        estimateLow: estimate_low
+        date
+        isBestHomeValue: isbest_homevalue
+    }
+}
+"""
+
 _SEARCH_HOMES_DATA_BASE = """{
     pending_date
     listing_id
@@ -181,8 +371,189 @@ _SEARCH_HOMES_DATA_BASE = """{
 
 
 HOME_FRAGMENT = """
-fragment HomeData on Home {
+fragment PropertyResult on Home {
+    __typename
+    pending_date
+    listing_id
     property_id
+    href
+    permalink
+    list_date
+    status
+    mls_status
+    last_sold_price
+    last_sold_date
+    last_status_change_date
+    last_update_date
+    list_price
+    list_price_max
+    list_price_min
+    price_per_sqft
+    tags
+    open_houses {
+        start_date
+        end_date
+        description
+        time_zone
+        dst
+        href
+        methods
+    }
+    details {
+        category
+        text
+        parent_category
+    }
+    pet_policy {
+        cats
+        dogs
+        dogs_small
+        dogs_large
+        __typename
+    }
+    units {
+        availability {
+          date
+          __typename
+        }
+        description {
+          baths_consolidated
+          baths
+          beds
+          sqft
+          __typename
+        }
+        photos(https: true) {
+            title
+            href
+            tags {
+                label
+            }
+        }
+        list_price
+        __typename
+    }
+    flags {
+        is_contingent
+        is_pending
+        is_new_construction
+    }
+    description {
+        type
+        sqft
+        beds
+        baths_full
+        baths_half
+        lot_sqft
+        year_built
+        garage
+        type
+        name
+        stories
+        text
+    }
+    source {
+        id
+        listing_id
+    }
+    hoa {
+        fee
+    }
+    location {
+        address {
+            street_direction
+            street_number
+            street_name
+            street_suffix
+            line
+            unit
+            city
+            state_code
+            postal_code
+            coordinate {
+                lon
+                lat
+            }
+        }
+        county {
+            name
+            fips_code
+        }
+        neighborhoods {
+            name
+        }
+        parcel {
+            parcel_id
+        }
+    }
+    tax_record {
+        cl_id
+        public_record_id
+        last_update_date
+        apn
+        tax_parcel_id
+    }
+    primary_photo(https: true) {
+        href
+    }
+    photos(https: true) {
+        title
+        href
+        tags {
+            label
+        }
+    }
+    advertisers {
+        email
+        broker {
+            name
+            fulfillment_id
+        }
+        type
+        name
+        fulfillment_id
+        builder {
+            name
+            fulfillment_id
+        }
+        phones {
+            ext
+            primary
+            type
+            number
+        }
+        office {
+            name
+            email
+            fulfillment_id
+            href
+            phones {
+                number
+                type
+                primary
+                ext
+            }
+            mls_set
+        }
+        corporation {
+            specialties
+            name
+            bio
+            href
+            fulfillment_id
+        }
+        mls_set
+        nrds_id
+        state_license
+        rental_corporation {
+            fulfillment_id
+        }
+        rental_management {
+            name
+            href
+            fulfillment_id
+        }
+    }
     nearbySchools: nearby_schools(radius: 5.0, limit_per_level: 3) {
         __typename schools { district { __typename id name } }
     }
@@ -198,11 +569,6 @@ fragment HomeData on Home {
             last_n_days
         }
     }
-    location {
-        parcel {
-            parcel_id
-        }
-    }
     taxHistory: tax_history { __typename tax year assessment { __typename building land total } }
     property_history {
         date
@@ -227,6 +593,18 @@ fragment HomeData on Home {
         text
         category
     }
+    estimates {
+        __typename
+        currentValues: current_values {
+            __typename
+            source { __typename type name }
+            estimate
+            estimateHigh: estimate_high
+            estimateLow: estimate_low
+            date
+            isBestHomeValue: isbest_homevalue
+        }
+    }
 }
 """
 
@@ -300,8 +678,128 @@ current_estimates {
 }
 }""" % _SEARCH_HOMES_DATA_BASE
 
-GENERAL_RESULTS_QUERY = """{
+# Query body using inline fields (kept for backward compatibility)
+GENERAL_RESULTS_QUERY_BODY = """{
                             count
                             total
                             results %s
                         }""" % SEARCH_HOMES_DATA
+
+GENERAL_RESULTS_QUERY = """{
+                            __typename
+                            count
+                            total
+                            results %s
+                        }""" % SEARCH_HOMES_DATA
+
+LISTING_PHOTOS_FRAGMENT = """
+fragment ListingPhotosFragment on SearchHome {
+    __typename
+    photos(https: true) {
+        __typename
+        title
+        href
+        tags {
+            __typename
+            label
+            probability
+        }
+    }
+}
+"""
+
+SEARCH_SUGGESTIONS_QUERY = """query Search_suggestions($searchInput: SearchSuggestionsInput!) {
+  search_suggestions(search_input: $searchInput) {
+    raw_input_parser_result
+    typeahead_results {
+      display_string
+      display_geo
+      geo {
+        _id
+        _score
+        mpr_id
+        area_type
+        city
+        state_code
+        state
+        postal_code
+        country
+        lat
+        lon
+        county
+        counties {
+          name
+          fips
+          state_code
+        }
+        slug_id
+        geo_id
+        score
+        name
+        city_slug_id
+        centroid {
+          lat
+          lon
+        }
+        county_needed_for_uniq
+        street
+        line
+        school
+        school_id
+        school_district
+        has_catchment
+        university
+        university_id
+        neighborhood
+        park
+      }
+      url
+    }
+    geo_results {
+      type
+      text
+      geo {
+        _id
+        _score
+        mpr_id
+        area_type
+        city
+        state_code
+        state
+        postal_code
+        country
+        lat
+        lon
+        county
+        counties {
+          name
+          fips
+          state_code
+        }
+        slug_id
+        geo_id
+        score
+        name
+        city_slug_id
+        centroid {
+          lat
+          lon
+        }
+        county_needed_for_uniq
+        street
+        line
+        school
+        school_id
+        school_district
+        has_catchment
+        university
+        university_id
+        neighborhood
+        park
+      }
+    }
+    no_matches
+    has_results
+    original_string
+  }
+}"""

homeharvest/utils.py

@@ -331,15 +331,26 @@ def validate_sort(sort_by: str | None, sort_direction: str | None = "desc") -> N
 
 def convert_to_datetime_string(value) -> str | None:
     """
-    Convert datetime object or string to ISO 8601 string format.
+    Convert datetime object or string to ISO 8601 string format with UTC timezone.
 
     Accepts:
-    - datetime.datetime objects
-    - datetime.date objects
+    - 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 or 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
@@ -349,13 +360,23 @@ def convert_to_datetime_string(value) -> str | None:
         return value
 
     # datetime.datetime object
-    from datetime import datetime, date
+    from datetime import datetime, date, timezone
     if isinstance(value, datetime):
-        return value.isoformat()
+        # 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)
+    # datetime.date object (convert to datetime at midnight UTC)
     if isinstance(value, date):
-        return datetime.combine(value, datetime.min.time()).isoformat()
+        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. "

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.8.2"
+version = "0.8.17"
 description = "Real estate scraping library"
 authors = ["Zachary Hampton <zachary@bunsly.com>", "Cullen Watson <cullen@bunsly.com>"]
 homepage = "https://github.com/ZacharyHampton/HomeHarvest"

tests/test_realtor.py

@@ -1,3 +1,6 @@
+import pytz
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
 from homeharvest import scrape_property, Property
 import pandas as pd
 
@@ -85,6 +88,25 @@ def test_realtor_date_range_sold():
     )
 
 
+def test_listing_type_none_includes_sold():
+    """Test that listing_type=None includes sold listings (issue #142)"""
+    # Get properties with listing_type=None (should include all common types)
+    result_none = scrape_property(
+        location="Warren, MI",
+        listing_type=None
+    )
+
+    # Verify we got results
+    assert result_none is not None and len(result_none) > 0
+
+    # Verify sold listings are included
+    status_types = set(result_none['status'].unique())
+    assert 'SOLD' in status_types, "SOLD listings should be included when listing_type=None"
+
+    # Verify we get multiple listing types (not just one)
+    assert len(status_types) > 1, "Should return multiple listing types when listing_type=None"
+
+
 def test_realtor_single_property():
     results = [
         scrape_property(
@@ -286,6 +308,30 @@ def test_phone_number_matching():
     assert row["agent_phones"].values[0] == matching_row["agent_phones"].values[0]
 
 
+def test_parallel_search_consistency():
+    """Test that the same search executed 3 times in parallel returns consistent results"""
+    def search_task():
+        return scrape_property(
+            location="Phoenix, AZ",
+            listing_type="for_sale",
+            limit=100
+        )
+
+    with ThreadPoolExecutor(max_workers=3) as executor:
+        futures = [executor.submit(search_task) for _ in range(3)]
+        results = [future.result() for future in as_completed(futures)]
+
+    # Verify all results are valid
+    assert all([result is not None for result in results])
+    assert all([isinstance(result, pd.DataFrame) for result in results])
+    assert all([len(result) > 0 for result in results])
+
+    # Verify all results have the same length (primary consistency check)
+    lengths = [len(result) for result in results]
+    assert len(set(lengths)) == 1, \
+        f"All parallel searches should return same number of results, got lengths: {lengths}"
+
+
 def test_return_type():
     results = {
         "pandas": [scrape_property(location="Surprise, AZ", listing_type="for_rent", limit=100)],
@@ -1524,4 +1570,71 @@ def test_pending_date_optimization():
                 assert dates[i] >= dates[i + 1], \
                     "PENDING auto-applied sort should order by pending_date descending"
 
-    print("PENDING optimization verified ✓")
+    print("PENDING optimization verified ✓")
+
+
+def test_basic_last_update_date():
+    from datetime import datetime, timedelta
+
+    # Test with naive datetime (treated as local time)
+    now = datetime.now()
+
+    properties = scrape_property(
+        "California",
+        updated_since=now - timedelta(minutes=10),
+        sort_by="last_update_date",
+        sort_direction="desc"
+    )
+
+    # Convert now to timezone-aware for comparison with UTC dates in DataFrame
+    now_utc = now.astimezone(tz=pytz.timezone("UTC"))
+
+    # Check all last_update_date values are <= now
+    assert (properties["last_update_date"] <= now_utc).all()
+
+    # Verify we got some results
+    assert len(properties) > 0
+
+
+def test_timezone_aware_last_update_date():
+    """Test that timezone-aware datetimes work correctly for updated_since"""
+    from datetime import datetime, timedelta, timezone
+
+    # Test with timezone-aware datetime (explicit UTC)
+    now_utc = datetime.now(timezone.utc)
+
+    properties = scrape_property(
+        "California",
+        updated_since=now_utc - timedelta(minutes=10),
+        sort_by="last_update_date",
+        sort_direction="desc"
+    )
+
+    # Check all last_update_date values are <= now
+    assert (properties["last_update_date"] <= now_utc).all()
+
+    # Verify we got some results
+    assert len(properties) > 0
+
+
+def test_timezone_handling_date_range():
+    """Test timezone handling for date_from and date_to parameters"""
+    from datetime import datetime, timedelta
+
+    # Test with naive datetimes for date range (PENDING properties)
+    now = datetime.now()
+    three_days_ago = now - timedelta(days=3)
+
+    properties = scrape_property(
+        "California",
+        listing_type="pending",
+        date_from=three_days_ago,
+        date_to=now
+    )
+
+    # Verify we got results and they're within the date range
+    if len(properties) > 0:
+        # Convert now to UTC for comparison
+        now_utc = now.astimezone(tz=pytz.timezone("UTC"))
+        assert (properties["pending_date"] <= now_utc).all()
+