Snippet for soup_line

soup_line.py

def soup_line(dir_name, *exclusions):
    """
     Pair up soups with the files they're based on.
    :param dir_name: Directory with the html files needed.
    :param exclusions: Don't include these files.
    :return: A tuple of soup file name pairs.
    """
    import os

    from collections import namedtuple
    SoupFilePair = namedtuple("SoupFileName", ["soup", "file_name"])
    
    def is_valid_file(fpath):
        if os.path.isfile(fpath):
            if fpath.endswith(".html"):
                if fpath not in exclusions:
                    return True
        else:
            return False
        
        
    for fname in os.listdir(dir_name):
        file_path = "{0}/{1}".format(dir_name, fname)
        if is_valid_file(file_path):
            with open(file_path, "rt", encoding="utf-8") as file_ob:
                soup = BeautifulSoup(file_ob.read().strip())
                yield SoupFilePair(soup, fname)