Web scraper example

import time
import concurrent.futures
import xlrd
import csv
import requests
from bs4 import BeautifulSoup
from bs4 import SoupStrainer
from menu import Link


def read_initial_file(location):
    primary_list = []
    wb = xlrd.open_workbook(location)
    sheet = wb.sheet_by_index(0)
    for i in range(sheet.nrows)[1:]:
        try:
            category = sheet.row_values(i)[0]
            link = sheet.row_values(i)[1]
            img_link = sheet.row_values(i)[2]
            primary_list.append(Link(category, link, img_link))
        except:
            pass
    return primary_list


def get_details(link):
    description = ''
    session = requests.Session()
    response = session.get(link)
    strainer = SoupStrainer('div', attrs={'class': 'value'})
    strainer1 = SoupStrainer('span', {'class': 'price'})
    strainer2 = SoupStrainer('span', {'class': 'base'})
    soup = BeautifulSoup(response.content, 'lxml', parse_only=strainer)
    p_description = soup.findAll('p')
    for desc in p_description:
        description += desc.getText(strip=True) + '\n'
    brand_name = soup.div.getText(strip=True)
    price = BeautifulSoup(response.content, 'lxml', parse_only=strainer1).span.getText(strip=True)
    name = BeautifulSoup(response.content, 'lxml', parse_only=strainer2).getText(strip=True)
    return name, price, brand_name, description


def write_output(temp_list):
    with open('C://Users/henri/OneDrive/Desktop/Images/Write2/en.xls', 'w', encoding='utf-8', newline='') as f:
        writer = csv.writer(f)
        writer.writerow(['Product Name', 'Price', 'Brand', 'Description', 'Category', 'Image Link'])
        f.flush()
        for i, list_row in enumerate(temp_list):
            try:
                x = list(temp_list[i][0].result())
                x.extend([temp_list[i][1], temp_list[i][2]])
                writer.writerow(x)
            except:
                pass
        f.flush()


if __name__ == '__main__':
    start = time.perf_counter()
    # reads a provided file with Category, Link and Image Link
    work_book = read_initial_file('C://Users/henri/OneDrive/Desktop/Images/Read.xls')

    # temp_list collects information that was scraped from web
    temp_list = []
    with concurrent.futures.ProcessPoolExecutor() as executor:
        for row in work_book:
            try:
                temp_list.append([executor.submit(get_details, row.link), row.name, row.img_link.replace('\xa0', '')])
            except:
                pass

    # writes temp_list into a file
    print('Writing file.')
    write_output(temp_list)

    finish = time.perf_counter()
    print(f'Finished in {round(finish - start, 2)} second(s)')