- base

homeharvest/__init__.py

@@ -0,0 +1,30 @@
+from .core.scrapers.redfin import RedfinScraper
+from .core.scrapers.types import ListingType, Home
+from .core.scrapers import ScraperInput
+from .exceptions import InvalidSite, InvalidListingType
+
+
+_scrapers = {
+    "redfin": RedfinScraper,
+}
+
+
+def scrape_property(
+        location: str,
+        listing_type: str = "for_sale",  #: for_sale, for_rent, sold
+        site_name: str = "redfin",
+) -> list[Home]:  #: eventually, return pandas dataframe
+    if site_name not in _scrapers:
+        raise InvalidSite(f"Provided site, '{site_name}', does not exist.")
+
+    if listing_type.upper() not in ListingType.__members__:
+        raise InvalidListingType(f"Provided listing type, '{listing_type}', does not exist.")
+
+    scraper_input = ScraperInput(
+        location=location,
+        listing_type=ListingType[listing_type.upper()],
+    )
+
+    site = _scrapers[site_name](scraper_input)
+
+    return site.search()

homeharvest/core/scrapers/__init__.py

@@ -0,0 +1,25 @@
+from dataclasses import dataclass
+import requests
+from .types import Home, ListingType
+
+
+@dataclass
+class ScraperInput:
+    location: str
+    listing_type: ListingType
+    proxy_url: str | None = None
+
+
+class Scraper:
+    def __init__(self, scraper_input: ScraperInput):
+        self.location = scraper_input.location
+        self.session = requests.Session()
+
+        if scraper_input.proxy_url:
+            self.session.proxies = {
+                "http": scraper_input.proxy_url,
+                "https": scraper_input.proxy_url,
+            }
+
+    def search(self) -> list[Home]:
+        ...

homeharvest/core/scrapers/redfin/__init__.py

@@ -0,0 +1,6 @@
+from .. import Scraper
+
+
+class RedfinScraper(Scraper):
+    def __init__(self, scraper_input):
+        super().__init__(scraper_input)

homeharvest/core/scrapers/types.py

@@ -0,0 +1,23 @@
+from dataclasses import dataclass
+from enum import Enum
+
+
+class ListingType(Enum):
+    FOR_SALE = "for_sale"
+    FOR_RENT = "for_rent"
+    SOLD = "sold"
+
+
+@dataclass
+class Address:
+    address_one: str
+    city: str
+    state: str
+    zip_code: str
+
+    address_two: str | None = None
+
+
+@dataclass
+class Home:
+    address: Address

homeharvest/exceptions.py

@@ -0,0 +1,8 @@
+class InvalidSite(Exception):
+    """Raised when a provided site is does not exist."""
+    pass
+
+
+class InvalidListingType(Exception):
+    """Raised when a provided listing type is does not exist."""
+    pass