extract_from_requirements.py

import pkg_resources
import argparse
import os.path as osp
import csv

def get_pkg_license(pkgname):
    """
    Given a package reference (as from requirements.txt),
    return license listed in package metadata.
    """
    pkgs = pkg_resources.require(pkgname)
    pkg = pkgs[0]
    for line in pkg.get_metadata_lines('PKG-INFO'):
        (k, v) = line.split(': ', 1)
        if k == "License":
            return v
    return None

if __name__ == "__main__":
    
    parser = argparse.ArgumentParser(description='Process some integers.')
    parser.add_argument('file', metavar='f', type=str,
                        help='a list of requirements files.')
    parser.add_argument('output', metavar='f', type=str,
                        help='a csv to stash the results')

    args = parser.parse_args()

    output = {}
    with open(args.file, 'r') as targets:
        for apath in targets:
            apath = osp.realpath(apath)
            apath = "".join(apath.split())
            with open(apath, 'r') as f:
                for line in f:
                    try:
                        line = "".join(line.split())
                        line = line.split("=")[0]
                        try: 
                            l = get_pkg_license(line)
                            if l is None:
                                continue
                        except Exception as e:
                            print "No license for {1} in {0}.".format(apath,line)

                        if output.has_key(line):
                            output[line].append([l,apath])
                        else:
                            output[line] = []
                            output[line].append([l,apath])
                    except Exception as e:
                        print "failed on {0} in {1} because: {2}.".format(apath,line,e)
                        continue
    print output
        
    with open(args.output, 'w') as csvfile:
        fieldnames = ['library','license','location']
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()
        for k,v in output.items():
            stuff = {}
            stuff["library"] = k
            for places in v:
                stuff["license"]=places[0]
                stuff["location"]=places[1]
                writer.writerow(stuff)