from util import *
import glob

old_urls = []
new_urls = []
url_list = {}

with open('embassy-list-4.txt', 'r') as f:
  for line in f.readlines():
    old_urls.append(line.strip())
    url = line.split(' ')[0]
    url_list[url] = ''

for f in glob.iglob('./embassy/by_country/*.txt'):
  links = read_json(f)
  for link in links:
    # https://www.flickr.com/photos/us_mission_canada/37316818631
    url = link['url']
    url_partz = url.split('/')[:5]
    if len(url_partz) < 5:
      continue
    username = url_partz[4]
    if '@' in username:
      continue
    url_fix = '/'.join(url_partz)
    if url_fix not in url_list:
      new_urls.append(url_fix + ' ' + link['title'])
    url_list[url_fix] = link['title']

for line in old_urls:
  print(line)

for url in sorted(new_urls):
  print(url)