linkedin_collect_url.py 文件源码

def duplicate_checker(x): ##TODO: implement the files with hash table; especially as the list grows really large??
    with open('linkedin_rec_people.txt') as f, open('linkedin_data_collection.txt') as b:
        w = b.readlines()
        b = []
        for line in w: ##TODO: highly inefficient... is their a better way to compare without including last word???
            line = line.split()
            line = line[:-1]
            b.append(' '.join(line))
        for line in fileinput.input('linkedin_rec_people.txt', inplace=True):
            if x in w:
                line = line.replace(x, '')
            sys.stdout.write(line)
            fileinput.close()
            return True
        return False