1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

from lxml import etree
import urllib2

urls = {}
ranks=[]

f = file("languages.html", "r")
parser = etree.HTMLParser()
tree = etree.parse(f, parser)
languages = tree.findall("//div[@class='all_languages']//a")

def norm(name):
    name=name.replace(' ', '_')
    name=name.replace('/', '_')
    return name

#Create the urls list
for l in languages:
    name = l.text
    url = l.get('href')
    urls[name] = url

#Download the files
for name in urls:
    url = urls[name]
    filename = 'languages/'+norm(name)
    print filename
    fo = file(filename, 'w')
    try:
        fo.write(urllib2.urlopen("http://www.github.com"+url).read())
    except:
        print "Error getting language",name

#Analyize them
for name in urls:
    url = urls[name]
    filename = 'languages/'+norm(name)
    fo = file(filename, 'r')
    try :
        tree = etree.parse(fo, parser)
        pop = int(tree.find("//div[@class='pagehead']/h1/em").text.split()[2][1:])
        ranks.append((pop, name))
    except:
        pass

print ranks