scraper_file_read.py

import os
import csv
import requests
from dotenv import load_dotenv
from utils import extract_emails, name_email_similarity


load_dotenv()
HASDATA_API_KEY = os.getenv('HASDATA_API_KEY')

URL = 'https://api.hasdata.com/scrape/google/serp'

HEADERS = {
    'x-api-key': HASDATA_API_KEY,
    'Content-Type': "application/json"
}


def read_csv_file(file_path: str):
    with open(file_path, newline="", encoding="utf-8") as f:
        reader = csv.DictReader(f)
        return list(reader)


def get_person_email(person_first_name, person_last_name, person_company):
    info_to_extract = 'email'
    term_to_search = f'"{person_first_name}" "{person_last_name}" {person_company} {info_to_extract}'
    params = {"q": term_to_search}

    response = requests.get(url=URL, params=params, headers=HEADERS)
    response = response.json()

    most_similar_email = ''
    max_similarity_so_far = 0

    for result in response['organicResults']:
        snippet = result['snippet']
        full_name = f'{person_last_name} {person_last_name}'
        emails = extract_emails(snippet)
        for email in emails:
            score = name_email_similarity(full_name, email)
            if score > max_similarity_so_far:
                max_similarity_so_far = score
                most_similar_email = email

    return most_similar_email


def main():
    csv_data = read_csv_file('people_info.csv')
    print('\n\n')
    for row in csv_data:
        person_first_name, person_last_name = row['full_name'].split(' ')
        person_company = row['company']
        email = get_person_email(person_first_name, person_last_name, person_company)
        print(f'{person_first_name} {person_last_name}')
        print(f'Email: {email}\n')


if '__main__' == __name__:
    main()