read_csv_xlsx_scrapy.py

import scrapy
import pandas as pd


base_url = 'https://stackoverflow.com/questions/tagged/{}'

def read_csv():
    df = pd.read_csv('so_tags.csv')
    return df['Tags'].values.tolist()


def read_excel():
    df = pd.read_excel('so_tags.xlsx')
    return df['Tags'].values.tolist()


class SoSpider(scrapy.Spider):
    name = 'so'

    def start_requests(self):
        for tag in read_excel():
            yield scrapy.Request(base_url.format(tag))

    def parse(self, response):
        questions = response.xpath('normalize-space(//*[@id="mainbar"]/div[4]/div/div[1]/text())').get()
        questions = questions.strip('questions')

        yield {
            'questions': questions,
            'url': response.url
        }