github-scrape.py

import csv, httplib, json
from string import ascii_lowercase

con = httplib.HTTPSConnection('api.github.com')
languages = ['java', 'c', 'ruby', 'python', 'javascript']
for lang in languages:
	with open(lang + '.csv', 'wb') as csvfile:
		csvwriter = csv.writer(csvfile, delimiter = ',', quotechar='"', quoting = csv.QUOTE_MINIMAL)
		for ch in ascii_lowercase:
			print("Processing repos with " + ch + " for language " + lang)
			con.request('GET', '/legacy/repos/search/' + ch + '?language=' + lang)
			data = json.load(con.getresponse())
			for repo in data['repositories']:
				csvwriter.writerow([repo['name'], repo['username'], repo['followers'], repo['forks'], repo['fork']])