PicPack - Find Tax Exempt Homepages

gistfile1.txt

#find homepages for tax exempt organizations
from googlesearch import search 
from csv import reader
from urllib.parse import urlparse

            
with open('A50 - Museum Museum Activities.csv', 'r') as read_obj:
        

        csv_reader = reader(read_obj)
        rowCount = 0
        skipped = 0
        for row in csv_reader:

            if rowCount > 0:

                #run a query with the org name and its location
                searchQuery = row[0] + " " + row[2] + " " + row[3]
                for j in search(searchQuery, tld="co.in", num=1, stop=1 ):

                    #skip if the first result is a directory
                    if ( 'guidestar' in j or 'propublica.org' in j ):
                            skipped += 1

                    else: 
                        print(str(rowCount) + " - " + row[0] + "," + row[1] + "," + row[2] + "," + row[3] + "," + row[4] + "," + j)
                        rowCount += 1 
                
            else:
                rowCount += 1