app.py

import gradio as gr
import pandas as pd
import requests
from bs4 import BeautifulSoup

example_tickers = [
    {"Ticker": "PLD", "Company Name": "Prologis Inc"},
    {"Ticker": "PSA", "Company Name": "Public Storage"},
    {"Ticker": "O", "Company Name": "Realty Income Corp"},
    {
        "Ticker": "META",
        "Company Name": "Meta Platforms",
    },
    {"Ticker": "AMZN", "Company Name": "Amazon.com"},
    {"Ticker": "MSFT", "Company Name": "Microsoft Corporation"},
]


def get_esg_from_yahoo_finance(row):
    elements = []
    # This is a standard user-agent of Chrome browser running on Windows 10
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36"
    }
    html = requests.get(
        "https://finance.yahoo.com/quote/" + row.Ticker + "/sustainability",
        headers=headers,
    ).text
    soup = BeautifulSoup(html, "html.parser")

    scores = soup.find_all("div", {"class": "content svelte-y3c2sq"})
    for score in scores:
        elements.append(float(score.find("h4").text.strip()))
    if elements:
        row["Total ESG Risk Score"] = elements[0]
        row["Environmental Risk Score"] = elements[1]
        row["Social Risk Score"] = elements[2]
        row["Governance Risk Score"] = elements[3]
    else:
        row["Total ESG Risk Score"] = None
        row["Environmental Risk Score"] = None
        row["Social Risk Score"] = None
        row["Governance Risk Score"] = None
    return row


def get_esg_score_from_google_finance(row):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.134 Safari/537.36"
    }

    html = requests.get(
        f"https://www.google.com/finance/quote/META:NASDAQ", headers=headers, timeout=30
    ).text
    soup = BeautifulSoup(html, "html.parser")
    scores = soup.find_all("div", {"class": "IPIeJ"})

    row["CDP Score"] = scores[0].find("div", {"class": "P6K39c"}).text

    return row


example_input_data = pd.DataFrame(example_tickers)


inputs = [
    gr.Dataframe(
        row_count=(6, "dynamic"),
        col_count=(1, "dynamic"),
        label="Input Data",
        interactive=1,
    )
]

outputs = [
    gr.Dataframe(
        row_count=(6, "dynamic"),
        col_count=(7, "fixed"),
        label="ESG Scores",
        headers=[
            "Ticker",
            "Company Name",
            "Total ESG Risk Score",
            "Environmental Risk Score",
            "Social Risk Score",
            "Governance Risk Score",
            "CDP Score",
        ],
    )
]


def get_esg_scores(input_dataframe):
    input_dataframe = input_dataframe.apply(
        lambda x: get_esg_from_yahoo_finance(x), axis=1
    )
    input_dataframe = input_dataframe.apply(
        lambda x: get_esg_score_from_google_finance(x), axis=1
    )

    return input_dataframe


gr.Interface(
    fn=get_esg_scores,
    inputs=inputs,
    outputs=outputs,
    title="🌳ESG  Data Scraper🌳\n\nIt scrapes ESG ratings from Yahoo Finance and Google Finance!",
    examples=[[example_input_data.head(6)]],
).launch()