(20241227) Auto GIT deployment test.

This commit is contained in:
2024-12-27 17:18:03 +05:30
parent 2349bf3d3e
commit fb29011749
13 changed files with 1152 additions and 6 deletions
@@ -0,0 +1,263 @@
"""
AUTHOR:
Khushal P Soonderji
DATE:
Thursday, 28th Nov., 2024
OBJECTIVE:
To provide a way to retrieve dates of important events like financial-results, stock-splits, fund-raising, etc.
from NSE's portal.
NOTE: This method involves web scraping. It is good for proof-of-concept development, but it is recommended that
more professional data-sources be used when the product starts becoming mature.
REFERENCES:
N/A
DOWNLOADS:
N/A
"""
# *****************************************************************************************************************
# ***** ****
# *** IMPORT ***
# ***** ****
# *****************************************************************************************************************
# To make sibling directories accessible for imports:
import sys
sys.path.append(".")
sys.path.append("..")
# System-level activities:
import io
# My utils:
from utils_v2.string import json
from utils_v2.date_time import date_time
# NSE-related utils:
from utils_v2.nse.controllers.base import AsyncNSEBase
from utils_v2.nse.models.api_call import NSEApiResponse
# To make REST-ful API calls:
import httpx
# To work with date and time:
import datetime
# To work with datatypes:
from typing import Any, List
# For asynchronous activities:
import asyncio
# *****************************************************************************************************************
# ***** ****
# *** MACROS / ONE-TIME INIT ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** VARIABLES ***
# ***** ****
# *****************************************************************************************************************
# --- Nothing Yet
# *****************************************************************************************************************
# ***** ****
# *** FUNCTIONS ***
# ***** ****
# *****************************************************************************************************************
class NSECorporateActions(AsyncNSEBase):
# The types of corporate actions/entities:
TYPE_EQUITIES = "equities"
TYPE_MUTUAL_FUNDS = "mf"
TYPE_DEBT = "debt"
TYPE_SME = "sme"
def __init__(
self,
http_client: httpx.AsyncClient,
debug = True,
debug_prefix = "NSE (C.Act.) | ",
debug_only_errors = True
):
# Pass on the initialization to the parent:
super().__init__(
base_url = r"https://www.nseindia.com/companies-listing/corporate-filings-actions",
data_url = r"https://www.nseindia.com/api/corporates-corporateActions",
http_client = http_client,
debug = debug,
debug_prefix = debug_prefix,
debug_only_errors = debug_only_errors
)
async def get_data(
self,
action_type: str,
from_date: datetime.datetime,
to_date: datetime.datetime,
return_raw: bool = False,
) -> NSEApiResponse:
"""
To get the data of the corporate event calendar.
:param action_type: The option between 'equities", "mf", "debt", and "sme".
:param from_date: The starting date (inclusive) from which the events must be fetched.
:param to_date: The ending date (inclusive) till which the events must be fetched.
:param return_raw: Whether you want the raw JSON from NSE or you want it formatted.
:return: The raw or formatted event calendar data in the 'data' field of the response model.
"""
# Make the API call:
api_response = await self.get(
params = {
"index": action_type,
"from_date": from_date.strftime("%d-%m-%Y"),
"to_date": to_date.strftime("%d-%m-%Y"),
}
)
# If the API call was successful:
if api_response.httpCode in [200]:
api_response.success = True
if return_raw: api_response.data = await api_response.get_json()
else:
try: api_response.data = self.format_data(
raw_json = await api_response.get_json(),
timestamp = date_time.get_current_utc_date_time(as_string = True),
raise_exception = True
)
except Exception as exception:
api_response.exception = exception
api_response.success = False
# Done here:
return api_response
@staticmethod
def format_data(
raw_json: List[dict],
timestamp: datetime.datetime = None,
raise_exception: bool = False
) -> List[dict] | None:
"""
We format the data here to be able to retrieve it properly later.
:param raw_json: The raw data as scraped from NSE.
:param timestamp: The timestamp at which the data was scraped. This shall be useful for data retrieval from the
database, later.
:param raise_exception: If set to True, any exception will be propagated. If set to False, any exception will be
suppressed internally.
:return: The formatted data if successful, else None.
"""
# Can't do anything if the chain itself is null:
if raw_json is None: return raw_json
# Start by assuming failure:
formatted_data = None
# Ensure that we've got a proper timestamp:
if timestamp is None: timestamp = date_time.get_current_utc_date_time(as_string = False)
try:
# Format the data:
formatted_data = [
{
"scrapeTs": timestamp,
"symbol": action["symbol"],
"company": action["comp"],
"isin": action["isin"],
"segment": action["series"],
"faceVal": action["faceVal"],
"action": action["subject"],
"exDate": action["exDate"],
"recDate": action["recDate"],
"bcStartDate": action["bcStartDate"],
"bcEndDate": action["bcEndDate"],
"ndStartDate": action["ndStartDate"],
"caBroadcastDate": action["caBroadcastDate"],
"ind": action["ind"],
# "action": action["subject"],
# "action": action["subject"],
} for action in raw_json
]
# If something goes wrong:
except Exception as exception:
formatted_data = None
if raise_exception: raise
# Done here:
return formatted_data
# *****************************************************************************************************************
# ***** ****
# *** MAIN PROGRAM ***
# ***** ****
# *****************************************************************************************************************
if __name__ == "__main__":
async def main():
# Create an HTTP client:
test_client = httpx.AsyncClient(
limits = httpx.Limits(
max_connections = 100, # ............ Maximum number of connections allowed in the pool.
max_keepalive_connections = 50, # ... Maximum number of connections that can be kept alive.
),
timeout = httpx.Timeout(
pool = 120.0, # .... Time to wait for a free connection from the pool.
connect = 2.5, # ... Time to wait for establishing a connection to the server.
write = 10.0, # .... Time to wait for sending data.
read = 2.5 # ....... Time to wait for receiving data.
)
)
# Create an instance of the scraper, and refresh its cookies:
my_nse = NSECorporateActions(http_client = test_client)
# Get and show the data:
to_date = date_time.get_current_ist_date_time()
from_date = to_date - datetime.timedelta(days = 31)
print("FROM :", from_date)
print("TO :", to_date)
api_response = await my_nse.get_data(
action_type = NSECorporateActions.TYPE_EQUITIES,
from_date = from_date,
to_date = to_date,
return_raw = True
)
print("SUMMARY:", api_response.to_markdown(), "\n---\n\n")
if api_response.success: print("CORPORATE ACTIONS:", json.to_string(api_response.data, default = str))
asyncio.run(main())
@@ -35,7 +35,6 @@
# To make sibling directories accessible for imports:
import sys
from time import timezone
sys.path.append(".")
sys.path.append("..")