Instantly share code, notes, and snippets.

Embed
What would you like to do?
GitHub license analyzer
#!/usr/bin/env python
#
# Copyright (c) 2012, Max Jonas Werner <mail@makk.es>
# All rights reserved.
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
from beautifulscraper import BeautifulScraper
from collections import defaultdict, Counter
import urllib2, re
LICENSE_FILE_REGEX = re.compile('^(.*license.*)|copying|copyright$', re.IGNORECASE)
README_REGEX = re.compile('^readme(\..+)*$', re.IGNORECASE)
LICENSE_REGEX = re.compile('^[#=]* *license *$', re.IGNORECASE)
def top_languages():
scraper = BeautifulScraper()
body = scraper.go("https://github.com/languages")
return [ (x.string, x["href"]) for x in body.select("#languages .popular .left td[width=100] a") ]
def analyze_language(language):
langname = language[0]
langhref = language[1]
return analyze_projects("https://github.com" + langhref + "/most_watched")
def analyze_projects(url):
scraper = BeautifulScraper()
body = scraper.go(url)
projects = body.select("ul.repolist > li > h3 > a")
licensed = defaultdict(lambda: 0)
for project in projects:
try:
projbody = scraper.go("https://github.com" + project["href"])
license = find_license(projbody.select("table.tree-browser tbody td.content > a"))
licensed[license != None] += 1
except HTTPError as err:
print "Error analyzing project " + project.string + ": " + str(err)
nextlink = body.select("a.next_page")
if nextlink:
return Counter(licensed) + Counter(analyze_projects("https://github.com" + nextlink[0]["href"]))
else:
return licensed
def find_license(file_list):
license_file = find_license_file(file_list)
return license_file
def find_license_file(file_list):
for fname in file_list:
if LICENSE_FILE_REGEX.match(fname.string):
return fname.string
if README_REGEX.match(fname.string):
return check_readme(fname)
return None
def check_readme(fname):
url = ("https://github.com" + fname["href"]).replace('/blob/', '/raw/')
for line in urllib2.build_opener().open(url):
if LICENSE_REGEX.match(line):
return line.strip()
def run():
for language in top_languages():
print "{0}: {1}".format(language[0], analyze_language(language))
return
if __name__ == "__main__":
run()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment