Merge pull request #147 from ZacharyHampton/feature/ios-mobile-headers

Improve API stability and reliability

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.
@@ -96,6 +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.
     """
@@ -190,6 +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
@@ -73,26 +76,22 @@ class Scraper:
                 total=3, backoff_factor=4, status_forcelist=[429, 403], 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",
+                    'Host': 'api.frontdoor.realtor.com',
-                    "accept-language": "en-US,en;q=0.9",
+                    'rdc-ab-test-client': 'ios_for_sale',
-                    "cache-control": "no-cache",
+                    'Content-Type': 'application/json',
-                    "content-type": "application/json",
+                    'apollographql-client-version': '26.9.25-26.9.25.0774600',
-                    "origin": "https://www.realtor.com",
+                    'Accept': '*/*',
-                    "pragma": "no-cache",
+                    'Accept-Language': 'en-US,en;q=0.9',
-                    "priority": "u=1, i",
+                    'rdc-client-version': '26.9.25',
-                    "rdc-ab-tests": "commute_travel_time_variation:v1",
+                    'X-APOLLO-OPERATION-TYPE': 'query',
-                    "sec-ch-ua": '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
+                    'rdc-client-name': 'RDC_NATIVE_MOBILE-iPhone-com.move.Realtor',
-                    "sec-ch-ua-mobile": "?0",
+                    'apollographql-client-name': 'com.move.Realtor-apollo-ios',
-                    "sec-ch-ua-platform": '"Windows"',
+                    'User-Agent': 'Realtor.com/26.9.25.0774600 CFNetwork/3860.200.71 Darwin/25.1.0',
-                    "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",
                 }
             )
 
@@ -141,6 +140,9 @@ 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

@@ -35,47 +35,109 @@ 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
 
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
 
-    def handle_location(self):
+    def _graphql_post(self, query: str, variables: dict, operation_name: str) -> dict:
-        # Get client_id from listing_type
+        """
-        if self.listing_type is None:
+        Execute a GraphQL query with operation-specific headers.
-            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("_", "-")
 
-        params = {
+        Args:
-            "input": self.location,
+            query: GraphQL query string (must include operationName matching operation_name param)
-            "client_id": client_id,
+            variables: Query variables dictionary
-            "limit": "1",
+            operation_name: Name of the GraphQL operation for Apollo headers
-            "area_types": "city,state,county,postal_code,address,street,neighborhood,school,school_district,university,park",
+
+        Returns:
+            Response JSON dictionary
+        """
+        # Set operation-specific header (must match query's operationName)
+        self.session.headers['X-APOLLO-OPERATION-NAME'] = operation_name
+
+        payload = {
+            "operationName": operation_name,  # Include in payload
+            "query": query,
+            "variables": variables,
         }
 
-        response = self.session.get(
+        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-            self.ADDRESS_AUTOCOMPLETE_URL,
+        return response.json()
-            params=params,
-        )
-        response_json = response.json()
 
-        result = response_json["autocomplete"]
+    @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):
+        query = """query SearchSuggestions($searchInput: SearchSuggestionsInput!) {
+            search_suggestions(search_input: $searchInput) {
+                geo_results {
+                    type
+                    text
+                    geo {
+                        _id
+                        area_type
+                        city
+                        state_code
+                        postal_code
+                        county
+                        centroid { lat lon }
+                        slug_id
+                        geo_id
+                    }
+                }
+            }
+        }"""
 
-        if not result:
+        variables = {
+            "searchInput": {
+                "search_term": self.location
+            }
+        }
+
+        response_json = self._graphql_post(query, variables, "SearchSuggestions")
+
+        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":
+            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($property_id: ID!) {
+        query = """query GetPropertyListingId($property_id: ID!) {
                     property(id: $property_id) {
                         listings {
                             listing_id
@@ -86,13 +148,7 @@ class RealtorScraper(Scraper):
                 """
 
         variables = {"property_id": property_id}
-        payload = {
+        response_json = self._graphql_post(query, variables, "GetPropertyListingId")
-            "query": query,
-            "variables": variables,
-        }
-
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
-        response_json = response.json()
 
         property_info = response_json["data"]["property"]
         if property_info["listings"] is None:
@@ -108,31 +164,40 @@ class RealtorScraper(Scraper):
             return property_info["listings"][0]["listing_id"]
 
     def handle_home(self, property_id: str) -> list[Property]:
+        """Fetch single home with proper error handling."""
         query = (
-            """query Home($property_id: ID!) {
+            """query GetHomeDetails($property_id: ID!) {
                     home(property_id: $property_id) %s
                 }"""
             % HOMES_DATA
         )
 
         variables = {"property_id": property_id}
-        payload = {
-            "query": query,
-            "variables": variables,
-        }
 
-        response = self.session.post(self.SEARCH_GQL_URL, json=payload)
+        try:
-        response_json = response.json()
+            data = self._graphql_post(query, variables, "GetHomeDetails")
 
-        property_info = response_json["data"]["home"]
+            # Check for errors or missing data
+            if "errors" in data or "data" not in data:
+                return []
 
-        if self.return_type != ReturnType.raw:
+            if data["data"] is None or "home" not in data["data"]:
-            return [process_property(property_info, self.mls_only, self.extra_property_data, 
+                return []
-                                   self.exclude_pending, self.listing_type, get_key, process_extra_property_details)]
-        else:
-            return [property_info]
 
+            property_info = data["data"]["home"]
+            if property_info is None:
+                return []
 
+            # Process based on return type
+            if self.return_type != ReturnType.raw:
+                return [process_property(property_info, self.mls_only, self.extra_property_data,
+                                       self.exclude_pending, self.listing_type, get_key,
+                                       process_extra_property_details)]
+            else:
+                return [property_info]
+
+        except Exception:
+            return []
 
     def general_search(self, variables: dict, search_type: str) -> Dict[str, Union[int, Union[list[Property], list[dict]]]]:
         """
@@ -144,7 +209,15 @@ 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 +350,14 @@ 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)
@@ -317,7 +394,7 @@ 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!,
@@ -350,20 +427,14 @@ class RealtorScraper(Scraper):
                 GENERAL_RESULTS_QUERY,
             )
         elif search_type == "area":  #: general search, came from a general location
-            query = """query Home_search(
+            query = """query GetHomeSearch(
-                                $city: String,
+                                $search_location: SearchLocation,
-                                $county: [String],
-                                $state_code: String,
-                                $postal_code: String
                                 $offset: Int,
                             ) {
                                 home_search(
                                     query: {
                                         %s
-                                        city: $city
+                                        search_location: $search_location
-                                        county: $county
-                                        postal_code: $postal_code
-                                        state_code: $state_code
                                         %s
                                         %s
                                         %s
@@ -388,7 +459,7 @@ class RealtorScraper(Scraper):
             )
         else:  #: general search, came from an address
             query = (
-                """query Property_search(
+                """query GetHomeSearch(
                         $property_id: [ID]!
                         $offset: Int!,
                     ) {
@@ -403,13 +474,7 @@ class RealtorScraper(Scraper):
                 % GENERAL_RESULTS_QUERY
             )
 
-        payload = {
+        response_json = self._graphql_post(query, variables, "GetHomeSearch")
-            "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"
 
         properties: list[Union[Property, dict]] = []
@@ -499,24 +564,16 @@ 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:
@@ -526,39 +583,49 @@ class RealtorScraper(Scraper):
         total = result["total"]
         homes = result["properties"]
 
-        # Pre-check: Should we continue pagination?
+        # Fetch remaining pages based on parallel parameter
-        # This optimization prevents unnecessary API calls when using time-based filters
+        if self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
-        # with date sorting. If page 1's last property is outside the time window,
+            if self.parallel:
-        # all future pages will also be outside (due to sort order).
+                # Parallel mode: Fetch all remaining pages in parallel
-        should_continue_pagination = self._should_fetch_more_pages(homes)
+                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
+                    # Collect results and sort by offset to preserve API sort order
-        if should_continue_pagination and self.offset + self.DEFAULT_PAGE_SIZE < min(total, self.offset + self.limit):
+                    results = []
-            with ThreadPoolExecutor() as executor:
+                    for offset, future in futures_with_offsets:
-                # Store futures with their offsets to maintain proper sort order
+                        results.append((offset, future.result()["properties"]))
-                # Start from offset + page_size and go up to offset + limit
+
-                futures_with_offsets = [
+                    results.sort(key=lambda x: x[0])
-                    (i, executor.submit(
+                    for offset, properties in results:
-                        self.general_search,
+                        homes.extend(properties)
-                        variables=search_variables | {"offset": i},
+            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,
                     )
-                ]
+                    page_properties = result["properties"]
-
+                    homes.extend(page_properties)
-                # 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)
 
         # Apply client-side hour-based filtering if needed
         # (API only supports day-level filtering, so we post-filter for hour precision)
@@ -1028,8 +1095,8 @@ class RealtorScraper(Scraper):
 
 
     @retry(
-        retry=retry_if_exception_type(JSONDecodeError),
+        retry=retry_if_exception_type((JSONDecodeError, Exception)),
-        wait=wait_exponential(min=4, max=10),
+        wait=wait_exponential(multiplier=1, min=1, max=10),
         stop=stop_after_attempt(3),
     )
     def get_bulk_prop_details(self, property_ids: list[str]) -> dict:
@@ -1048,15 +1115,19 @@ class RealtorScraper(Scraper):
             for property_id in property_ids
         )
         query = f"""{HOME_FRAGMENT}
-        
-        query GetHomes {{
-            {fragments}
-        }}"""
 
-        response = self.session.post(self.SEARCH_GQL_URL, json={"query": query})
+query GetBulkPropertyDetails {{
-        data = response.json()
+    {fragments}
+}}"""
+
+        data = self._graphql_post(query, {}, "GetBulkPropertyDetails")
 
         if "data" not in data:
+            # 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"]

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.8.3"
+version = "0.8.7"
 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

@@ -1,4 +1,5 @@
 import pytz
+from concurrent.futures import ThreadPoolExecutor, as_completed
 
 from homeharvest import scrape_property, Property
 import pandas as pd
@@ -87,6 +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(
@@ -288,6 +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)],