Screenshots for federal domains using pikwy api

fedweb_screenshots.py

#Loop thru csv of federal domains, write screenshots

#!/usr/bin/python3
import csv 
import urllib.request
import urllib.parse
import time
from datetime import datetime

#CISA list of Federal domains https://raw.githubusercontent.com/cisagov/dotgov-data/main/current-federal.csv

with open('current-federal.csv', 'r') as csvfile: 
  
    next(csvfile, None)  # skip the headers

    # Return a reader object which will 
    # iterate over lines in the given csvfile 
    csv_reader = csv.reader(csvfile) 

    # convert string to list 
    #list_of_csv = list(csv_reader) 
    #print(list_of_csv) 

    for row in csv_reader:
        url = 'https://www.' + row[0]
        url_name = row[0]
        #agency_name = row[2].replace(" ", "") #remove spaces in agency name for file name
        #time.sleep(5) #add a delay - dont need delay

# python3 api example from pikwy https://pikwy.com/api#codeexample

        def generate_screenshot_api_url(token, options):
          api_url = 'https://api.pikwy.com/?token=' + token
          if token:
            api_url = api_url + '&url=' + options.get('url')
            api_url = api_url + '&width=' + options.get('width')
            api_url = api_url + '&height=' + options.get('height')
            api_url = api_url + '&response_type=' + options.get('response_type')
          return api_url;

        token = 'INSERT TOKEN'
        options = {
          'url': url,
          'width': '1280',
          'height': '2000',
          'response_type': 'image'
          }

        api_url = generate_screenshot_api_url(token, options)
        print(api_url)

        timestamp = datetime.now().strftime('%Y%m%d%H%M')
       
        opener = urllib.request.build_opener()
        urllib.request.install_opener(opener)
        output = url_name + '-' + timestamp + '.png'
        urllib.request.urlretrieve(api_url, output)

 

Output examples