Compare commits

...

8 Commits

Author SHA1 Message Date
Zachary Hampton
3b7c17b7b5 - zillow proxy support 2023-09-28 18:40:16 -07:00
Zachary Hampton
59317fd6fc Merge pull request #25 from ZacharyHampton/fix/recent-issues
Fix/recent issues
2023-09-28 18:27:04 -07:00
Zachary Hampton
928b431d1f - bump version 2023-09-28 18:25:53 -07:00
Zachary Hampton
896f862137 - zillow flow update 2023-09-28 18:25:47 -07:00
Zachary Hampton
3174f5076c Merge pull request #23 from ZacharyHampton/fix/recent-issues
Fixes & Changes for recent issues
2023-09-28 18:07:55 -07:00
Zachary Hampton
2abbb913a8 - convert posted_time to datetime
- zillow location bug fix
2023-09-28 18:07:42 -07:00
Cullen Watson
73b6d5b33f [fix] zilow tls client 2023-09-28 19:34:01 -05:00
Zachary Hampton
da39c989d9 - version bump 2023-09-28 15:27:36 -07:00
5 changed files with 74 additions and 37 deletions

View File

@@ -1,5 +1,6 @@
from dataclasses import dataclass
import requests
import tls_client
from .models import Property, ListingType, SiteName
@@ -12,15 +13,20 @@ class ScraperInput:
class Scraper:
def __init__(self, scraper_input: ScraperInput):
def __init__(self, scraper_input: ScraperInput, session: requests.Session | tls_client.Session = None):
self.location = scraper_input.location
self.listing_type = scraper_input.listing_type
self.session = requests.Session()
if not session:
self.session = requests.Session()
else:
self.session = session
if scraper_input.proxy:
proxy_url = scraper_input.proxy
proxies = {"http": proxy_url, "https": proxy_url}
self.session.proxies.update(proxies)
self.listing_type = scraper_input.listing_type
self.site_name = scraper_input.site_name

View File

@@ -6,16 +6,41 @@ 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
session = tls_client.Session(
client_identifier="chrome112", random_tls_extension_order=True
)
super().__init__(scraper_input, session)
self.session.headers.update({
'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-language': 'en-US,en;q=0.9',
'cache-control': 'max-age=0',
'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-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',
})
if not self.is_plausible_location(self.location):
raise NoResultsFound("Invalid location input: {}".format(self.location))
@@ -32,15 +57,18 @@ class ZillowScraper(Scraper):
url = (
"https://www.zillowstatic.com/autocomplete/v3/suggestions?q={"
"}&abKey=6666272a-4b99-474c-b857-110ec438732b&clientId=homepage-render"
).format(location)
).format(urllib.parse.quote(location))
response = self.session.get(url)
resp = self.session.get(url)
return response.json()["results"] != []
return resp.json()["results"] != []
def search(self):
resp = self.session.get(self.url, headers=self._get_headers())
resp.raise_for_status()
resp = self.session.get(self.url)
if resp.status_code != 200:
raise HTTPError(
f"bad response status code: {resp.status_code}"
)
content = resp.text
match = re.search(
@@ -134,12 +162,23 @@ class ZillowScraper(Scraper):
"wants": {"cat1": ["mapResults"]},
"isDebugRequest": False,
}
resp = self.session.put(url, headers=self._get_headers(), json=payload)
resp.raise_for_status()
self.cookies = resp.cookies
a = resp.json()
resp = self.session.put(url, json=payload)
if resp.status_code != 200:
raise HTTPError(
f"bad response status code: {resp.status_code}"
)
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"]
@@ -165,7 +204,7 @@ class ZillowScraper(Scraper):
home_info["statusType"] if "statusType" in home_info else self.listing_type
),
status_text=result.get("statusText"),
posted_time=result["variableData"]["text"] #: TODO: change to datetime
posted_time=self.parse_posted_time(result["variableData"]["text"])
if "variableData" in result
and "text" in result["variableData"]
and result["variableData"]["type"] == "TIME_ON_INFO"
@@ -297,24 +336,3 @@ class ZillowScraper(Scraper):
state=state,
zip_code=zip_code,
)
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=0.7',
'accept-language': 'en-US,en;q=0.9',
'sec-ch-ua': '"Google Chrome";v="117", "Not;A=Brand";v="8", "Chromium";v="117"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'sec-fetch-dest': 'document',
'sec-fetch-mode': 'navigate',
'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',
}
if self.cookies:
headers['Cookie'] = self.cookies
return headers

13
poetry.lock generated
View File

@@ -408,6 +408,17 @@ 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"
@@ -450,4 +461,4 @@ zstd = ["zstandard (>=0.18.0)"]
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
content-hash = "3647d568f5623dd762f19029230626a62e68309fa2ef8be49a36382c19264a5f"
content-hash = "9b77e1a09fcf2cf5e7e6be53f304cd21a6a51ea51680d661a178afe5e5343670"

View File

@@ -1,6 +1,6 @@
[tool.poetry]
name = "homeharvest"
version = "0.2.15"
version = "0.2.18"
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"
@@ -14,6 +14,7 @@ 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]

View File

@@ -11,6 +11,7 @@ def test_zillow():
results = [
scrape_property(location="2530 Al Lipscomb Way", site_name="zillow", listing_type="for_sale"),
scrape_property(location="Phoenix, AZ, USA", site_name=["zillow"], listing_type="for_rent"),
scrape_property(location="Surprise, AZ", site_name=["zillow"], listing_type="for_sale"),
scrape_property(location="Dallas, TX, USA", site_name="zillow", listing_type="sold"),
scrape_property(location="85281", site_name="zillow"),
scrape_property(location="3268 88th st s, Lakewood", site_name="zillow", listing_type="for_rent"),