import csv, re, requests, pytesseract
from bs4 import BeautifulSoup
from PIL import Image
from io import BytesIO
import pandas as pd

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]

email_list_per_country = []

with open(('s.csv'), 'w') as myfile:
    pass

for i in range(len(countries)):
    try:
        country = countries_code[i]
        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)
        email_list = []
        email_list.append(countries[i])


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

        print(countries[i] + ' finished successfully!\n')

        file_name = "s.csv"
        numbers = [i for i in range(15)]
        email_list_per_country.append(email_list)
        df = pd.DataFrame(email_list_per_country)
        df = df.transpose()
        df.to_csv(file_name, index=False, header=None)
        print(email_list_per_country)
    except:
        pass