turtlebasket
/
HomeHarvest
mirror of https://github.com/Bunsly/HomeHarvest.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

feat: add pandas

pull/1/head
Cullen Watson 2023-09-17 18:30:37 -05:00
parent b76c659f94
commit 3697b7cf2d
9 changed files with 393 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -3,3 +3,4 @@
**/__pycache__/ **/__pycache__/
**/.pytest_cache/ **/.pytest_cache/
*.pyc *.pyc
/.ipynb_checkpoints/

73
HomeHarvest_Demo.ipynb Normal file
View File

@ -0,0 +1,73 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "cb48903e-5021-49fe-9688-45cd0bc05d0f",
"metadata": {},
"outputs": [],
"source": [
"from homeharvest import scrape_property\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "156488ce-0d5f-43c5-87f4-c33e9c427860",
"metadata": {},
"outputs": [],
"source": [
"pd.set_option('display.max_columns', None) # Show all columns\n",
"pd.set_option('display.max_rows', None) # Show all rows\n",
"pd.set_option('display.width', None) # Auto-adjust display width to fit console\n",
"pd.set_option('display.max_colwidth', 50) # Limit max column width to 50 characters"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1c8b9744-8606-4e9b-8add-b90371a249a7",
"metadata": {},
"outputs": [],
"source": [
"scrape_property(\n",
" location=\"dallas\", site_name=\"zillow\", listing_type=\"for_sale\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ab7b4c21-da1d-4713-9df4-d7425d8ce21e",
"metadata": {},
"outputs": [],
"source": [
"scrape_property(\n",
" location=\"dallas\", site_name=\"redfin\", listing_type=\"for_sale\"\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

68
homeharvest/__init__.py
View File

@ -1,10 +1,11 @@
from .core.scrapers.redfin import RedfinScraper from .core.scrapers.redfin import RedfinScraper
from .core.scrapers.realtor import RealtorScraper from .core.scrapers.realtor import RealtorScraper
from .core.scrapers.zillow import ZillowScraper from .core.scrapers.zillow import ZillowScraper
from .core.scrapers.models import ListingType, Property, Building from .core.scrapers.models import ListingType, Property, Building, SiteName
from .core.scrapers import ScraperInput from .core.scrapers import ScraperInput
from .exceptions import InvalidSite, InvalidListingType from .exceptions import InvalidSite, InvalidListingType
from typing import Union from typing import Union
import pandas as pd
_scrapers = { _scrapers = {
@ -18,7 +19,7 @@ def scrape_property(
location: str, location: str,
site_name: str, site_name: str,
listing_type: str = "for_sale", #: for_sale, for_rent, sold listing_type: str = "for_sale", #: for_sale, for_rent, sold
) -> Union[list[Building], list[Property]]: #: eventually, return pandas dataframe ) -> Union[list[Building], list[Property]]:
if site_name.lower() not in _scrapers: if site_name.lower() not in _scrapers:
raise InvalidSite(f"Provided site, '{site_name}', does not exist.") raise InvalidSite(f"Provided site, '{site_name}', does not exist.")
@ -30,8 +31,69 @@ def scrape_property(
scraper_input = ScraperInput( scraper_input = ScraperInput(
location=location, location=location,
listing_type=ListingType[listing_type.upper()], listing_type=ListingType[listing_type.upper()],
site_name=SiteName[site_name.upper()],
) )
site = _scrapers[site_name.lower()](scraper_input) site = _scrapers[site_name.lower()](scraper_input)
results = site.search()
return site.search() properties_dfs = []
for result in results:
prop_data = result.__dict__
address_data = prop_data["address"]
prop_data["site_name"] = prop_data["site_name"].value
prop_data["listing_type"] = prop_data["listing_type"].value
prop_data["property_type"] = prop_data["property_type"].value.lower()
prop_data["address_one"] = address_data.address_one
prop_data["city"] = address_data.city
prop_data["state"] = address_data.state
prop_data["zip_code"] = address_data.zip_code
prop_data["address_two"] = address_data.address_two
del prop_data["address"]
if isinstance(result, Property):
desired_order = [
"listing_type",
"address_one",
"city",
"state",
"zip_code",
"address_two",
"url",
"property_type",
"price",
"beds",
"baths",
"square_feet",
"price_per_square_foot",
"lot_size",
"stories",
"year_built",
"agent_name",
"mls_id",
"description",
]
elif isinstance(result, Building):
desired_order = [
"address_one",
"city",
"state",
"zip_code",
"address_two",
"url",
"num_units",
"min_unit_price",
"max_unit_price",
"avg_unit_price",
"listing_type",
]
properties_df = pd.DataFrame([prop_data])
properties_df = properties_df[desired_order]
properties_dfs.append(properties_df)
return pd.concat(properties_dfs, ignore_index=True)

5
homeharvest/core/scrapers/__init__.py
View File

@ -1,12 +1,13 @@
from dataclasses import dataclass from dataclasses import dataclass
import requests import requests
from .models import Property, ListingType from .models import Property, ListingType, SiteName
@dataclass @dataclass
class ScraperInput: class ScraperInput:
location: str location: str
listing_type: ListingType listing_type: ListingType
site_name: SiteName
proxy_url: str | None = None proxy_url: str | None = None
@ -14,6 +15,8 @@ class Scraper:
def __init__(self, scraper_input: ScraperInput): def __init__(self, scraper_input: ScraperInput):
self.location = scraper_input.location self.location = scraper_input.location
self.session = requests.Session() self.session = requests.Session()
self.listing_type = scraper_input.listing_type
self.site_name = scraper_input.site_name
if scraper_input.proxy_url: if scraper_input.proxy_url:
self.session.proxies = { self.session.proxies = {

53
homeharvest/core/scrapers/models.py
View File

@ -2,12 +2,43 @@ from dataclasses import dataclass
from enum import Enum from enum import Enum
class SiteName(Enum):
ZILLOW = "zillow"
REDFIN = "redfin"
REALTOR = "realtor.com"
class ListingType(Enum): class ListingType(Enum):
FOR_SALE = "for_sale" FOR_SALE = "for_sale"
FOR_RENT = "for_rent" FOR_RENT = "for_rent"
SOLD = "sold" SOLD = "sold"
class PropertyType(Enum):
HOUSE = "HOUSE"
CONDO = "CONDO"
TOWNHOUSE = "townhousE"
SINGLE_FAMILY = "SINGLE_FAMILY"
MULTI_FAMILY = "MULTI_FAMILY"
LAND = "LAND"
OTHER = "OTHER"
@classmethod
def from_int_code(cls, code):
mapping = {
1: cls.HOUSE,
2: cls.CONDO,
3: cls.TOWNHOUSE,
4: cls.MULTI_FAMILY,
5: cls.LAND,
6: cls.OTHER,
8: cls.SINGLE_FAMILY,
13: cls.SINGLE_FAMILY,
}
return mapping.get(code, cls.OTHER)
@dataclass @dataclass
class Address: class Address:
address_one: str address_one: str
@ -18,35 +49,35 @@ class Address:
address_two: str | None = None address_two: str | None = None
@dataclass @dataclass()
class Property: class Realty:
site_name: SiteName
address: Address address: Address
url: str url: str
listing_type: ListingType | None = None
@dataclass
class Property(Realty):
price: int | None = None
beds: int | None = None beds: int | None = None
baths: float | None = None baths: float | None = None
stories: int | None = None stories: int | None = None
agent_name: str | None = None
year_built: int | None = None year_built: int | None = None
square_feet: int | None = None square_feet: int | None = None
price_per_square_foot: int | None = None price_per_square_foot: int | None = None
year_built: int | None = None year_built: int | None = None
price: int | None = None
mls_id: str | None = None mls_id: str | None = None
listing_type: ListingType | None = None agent_name: str | None = None
property_type: PropertyType | None = None
lot_size: int | None = None lot_size: int | None = None
description: str | None = None description: str | None = None
@dataclass @dataclass
class Building: class Building(Realty):
address: Address
url: str
num_units: int | None = None num_units: int | None = None
min_unit_price: int | None = None min_unit_price: int | None = None
max_unit_price: int | None = None max_unit_price: int | None = None
avg_unit_price: int | None = None avg_unit_price: int | None = None
listing_type: str | None = None

12
homeharvest/core/scrapers/redfin/__init__.py
View File

@ -1,5 +1,5 @@
import json import json
from ..models import Property, Address from ..models import Property, Address, PropertyType
from .. import Scraper from .. import Scraper
from typing import Any from typing import Any
@ -7,6 +7,7 @@ from typing import Any
class RedfinScraper(Scraper): class RedfinScraper(Scraper):
def __init__(self, scraper_input): def __init__(self, scraper_input):
super().__init__(scraper_input) super().__init__(scraper_input)
self.listing_type = scraper_input.listing_type
def _handle_location(self): def _handle_location(self):
url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format( url = "https://www.redfin.com/stingray/do/location-autocomplete?v=2&al=1&location={}".format(
@ -31,8 +32,7 @@ class RedfinScraper(Scraper):
return target["id"].split("_")[1], get_region_type(target["type"]) return target["id"].split("_")[1], get_region_type(target["type"])
@staticmethod def _parse_home(self, home: dict, single_search: bool = False) -> Property:
def _parse_home(home: dict, single_search: bool = False) -> Property:
def get_value(key: str) -> Any | None: def get_value(key: str) -> Any | None:
if key in home and "value" in home[key]: if key in home and "value" in home[key]:
return home[key]["value"] return home[key]["value"]
@ -53,10 +53,12 @@ class RedfinScraper(Scraper):
state=home["state"], state=home["state"],
zip_code=home["zip"], zip_code=home["zip"],
) )
url = "https://www.redfin.com{}".format(home["url"]) url = "https://www.redfin.com{}".format(home["url"])
property_type = home["propertyType"] if "propertyType" in home else None
return Property( return Property(
site_name=self.site_name,
listing_type=self.listing_type,
address=address, address=address,
url=url, url=url,
beds=home["beds"] if "beds" in home else None, beds=home["beds"] if "beds" in home else None,
@ -68,6 +70,8 @@ class RedfinScraper(Scraper):
if not single_search if not single_search
else home["yearBuilt"], else home["yearBuilt"],
square_feet=get_value("sqFt"), square_feet=get_value("sqFt"),
lot_size=home.get("lotSize", {}).get("value", None),
property_type=PropertyType.from_int_code(home.get("propertyType")),
price_per_square_foot=get_value("pricePerSqFt"), price_per_square_foot=get_value("pricePerSqFt"),
price=get_value("price"), price=get_value("price"),
mls_id=get_value("mlsId"), mls_id=get_value("mlsId"),

23
homeharvest/core/scrapers/zillow/__init__.py
View File

@ -1,13 +1,11 @@
import re import re
import json import json
from ..models import Property, Address, Building, ListingType from ..models import Property, Address, Building, ListingType, PropertyType
from ....exceptions import NoResultsFound, PropertyNotFound from ....exceptions import NoResultsFound, PropertyNotFound
from .. import Scraper from .. import Scraper
class ZillowScraper(Scraper): class ZillowScraper(Scraper):
listing_type: ListingType.FOR_SALE
def __init__(self, scraper_input): def __init__(self, scraper_input):
super().__init__(scraper_input) super().__init__(scraper_input)
self.listing_type = scraper_input.listing_type self.listing_type = scraper_input.listing_type
@ -65,15 +63,17 @@ class ZillowScraper(Scraper):
agent_name = self._extract_agent_name(home) agent_name = self._extract_agent_name(home)
beds = home["hdpData"]["homeInfo"]["bedrooms"] beds = home["hdpData"]["homeInfo"]["bedrooms"]
baths = home["hdpData"]["homeInfo"]["bathrooms"] baths = home["hdpData"]["homeInfo"]["bathrooms"]
listing_type = home["hdpData"]["homeInfo"].get("homeType") property_type = home["hdpData"]["homeInfo"].get("homeType")
return Property( return Property(
site_name=self.site_name,
address=address, address=address,
agent_name=agent_name, agent_name=agent_name,
url=url, url=url,
beds=beds, beds=beds,
baths=baths, baths=baths,
listing_type=listing_type, listing_type=self.listing_type,
property_type=PropertyType(property_type),
**price_data, **price_data,
) )
else: else:
@ -83,10 +83,11 @@ class ZillowScraper(Scraper):
address = Address(address_one, city, state, zip_code, address_two) address = Address(address_one, city, state, zip_code, address_two)
building_info = self._extract_building_info(home) building_info = self._extract_building_info(home)
return Building(address=address, url=url, **building_info) return Building(
site_name=self.site_name, address=address, url=url, **building_info
)
@classmethod def _get_single_property_page(self, property_data: dict):
def _get_single_property_page(cls, property_data: dict):
""" """
This method is used when a user enters the exact location & zillow returns just one property This method is used when a user enters the exact location & zillow returns just one property
""" """
@ -104,8 +105,11 @@ class ZillowScraper(Scraper):
state=address_data["state"], state=address_data["state"],
zip_code=address_data["zipcode"], zip_code=address_data["zipcode"],
) )
property_type = property_data.get("homeType", None)
print(property_type)
return Property( return Property(
site_name=self.site_name,
address=address, address=address,
url=url, url=url,
beds=property_data.get("bedrooms", None), beds=property_data.get("bedrooms", None),
@ -121,7 +125,8 @@ class ZillowScraper(Scraper):
"pricePerSquareFoot", None "pricePerSquareFoot", None
), ),
square_feet=property_data.get("livingArea", None), square_feet=property_data.get("livingArea", None),
listing_type=property_data.get("homeType", None), property_type=PropertyType(property_type),
listing_type=self.listing_type,
) )
def _extract_building_info(self, home: dict) -> dict: def _extract_building_info(self, home: dict) -> dict:

185
poetry.lock generated
View File

@ -142,6 +142,81 @@ files = [
{file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
] ]
[[package]]
name = "numpy"
version = "1.25.2"
description = "Fundamental package for array computing in Python"
optional = false
python-versions = ">=3.9"
files = [
{file = "numpy-1.25.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:db3ccc4e37a6873045580d413fe79b68e47a681af8db2e046f1dacfa11f86eb3"},
{file = "numpy-1.25.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:90319e4f002795ccfc9050110bbbaa16c944b1c37c0baeea43c5fb881693ae1f"},
{file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dfe4a913e29b418d096e696ddd422d8a5d13ffba4ea91f9f60440a3b759b0187"},
{file = "numpy-1.25.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f08f2e037bba04e707eebf4bc934f1972a315c883a9e0ebfa8a7756eabf9e357"},
{file = "numpy-1.25.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bec1e7213c7cb00d67093247f8c4db156fd03075f49876957dca4711306d39c9"},
{file = "numpy-1.25.2-cp310-cp310-win32.whl", hash = "sha256:7dc869c0c75988e1c693d0e2d5b26034644399dd929bc049db55395b1379e044"},
{file = "numpy-1.25.2-cp310-cp310-win_amd64.whl", hash = "sha256:834b386f2b8210dca38c71a6e0f4fd6922f7d3fcff935dbe3a570945acb1b545"},
{file = "numpy-1.25.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c5462d19336db4560041517dbb7759c21d181a67cb01b36ca109b2ae37d32418"},
{file = "numpy-1.25.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c5652ea24d33585ea39eb6a6a15dac87a1206a692719ff45d53c5282e66d4a8f"},
{file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d60fbae8e0019865fc4784745814cff1c421df5afee233db6d88ab4f14655a2"},
{file = "numpy-1.25.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60e7f0f7f6d0eee8364b9a6304c2845b9c491ac706048c7e8cf47b83123b8dbf"},
{file = "numpy-1.25.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:bb33d5a1cf360304754913a350edda36d5b8c5331a8237268c48f91253c3a364"},
{file = "numpy-1.25.2-cp311-cp311-win32.whl", hash = "sha256:5883c06bb92f2e6c8181df7b39971a5fb436288db58b5a1c3967702d4278691d"},
{file = "numpy-1.25.2-cp311-cp311-win_amd64.whl", hash = "sha256:5c97325a0ba6f9d041feb9390924614b60b99209a71a69c876f71052521d42a4"},
{file = "numpy-1.25.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b79e513d7aac42ae918db3ad1341a015488530d0bb2a6abcbdd10a3a829ccfd3"},
{file = "numpy-1.25.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:eb942bfb6f84df5ce05dbf4b46673ffed0d3da59f13635ea9b926af3deb76926"},
{file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e0746410e73384e70d286f93abf2520035250aad8c5714240b0492a7302fdca"},
{file = "numpy-1.25.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7806500e4f5bdd04095e849265e55de20d8cc4b661b038957354327f6d9b295"},
{file = "numpy-1.25.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8b77775f4b7df768967a7c8b3567e309f617dd5e99aeb886fa14dc1a0791141f"},
{file = "numpy-1.25.2-cp39-cp39-win32.whl", hash = "sha256:2792d23d62ec51e50ce4d4b7d73de8f67a2fd3ea710dcbc8563a51a03fb07b01"},
{file = "numpy-1.25.2-cp39-cp39-win_amd64.whl", hash = "sha256:76b4115d42a7dfc5d485d358728cdd8719be33cc5ec6ec08632a5d6fca2ed380"},
{file = "numpy-1.25.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:1a1329e26f46230bf77b02cc19e900db9b52f398d6722ca853349a782d4cff55"},
{file = "numpy-1.25.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c3abc71e8b6edba80a01a52e66d83c5d14433cbcd26a40c329ec7ed09f37901"},
{file = "numpy-1.25.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:1b9735c27cea5d995496f46a8b1cd7b408b3f34b6d50459d9ac8fe3a20cc17bf"},
{file = "numpy-1.25.2.tar.gz", hash = "sha256:fd608e19c8d7c55021dffd43bfe5492fab8cc105cc8986f813f8c3c048b38760"},
]
[[package]]
name = "numpy"
version = "1.26.0"
description = "Fundamental package for array computing in Python"
optional = false
python-versions = "<3.13,>=3.9"
files = [
{file = "numpy-1.26.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f8db2f125746e44dce707dd44d4f4efeea8d7e2b43aace3f8d1f235cfa2733dd"},
{file = "numpy-1.26.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:0621f7daf973d34d18b4e4bafb210bbaf1ef5e0100b5fa750bd9cde84c7ac292"},
{file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:51be5f8c349fdd1a5568e72713a21f518e7d6707bcf8503b528b88d33b57dc68"},
{file = "numpy-1.26.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:767254ad364991ccfc4d81b8152912e53e103ec192d1bb4ea6b1f5a7117040be"},
{file = "numpy-1.26.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:436c8e9a4bdeeee84e3e59614d38c3dbd3235838a877af8c211cfcac8a80b8d3"},
{file = "numpy-1.26.0-cp310-cp310-win32.whl", hash = "sha256:c2e698cb0c6dda9372ea98a0344245ee65bdc1c9dd939cceed6bb91256837896"},
{file = "numpy-1.26.0-cp310-cp310-win_amd64.whl", hash = "sha256:09aaee96c2cbdea95de76ecb8a586cb687d281c881f5f17bfc0fb7f5890f6b91"},
{file = "numpy-1.26.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:637c58b468a69869258b8ae26f4a4c6ff8abffd4a8334c830ffb63e0feefe99a"},
{file = "numpy-1.26.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:306545e234503a24fe9ae95ebf84d25cba1fdc27db971aa2d9f1ab6bba19a9dd"},
{file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c6adc33561bd1d46f81131d5352348350fc23df4d742bb246cdfca606ea1208"},
{file = "numpy-1.26.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e062aa24638bb5018b7841977c360d2f5917268d125c833a686b7cbabbec496c"},
{file = "numpy-1.26.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:546b7dd7e22f3c6861463bebb000646fa730e55df5ee4a0224408b5694cc6148"},
{file = "numpy-1.26.0-cp311-cp311-win32.whl", hash = "sha256:c0b45c8b65b79337dee5134d038346d30e109e9e2e9d43464a2970e5c0e93229"},
{file = "numpy-1.26.0-cp311-cp311-win_amd64.whl", hash = "sha256:eae430ecf5794cb7ae7fa3808740b015aa80747e5266153128ef055975a72b99"},
{file = "numpy-1.26.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:166b36197e9debc4e384e9c652ba60c0bacc216d0fc89e78f973a9760b503388"},
{file = "numpy-1.26.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f042f66d0b4ae6d48e70e28d487376204d3cbf43b84c03bac57e28dac6151581"},
{file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5e18e5b14a7560d8acf1c596688f4dfd19b4f2945b245a71e5af4ddb7422feb"},
{file = "numpy-1.26.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f6bad22a791226d0a5c7c27a80a20e11cfe09ad5ef9084d4d3fc4a299cca505"},
{file = "numpy-1.26.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4acc65dd65da28060e206c8f27a573455ed724e6179941edb19f97e58161bb69"},
{file = "numpy-1.26.0-cp312-cp312-win32.whl", hash = "sha256:bb0d9a1aaf5f1cb7967320e80690a1d7ff69f1d47ebc5a9bea013e3a21faec95"},
{file = "numpy-1.26.0-cp312-cp312-win_amd64.whl", hash = "sha256:ee84ca3c58fe48b8ddafdeb1db87388dce2c3c3f701bf447b05e4cfcc3679112"},
{file = "numpy-1.26.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:4a873a8180479bc829313e8d9798d5234dfacfc2e8a7ac188418189bb8eafbd2"},
{file = "numpy-1.26.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:914b28d3215e0c721dc75db3ad6d62f51f630cb0c277e6b3bcb39519bed10bd8"},
{file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c78a22e95182fb2e7874712433eaa610478a3caf86f28c621708d35fa4fd6e7f"},
{file = "numpy-1.26.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86f737708b366c36b76e953c46ba5827d8c27b7a8c9d0f471810728e5a2fe57c"},
{file = "numpy-1.26.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b44e6a09afc12952a7d2a58ca0a2429ee0d49a4f89d83a0a11052da696440e49"},
{file = "numpy-1.26.0-cp39-cp39-win32.whl", hash = "sha256:5671338034b820c8d58c81ad1dafc0ed5a00771a82fccc71d6438df00302094b"},
{file = "numpy-1.26.0-cp39-cp39-win_amd64.whl", hash = "sha256:020cdbee66ed46b671429c7265cf00d8ac91c046901c55684954c3958525dab2"},
{file = "numpy-1.26.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0792824ce2f7ea0c82ed2e4fecc29bb86bee0567a080dacaf2e0a01fe7654369"},
{file = "numpy-1.26.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7d484292eaeb3e84a51432a94f53578689ffdea3f90e10c8b203a99be5af57d8"},
{file = "numpy-1.26.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:186ba67fad3c60dbe8a3abff3b67a91351100f2661c8e2a80364ae6279720299"},
{file = "numpy-1.26.0.tar.gz", hash = "sha256:f93fc78fe8bf15afe2b8d6b6499f1c73953169fad1e9a8dd086cdff3190e7fdf"},
]
[[package]] [[package]]
name = "packaging" name = "packaging"
version = "23.1" version = "23.1"
@ -153,6 +228,67 @@ files = [
{file = "packaging-23.1.tar.gz", hash = "sha256:a392980d2b6cffa644431898be54b0045151319d1e7ec34f0cfed48767dd334f"}, {file = "packaging-23.1.tar.gz", hash = "sha256:a392980d2b6cffa644431898be54b0045151319d1e7ec34f0cfed48767dd334f"},
] ]
[[package]]
name = "pandas"
version = "2.1.0"
description = "Powerful data structures for data analysis, time series, and statistics"
optional = false
python-versions = ">=3.9"
files = [
{file = "pandas-2.1.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:40dd20439ff94f1b2ed55b393ecee9cb6f3b08104c2c40b0cb7186a2f0046242"},
{file = "pandas-2.1.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d4f38e4fedeba580285eaac7ede4f686c6701a9e618d8a857b138a126d067f2f"},
{file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e6a0fe052cf27ceb29be9429428b4918f3740e37ff185658f40d8702f0b3e09"},
{file = "pandas-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d81e1813191070440d4c7a413cb673052b3b4a984ffd86b8dd468c45742d3cc"},
{file = "pandas-2.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:eb20252720b1cc1b7d0b2879ffc7e0542dd568f24d7c4b2347cb035206936421"},
{file = "pandas-2.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:38f74ef7ebc0ffb43b3d633e23d74882bce7e27bfa09607f3c5d3e03ffd9a4a5"},
{file = "pandas-2.1.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cda72cc8c4761c8f1d97b169661f23a86b16fdb240bdc341173aee17e4d6cedd"},
{file = "pandas-2.1.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d97daeac0db8c993420b10da4f5f5b39b01fc9ca689a17844e07c0a35ac96b4b"},
{file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8c58b1113892e0c8078f006a167cc210a92bdae23322bb4614f2f0b7a4b510f"},
{file = "pandas-2.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:629124923bcf798965b054a540f9ccdfd60f71361255c81fa1ecd94a904b9dd3"},
{file = "pandas-2.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:70cf866af3ab346a10debba8ea78077cf3a8cd14bd5e4bed3d41555a3280041c"},
{file = "pandas-2.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:d53c8c1001f6a192ff1de1efe03b31a423d0eee2e9e855e69d004308e046e694"},
{file = "pandas-2.1.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:86f100b3876b8c6d1a2c66207288ead435dc71041ee4aea789e55ef0e06408cb"},
{file = "pandas-2.1.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:28f330845ad21c11db51e02d8d69acc9035edfd1116926ff7245c7215db57957"},
{file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b9a6ccf0963db88f9b12df6720e55f337447aea217f426a22d71f4213a3099a6"},
{file = "pandas-2.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d99e678180bc59b0c9443314297bddce4ad35727a1a2656dbe585fd78710b3b9"},
{file = "pandas-2.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b31da36d376d50a1a492efb18097b9101bdbd8b3fbb3f49006e02d4495d4c644"},
{file = "pandas-2.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:0164b85937707ec7f70b34a6c3a578dbf0f50787f910f21ca3b26a7fd3363437"},
{file = "pandas-2.1.0.tar.gz", hash = "sha256:62c24c7fc59e42b775ce0679cfa7b14a5f9bfb7643cfbe708c960699e05fb918"},
]
[package.dependencies]
numpy = [
{version = ">=1.22.4", markers = "python_version < \"3.11\""},
{version = ">=1.23.2", markers = "python_version >= \"3.11\""},
]
python-dateutil = ">=2.8.2"
pytz = ">=2020.1"
tzdata = ">=2022.1"
[package.extras]
all = ["PyQt5 (>=5.15.6)", "SQLAlchemy (>=1.4.36)", "beautifulsoup4 (>=4.11.1)", "bottleneck (>=1.3.4)", "dataframe-api-compat (>=0.1.7)", "fastparquet (>=0.8.1)", "fsspec (>=2022.05.0)", "gcsfs (>=2022.05.0)", "html5lib (>=1.1)", "hypothesis (>=6.46.1)", "jinja2 (>=3.1.2)", "lxml (>=4.8.0)", "matplotlib (>=3.6.1)", "numba (>=0.55.2)", "numexpr (>=2.8.0)", "odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pandas-gbq (>=0.17.5)", "psycopg2 (>=2.9.3)", "pyarrow (>=7.0.0)", "pymysql (>=1.0.2)", "pyreadstat (>=1.1.5)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)", "pyxlsb (>=1.0.9)", "qtpy (>=2.2.0)", "s3fs (>=2022.05.0)", "scipy (>=1.8.1)", "tables (>=3.7.0)", "tabulate (>=0.8.10)", "xarray (>=2022.03.0)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)", "zstandard (>=0.17.0)"]
aws = ["s3fs (>=2022.05.0)"]
clipboard = ["PyQt5 (>=5.15.6)", "qtpy (>=2.2.0)"]
compression = ["zstandard (>=0.17.0)"]
computation = ["scipy (>=1.8.1)", "xarray (>=2022.03.0)"]
consortium-standard = ["dataframe-api-compat (>=0.1.7)"]
excel = ["odfpy (>=1.4.1)", "openpyxl (>=3.0.10)", "pyxlsb (>=1.0.9)", "xlrd (>=2.0.1)", "xlsxwriter (>=3.0.3)"]
feather = ["pyarrow (>=7.0.0)"]
fss = ["fsspec (>=2022.05.0)"]
gcp = ["gcsfs (>=2022.05.0)", "pandas-gbq (>=0.17.5)"]
hdf5 = ["tables (>=3.7.0)"]
html = ["beautifulsoup4 (>=4.11.1)", "html5lib (>=1.1)", "lxml (>=4.8.0)"]
mysql = ["SQLAlchemy (>=1.4.36)", "pymysql (>=1.0.2)"]
output-formatting = ["jinja2 (>=3.1.2)", "tabulate (>=0.8.10)"]
parquet = ["pyarrow (>=7.0.0)"]
performance = ["bottleneck (>=1.3.4)", "numba (>=0.55.2)", "numexpr (>=2.8.0)"]
plot = ["matplotlib (>=3.6.1)"]
postgresql = ["SQLAlchemy (>=1.4.36)", "psycopg2 (>=2.9.3)"]
spss = ["pyreadstat (>=1.1.5)"]
sql-other = ["SQLAlchemy (>=1.4.36)"]
test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-asyncio (>=0.17.0)", "pytest-xdist (>=2.2.0)"]
xml = ["lxml (>=4.8.0)"]
[[package]] [[package]]
name = "pluggy" name = "pluggy"
version = "1.3.0" version = "1.3.0"
@ -190,6 +326,31 @@ tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
[package.extras] [package.extras]
testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"] testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
[[package]]
name = "python-dateutil"
version = "2.8.2"
description = "Extensions to the standard Python datetime module"
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
files = [
{file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
{file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
]
[package.dependencies]
six = ">=1.5"
[[package]]
name = "pytz"
version = "2023.3.post1"
description = "World timezone definitions, modern and historical"
optional = false
python-versions = "*"
files = [
{file = "pytz-2023.3.post1-py2.py3-none-any.whl", hash = "sha256:ce42d816b81b68506614c11e8937d3aa9e41007ceb50bfdcb0749b921bf646c7"},
{file = "pytz-2023.3.post1.tar.gz", hash = "sha256:7b4fddbeb94a1eba4b557da24f19fdf9db575192544270a9101d8509f9f43d7b"},
]
[[package]] [[package]]
name = "requests" name = "requests"
version = "2.31.0" version = "2.31.0"
@ -211,6 +372,17 @@ urllib3 = ">=1.21.1,<3"
socks = ["PySocks (>=1.5.6,!=1.5.7)"] socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"] use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "six"
version = "1.16.0"
description = "Python 2 and 3 compatibility utilities"
optional = false
python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
files = [
{file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
{file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
]
[[package]] [[package]]
name = "tomli" name = "tomli"
version = "2.0.1" version = "2.0.1"
@ -222,6 +394,17 @@ files = [
{file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"}, {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
] ]
[[package]]
name = "tzdata"
version = "2023.3"
description = "Provider of IANA time zone data"
optional = false
python-versions = ">=2"
files = [
{file = "tzdata-2023.3-py2.py3-none-any.whl", hash = "sha256:7e65763eef3120314099b6939b5546db7adce1e7d6f2e179e3df563c70511eda"},
{file = "tzdata-2023.3.tar.gz", hash = "sha256:11ef1e08e54acb0d4f95bdb1be05da659673de4acbd21bf9c69e94cc5e907a3a"},
]
[[package]] [[package]]
name = "urllib3" name = "urllib3"
version = "2.0.4" version = "2.0.4"
@ -242,4 +425,4 @@ zstd = ["zstandard (>=0.18.0)"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = "^3.10" python-versions = "^3.10"
content-hash = "bc3567f9501f9e18bf9f53d8b4efe1e7e3fc2d750ceda2fbab165bfa22d49c64" content-hash = "eede625d6d45085e143b0af246cb2ce00cff8579c667be3b63387c8594a5570d"

1
pyproject.toml
View File

@ -9,6 +9,7 @@ readme = "README.md"
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.10" python = "^3.10"
requests = "^2.31.0" requests = "^2.31.0"
pandas = "^2.1.0"
[tool.poetry.group.dev.dependencies] [tool.poetry.group.dev.dependencies]