import csv
import re
from bs4 import BeautifulSoup
import requests
from PIL import Image
import pytesseract
from selenium import webdriver
from io import BytesIO
pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'

countries = ['Albania', 'Algeria', 'Antigua And Barbuda', 'Argentina', 'Armenia', 'Australia', 'Austria', 'Azerbaijan', 'Bahrain', 'Bangladesh', 'Barbados', 'Belarus', 'Belgium', 'Belize', 'Bolivia', 'Bosnia and Herzegovina', 'Botswana', 'Brazil', 'Bulgaria', 'Cambodia', 'Canada', 'Chile', 'China', 'Colombia', 'Congo, Democractic Republic of the', 'Costa Rica', "Cote D'Ivoire", 'Croatia', 'Cuba', 'Cyprus', 'Czech Republic', 'Denmark', 'Dominican Republic', 'Ecuador', 'Egypt', 'El Salvador', 'Estonia', 'Finland', 'France', 'Georgia', 'Germany', 'Ghana', 'Greece', 'Guatemala', 'Hong Kong S.A.R.', 'Hungary', 'Iceland', 'India', 'Indonesia', 'Iran', 'Ireland', 'Israel', 'Italy', 'Jamaica', 'Japan', 'Jordan', 'Kazakhstan', 'Kenya', 'Korea, South', 'Kuwait', 'Kyrgyzstan', 'Laos', 'Latvia', 'Lebanon', 'Lithuania', 'Luxembourg', 'Macau S.A.R.', 'Macedonia, Former Yugoslav Republic of', 'Madagascar', 'Malaysia', 'Malta', 'Mauritius', 'Mexico', 'Moldova', 'Mongolia', 'Morocco', 'Mozambique', 'Myanmar', 'Namibia', 'Nepal', 'Netherlands Antilles', 'Netherlands, The', 'New Zealand', 'Nicaragua', 'Nigeria', 'Niue', 'Norway', 'Pakistan', 'Panama', 'Paraguay', 'Peru', 'Philippines', 'Poland', 'Portugal', 'Puerto Rico', 'Qatar', 'Reunion', 'Romania', 'Russia', 'Rwanda', 'Saint Kitts And Nevis', 'Saudi Arabia', 'Senegal', 'Serbia', 'Seychelles', 'Singapore', 'Slovakia', 'Slovenia', 'South Africa', 'Spain', 'Sri Lanka', 'Swaziland', 'Sweden', 'Switzerland', 'Taiwan', 'Tanzania', 'Thailand', 'Trinidad And Tobago', 'Tunisia', 'Turkey', 'Ukraine', 'United Arab Emirates', 'United Kingdom', 'United Nations', 'United States', 'United States Minor Outlying Islands', 'Uruguay', 'Uzbekistan', 'Venezuela', 'Vietnam', 'Yemen', 'Yugoslavia', 'Zimbabwe']

countries_code = [i.replace(' ', '_') for i in countries]

for i in range(len(countries)):
    print(countries[i], i)

country = input('Please choose the country: (type the number next to the country from the list above)\n')
country = countries_code[int(country)]

link = requests.get('https://services.creativecow.net/country/' + country)
soup = BeautifulSoup(link.text, 'html.parser')

companyLinks = [] #a list of all URL's for the companies on the webpage

for link in soup.findAll('a', attrs={'href': re.compile("^https://")}):
    companyLink = link.get('href')
    if '/s/' in companyLink and not companyLink in companyLinks:
        companyLinks.append(companyLink)
        # print(companyLink)
email_list = []

for i in range(len(companyLinks)):          #for i in range(len(companyLinks)):
    link = requests.get(companyLinks[i])
    soup = BeautifulSoup(link.text, 'html.parser')
    mydivs = soup.find("div", {"class": "vcard"})
    soup = mydivs
    text= soup.find('img')['src']
    r = requests.get('http:' + str(text))
    img = Image.open(BytesIO(r.content))
    imgtext = pytesseract.image_to_string(img, lang='eng')
    imgtext = imgtext[7:]
    imgtext = imgtext.replace(' ', '')
    email_list.append(imgtext)
    print('Finished ' + str(i+1) + ' out of '+  str(len(companyLinks)))
for i in email_list:
    print(i)


email_list = zip(email_list)
with open((country+'.csv'), 'w') as myfile:
    wr = csv.writer(myfile, quoting=csv.QUOTE_ALL)
    wr.writerows(email_list)