Scrape

import requests
import csv
import time
import backoff
from wappalyzer import Wappalyzer, WebPage
wappalyzer = Wappalyzer.latest()

platforms = ['WooCommerce','Shopify','Bigcommerce','Magento','Volusion','InkFrog','3DCart','OsCommerce','Yahoo! Ecommerce','Microsoft ASP.NET']

@backoff.on_exception(backoff.expo, (requests.exceptions.ReadTimeout, requests.exceptions.Timeout, requests.exceptions.ConnectionError))
def fetch_result(webpage):
    return wappalyzer.analyze(webpage)

with open('/Users/aabesh/Documents/Scripts/eriktest.csv') as csv_input, open('/Users/aabesh/Documents/Scripts/erikshopsoutput.csv', "w") as csv_output:
    csv_reader = csv.reader(csv_input, delimiter=',')
    writer = csv.writer(csv_output, lineterminator='\n')
    writer.writerow(['Shop Name', 'URL', 'Reverb ID', 'Integration', 'Close Website Platform', 'Wappalyzer Website'])
    next(csv_reader)
    for row in csv_reader:
        url = row[1]
        if not url: continue
        try:
            webpage = WebPage.new_from_url(row[1])
            result = fetch_result(webpage)
            print(result)
            wapwebsite = ",".join([u for u in result if u in platforms]) or ""
            row.append(wapwebsite)
            print(row)
            print(wapwebsite)
            writer.writerow(row)
        except:
            print(webpage," timed out.")