ghstats

github_stats.py

import re, urllib
from bs4 import BeautifulSoup

myurl = "https://github.com/emccode/rexray"
html = urllib.urlopen(myurl).read()
soup = BeautifulSoup(html, 'html.parser')

file = open("github.analysis", "w")
file.write(myurl+"\n")
for sibling in soup.findAll("a", { "class" : "social-count" }):
   if "watchers" in sibling['href']:
       file.write("Watchers: %s\n" % sibling.contents[0].strip())
   elif "gazers" in sibling['href']:
       file.write("Stars: %s\n" % sibling.contents[0].strip())
   elif "network" in sibling['href']:
       file.write("Forks: %s\n" % sibling.contents[0].strip())

for item in soup.findAll("ul", { "class" : "numbers-summary" }):
	    if "commits" in item.li.a['href']:
	    	file.write("Commits : %s\n" % item.span.next_sibling.next_sibling.contents[0].strip())
	    if "branches" in item.li.next_sibling.next_sibling.a['href']:
	    	file.write("Branches : %s\n" % item.li.next_sibling.next_sibling.span.next_sibling.next_sibling.contents[0].strip())
	    if "releases" in item.li.next_sibling.next_sibling.next_sibling.next_sibling.a['href']:
	    	file.write("Releases : %s\n" % item.li.next_sibling.next_sibling.next_sibling.next_sibling.span.next_sibling.next_sibling.contents[0].strip())
	    if "contributors" in item.li.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.a['href']:
	    	file.write("Contributors : %s\n" % item.li.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.next_sibling.span.next_sibling.next_sibling.contents[0].strip())

lang = soup.find("span", { "class" : "lang"})
file.write("Main Language : %s\n" % lang.contents[0].strip())
file.close()