# чтение файла, который содержит примеры записей
merifile = pd.read_csv("samplefcarecord.csv")
# создание пустого списка для хранения слов
wordsinwebsite = []
link = row.url
company = row.Company
words = ['Life Insurance', 'General Insurance', 'Motor Fleet','Fleet
Insurance', 'Motor Home Insurance', 'Insurance', 'Mortgages', 'Property
Insurance', 'Fire Insurance', 'Liability Insurance', 'Personal Insurance',
'Motor Fleet Insurance', 'Car Insurance', 'Travel Insurance', 'Home
Insurance', 'Pet Insurance', 'Health Insurance', 'Vehicle Insurance',
'Wealth Insurance', 'Income Protection Insurance', 'Auto Insurance',
'Building Insurance', 'Buildings Insurance', 'Disability Insurance', 'Common
Insurance', 'Guarantee Insurance', 'Social Insurance', 'Two-Wheeler
Insurance', 'Bike Insurance', 'Truck Insurance', 'Four Wheeler Insurance',
'Four-Wheeler Insurance', '4-wheeler insurance', '2-wheeler insurance',
'Business Insurance', 'Pawnbroking' , 'Travel Money', 'Used Cars', 'New
Cars']
site = urllib.request.urlopen(link).read().decode("utf-8")
# для цикла для извлечения каждого URL из списка, но только для его извлеченияURL последней записи
for word in words:
if word in site:
anchorandurldata = { 'Company' : company , 'url': link, 'word':
wordsinwebsite}
wordsinwebsite.append(word)
else:
pass