Created
October 7, 2014 05:14
-
-
Save w0ng/ecf4531da5c590b4ce95 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
#!/usr/bin/env python | |
import urllib2 | |
import json | |
import re | |
# 'Pretty print'. Outputs stuff nicer than normal print. Good for lists | |
from pprint import pprint | |
url = 'https://en.wikipedia.org/w/api.php?action=parse&page=List_of_national_capitals_in_alphabetical_order&prop=wikitext&format=json' | |
response = urllib2.urlopen(url) | |
json = json.load(response) | |
data = json['parse'] | |
title = data['title'] | |
text = data['wikitext']['*'] | |
#print(text) | |
text_list = text.split('\n') | |
#pprint(text_list) | |
# We want lines that begin with "| [[" | |
# For example: "| [[Warsaw]]..." | |
relevant_lines = [line for line in text_list if re.match('^\|\ \[\[', line)] | |
#pprint(relevant_lines) | |
# Put in dictionary. e.g. capital['AUS'] = 'Canberra' | |
# City is the first matching [[fdasfdasf]] of each line | |
# Country is the matching {{fdafsafd}} of each line | |
country_regex = '{{(.*?)}}' | |
city_regex = '\[\[(.*?)\]\]' | |
capital = {} | |
for line in relevant_lines: | |
if re.search(country_regex, line): | |
country = re.search(country_regex, line).group(1) | |
if re.search(city_regex, line): | |
city = re.search(city_regex, line).group(1) | |
if country and city: | |
capital[country] = city | |
for country_name,city_name in sorted(capital.iteritems()): | |
# capital[country] = city_name | |
print(country_name + ": " + city_name) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment