[python] 고정 너비 파일을 효율적으로 구문 분석하는 방법은 무엇입니까?

여기에 따라 파이썬 3를위한 간단한 모듈의 존 머신의 대답은 – 필요에 따라 적용 :

"""
fixedwidth

Parse and iterate through a fixedwidth text file, returning record objects.

Adapted from https://stackoverflow.com/a/4916375/243392


USAGE

    import fixedwidth, pprint

    # define the fixed width fields we want
    # fieldspecs is a list of [name, description, start, width, type] arrays.
    fieldspecs = [
        ["FILEID", "File Identification", 1, 6, "A/N"],
        ["STUSAB", "State/U.S. Abbreviation (USPS)", 7, 2, "A"],
        ["SUMLEV", "Summary Level", 9, 3, "A/N"],
        ["LOGRECNO", "Logical Record Number", 19, 7, "N"],
        ["POP100", "Population Count (100%)", 30, 9, "N"],
    ]

    # define the fieldtype conversion functions
    fieldtype_fns = {
        'A': str.rstrip,
        'A/N': str.rstrip,
        'N': int,
    }

    # iterate over record objects in the file
    with open(f, 'rb'):
        for record in fixedwidth.reader(f, fieldspecs, fieldtype_fns):
            pprint.pprint(record.__dict__)

    # output:
    {'FILEID': 'SF1ST', 'LOGRECNO': 2, 'POP100': 1, 'STUSAB': 'TX', 'SUMLEV': '040'}
    {'FILEID': 'SF1ST', 'LOGRECNO': 3, 'POP100': 2, 'STUSAB': 'TX', 'SUMLEV': '040'}
    ...

"""

import struct, io


# fieldspec columns
iName, iDescription, iStart, iWidth, iType = range(5)


def get_struct_unpacker(fieldspecs):
    """
    Build the format string for struct.unpack to use, based on the fieldspecs.
    fieldspecs is a list of [name, description, start, width, type] arrays.
    Returns a string like "6s2s3s7x7s4x9s".
    """
    unpack_len = 0
    unpack_fmt = ""
    for fieldspec in fieldspecs:
        start = fieldspec[iStart] - 1
        end = start + fieldspec[iWidth]
        if start > unpack_len:
            unpack_fmt += str(start - unpack_len) + "x"
        unpack_fmt += str(end - start) + "s"
        unpack_len = end
    struct_unpacker = struct.Struct(unpack_fmt).unpack_from
    return struct_unpacker


class Record(object):
    pass
    # or use named tuples


def reader(f, fieldspecs, fieldtype_fns):
    """
    Wrap a fixedwidth file and return records according to the given fieldspecs.
    fieldspecs is a list of [name, description, start, width, type] arrays.
    fieldtype_fns is a dictionary of functions used to transform the raw string values,
    one for each type.
    """

    # make sure fieldspecs are sorted properly
    fieldspecs.sort(key=lambda fieldspec: fieldspec[iStart])

    struct_unpacker = get_struct_unpacker(fieldspecs)

    field_indices = range(len(fieldspecs))

    for line in f:
        raw_fields = struct_unpacker(line) # split line into field values
        record = Record()
        for i in field_indices:
            fieldspec = fieldspecs[i]
            fieldname = fieldspec[iName]
            s = raw_fields[i].decode() # convert raw bytes to a string
            fn = fieldtype_fns[fieldspec[iType]] # get conversion function
            value = fn(s) # convert string to value (eg to an int)
            setattr(record, fieldname, value)
        yield record


if __name__=='__main__':

    # test module

    import pprint, io

    # define the fields we want
    # fieldspecs are [name, description, start, width, type]
    fieldspecs = [
        ["FILEID", "File Identification", 1, 6, "A/N"],
        ["STUSAB", "State/U.S. Abbreviation (USPS)", 7, 2, "A"],
        ["SUMLEV", "Summary Level", 9, 3, "A/N"],
        ["LOGRECNO", "Logical Record Number", 19, 7, "N"],
        ["POP100", "Population Count (100%)", 30, 9, "N"],
    ]

    # define a conversion function for integers
    def to_int(s):
        """
        Convert a numeric string to an integer.
        Allows a leading ! as an indicator of missing or uncertain data.
        Returns None if no data.
        """
        try:
            return int(s)
        except:
            try:
                return int(s[1:]) # ignore a leading !
            except:
                return None # assume has a leading ! and no value

    # define the conversion fns
    fieldtype_fns = {
        'A': str.rstrip,
        'A/N': str.rstrip,
        'N': to_int,
        # 'N': int,
        # 'D': lambda s: datetime.datetime.strptime(s, "%d%m%Y"), # ddmmyyyy
        # etc
    }

    # define a fixedwidth sample
    sample = """\
SF1ST TX04089000  00000023748        1
SF1ST TX04090000  00000033748!       2
SF1ST TX04091000  00000043748!
"""
    sample_data = sample.encode() # convert string to bytes
    file_like = io.BytesIO(sample_data) # create a file-like wrapper around bytes

    # iterate over record objects in the file
    for record in reader(file_like, fieldspecs, fieldtype_fns):
        # print(record)
        pprint.pprint(record.__dict__)