fix: redfin

example.py

@@ -0,0 +1,11 @@
+from homeharvest import scrape_property
+import pandas as pd
+
+properties: pd.DataFrame = scrape_property(
+    site_name=["redfin"],
+    location="85281",
+    listing_type="for_rent" # for_sale / sold
+)
+
+print(properties)
+properties.to_csv('properties.csv', index=False)

homeharvest/core/scrapers/__init__.py

@@ -17,6 +17,7 @@ class Scraper:
         self.listing_type = scraper_input.listing_type
 
         self.session = requests.Session()
+        self.session.headers.update({"user-agent": 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36'})
         if scraper_input.proxy:
             proxy_url = scraper_input.proxy
             proxies = {"http": proxy_url, "https": proxy_url}

homeharvest/core/scrapers/zillow/__init__.py

@@ -6,25 +6,16 @@ This module implements the scraper for zillow.com
 """
 import re
 import json
-
-import tls_client
-
 from .. import Scraper
-from requests.exceptions import HTTPError
 from ....utils import parse_address_one, parse_address_two
 from ....exceptions import GeoCoordsNotFound, NoResultsFound
 from ..models import Property, Address, ListingType, PropertyType, Agent
-import urllib.parse
-from datetime import datetime, timedelta
 
 
 class ZillowScraper(Scraper):
     def __init__(self, scraper_input):
         super().__init__(scraper_input)
         self.cookies = None
-        self.session = tls_client.Session(
-            client_identifier="chrome112", random_tls_extension_order=True
-        )
 
         if not self.is_plausible_location(self.location):
             raise NoResultsFound("Invalid location input: {}".format(self.location))
@@ -41,18 +32,15 @@ class ZillowScraper(Scraper):
         url = (
             "https://www.zillowstatic.com/autocomplete/v3/suggestions?q={"
             "}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render"
-        ).format(urllib.parse.quote(location))
+        ).format(location)
 
-        resp = self.session.get(url)
+        response = self.session.get(url)
 
-        return resp.json()["results"] != []
+        return response.json()["results"] != []
 
     def search(self):
         resp = self.session.get(self.url, headers=self._get_headers())
-        if resp.status_code != 200:
+        resp.raise_for_status()
-            raise HTTPError(
-                f"bad response status code: {resp.status_code}"
-            )
         content = resp.text
 
         match = re.search(
@@ -147,23 +135,11 @@ class ZillowScraper(Scraper):
             "isDebugRequest": False,
         }
         resp = self.session.put(url, headers=self._get_headers(), json=payload)
-        if resp.status_code != 200:
+        resp.raise_for_status()
-            raise HTTPError(
-                f"bad response status code: {resp.status_code}"
-            )
         self.cookies = resp.cookies
+        a = resp.json()
         return self._parse_properties(resp.json())
 
-    @staticmethod
-    def parse_posted_time(time: str) -> datetime:
-        int_time = int(time.split(" ")[0])
-
-        if "hour" in time:
-            return datetime.now() - timedelta(hours=int_time)
-
-        if "day" in time:
-            return datetime.now() - timedelta(days=int_time)
-
     def _parse_properties(self, property_data: dict):
         mapresults = property_data["cat1"]["searchResults"]["mapResults"]
 
@@ -189,7 +165,7 @@ class ZillowScraper(Scraper):
                         home_info["statusType"] if "statusType" in home_info else self.listing_type
                     ),
                     status_text=result.get("statusText"),
-                    posted_time=self.parse_posted_time(result["variableData"]["text"])
+                    posted_time=result["variableData"]["text"]  #: TODO: change to datetime
                     if "variableData" in result
                        and "text" in result["variableData"]
                        and result["variableData"]["type"] == "TIME_ON_INFO"
@@ -325,16 +301,14 @@ class ZillowScraper(Scraper):
     def _get_headers(self):
         headers = {
             'authority': 'www.zillow.com',
-            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
+            'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
             'accept-language': 'en-US,en;q=0.9',
-            'cache-control': 'max-age=0',
+            'sec-ch-ua': '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
-            'cookie': '<your_cookie_here>',
-            'sec-ch-ua': '"Chromium";v="117", "Not)A;Brand";v="24", "Google Chrome";v="117"',
             'sec-ch-ua-mobile': '?0',
             'sec-ch-ua-platform': '"Windows"',
             'sec-fetch-dest': 'document',
             'sec-fetch-mode': 'navigate',
-            'sec-fetch-site': 'same-origin',
+            'sec-fetch-site': 'none',
             'sec-fetch-user': '?1',
             'upgrade-insecure-requests': '1',
             'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36',

poetry.lock

@@ -408,17 +408,6 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
-[[package]]
-name = "tls-client"
-version = "0.2.2"
-description = "Advanced Python HTTP Client."
-optional = false
-python-versions = "*"
-files = [
-    {file = "tls_client-0.2.2-py3-none-any.whl", hash = "sha256:30934871397cdad6862e00b5634f382666314a452ddd3d774e18323a0ad9b765"},
-    {file = "tls_client-0.2.2.tar.gz", hash = "sha256:78bc0e291e3aadc6c5e903b62bb26c01374577691f2a9e5e17899900a5927a13"},
-]
-
 [[package]]
 name = "tomli"
 version = "2.0.1"
@@ -461,4 +450,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10"
-content-hash = "9b77e1a09fcf2cf5e7e6be53f304cd21a6a51ea51680d661a178afe5e5343670"
+content-hash = "3647d568f5623dd762f19029230626a62e68309fa2ef8be49a36382c19264a5f"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "homeharvest"
-version = "0.2.16"
+version = "0.2.15"
 description = "Real estate scraping library supporting Zillow, Realtor.com & Redfin."
 authors = ["Zachary Hampton <zachary@zacharysproducts.com>", "Cullen Watson <cullen@cullen.ai>"]
 homepage = "https://github.com/ZacharyHampton/HomeHarvest"
@@ -14,7 +14,6 @@ python = "^3.10"
 requests = "^2.31.0"
 pandas = "^2.1.0"
 openpyxl = "^3.1.2"
-tls-client = "^0.2.2"
 
 
 [tool.poetry.group.dev.dependencies]