Created
September 19, 2018 12:42
-
-
Save patricoferris/4c953c7cb640ad2bffae9e2f7c731254 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
from bs4 import BeautifulSoup | |
import json | |
#Accessing the Webpage | |
result = requests.get('https://github.com/factbook/factbook.json') | |
#Getting the content of the webpage | |
content = result.content | |
#Beautiful-souping it | |
bsoup = BeautifulSoup(content, 'html5lib') | |
#Getting the table data cells from the page with a specific class - (Use Chrome Dev Tools) | |
tds = bsoup.find_all('td', class_='content') | |
#An array of the possible continents | |
continents = [] | |
for td in tds[1:14]: | |
continents.append(td.text.split('\n')[1].split(' ')[-1]) | |
code_to_continent = {} | |
#Key-value pairs of country code to their respective continent | |
for continent in continents: | |
if continent != 'meta': | |
url = 'https://github.com/factbook/factbook.json/tree/master/{c}'.format(c=continent) | |
countries_page = requests.get(url) | |
content = countries_page.content | |
bsoup = BeautifulSoup(content, 'html5lib') | |
tds = bsoup.find_all('td', class_='content') | |
for td in tds[1:]: | |
code_to_continent[td.text.split('\n')[1].split(' ')[-1].split('.')[0]] = continent |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment