Python文本文件操作，以秒为单位为每行添加增量时间

我是python的初学者，正在尝试解决以下问题：

我有一个文本文件，每行开头如下：

<18:12:53.972>
<18:12:53.975>
<18:12:53.975>
<18:12:53.975>  
<18:12:54.008>

等

---

我想在每一行的开头加上以秒为单位的运行时间，但前提是该行以“第一点开头：当内存不足时（特别是当您不知道是否有足够的可用内存时），永远不要读取内存中的完整文件

第二点：学习使用python的循环和迭代协议。迭代

列表

和任何其他iterable的方法是：

 for item in some_iterable:
     do_something_with(item)

这样可以避免弄乱索引和出错；）

Python

file

对象的一个优点是它们实际上是可编辑的，因此要在文件行上迭代，最简单的方法是：

 for line in my_opened_file:
     do_something_with(line)

以下是一种简单但有效且主要是pythonic（nb:python2.7.x）的程序编写方法：

# -*- coding: utf-8 -*-
import os
import sys
import datetime
import re
import tempfile


def totime(timestr):
    """ returns a datetime object for a "HH:MM:SS" string """

    # we actually need datetime objects for substraction
    # so let's use the first available bogus date

    # notes:
    # `timestr.split(":")` will returns a list `["MM", "HH", "SS]`
    # `map(int, ...)` will apply `int()` on each item
    #    of the sequence (second argument) and return 
    #    the resulting list, ie 
    #    `map(int, "01", "02", "03")` => `[1, 2, 3]`

    return datetime.datetime(1900, 1, 1, *map(int, timestr.split(":")))

def process(instream, outstream):
    # some may consider that regexps are not that pythonic
    # but as far as I'm concerned it seems like a sensible
    # use case.
    time_re = re.compile("^<(?P<time>\d{2}:\d{2}:\d{2})\.")
    first = None

    # iterate over our input stream lines
    for line in instream:
        # should we handle this line at all ?
        # (nb a bit redundant but faster than re.match)
        if not line.startswith("<"):
            continue

        # looks like a candidate, let's try and
        # extract the 'time' value from it
        match = time_re.search(line)
        if not match:
            # starts with '<' BUT not followed by 'HH:MM:SS.' ?
            # unexpected from the sample source but well, we
            # can't do much about it either
            continue

        # retrieve the captured "time" (HH:MM:SS) part
        current = totime(match.group("time"))

        # store the first occurrence so we can
        # compute the elapsed time
        if first is None:
            first = current

        # `(current - first)` yields a `timedelta` object
        # we now just have to retrieve it's `seconds` attribute
        seconds = (current - first).seconds

        # inject the seconds before the line
        # and write the whole thing tou our output stream
        newline = "{}{}".format(seconds, line)
        outstream.write(newline)

def usage(err=None):
    if err:
        print >> sys.stderr, err
    print >> sys.stderr, "usage: python retime.py <filename>"
    # unix standards process exit codes 
    return 2 if err else 0

def main(*args):
    # our entry point... 
    # gets the source filename, process it 
    # (storing the results in a temporary file),
    # and if everything's ok replace the source file
    # by the temporary file.

    try:
        sourcename = args[0]
    except IndexError as e:
        return usage("missing <filename> argument")

    # `delete=False` prevents the tmp file to be
    # deleted on closing.    
    dest = tempfile.NamedTemporaryFile(delete=False)

    with open(sourcename) as source:
        try:
            process(source, dest)
        except Exception as e:
            dest.close()
            os.remove(dest)
            raise

    # ok done
    dest.close()
    os.rename(dest.name, sourcename)
    return 0


if __name__ == "__main__":
    # only execute main() if we are called as a script
    # (so we can also import this file as a module)
    sys.exit(main(*sys.argv[1:]))

#-*-编码：utf-8-*-
导入操作系统
导入系统
导入日期时间
进口稀土
导入临时文件
def totime（timestr）：
“”“返回“HH:MM:SS”字符串的datetime对象”“”
#我们实际上需要datetime对象进行减法运算
#那么，让我们使用第一个可用的伪造日期
#注:
#`timestr.split（“：”`将返回一个列表“[”MM”，“HH”，“SS]`
#`map（int，…）`将对每个项目应用`int（）
#序列（第二个参数）的
#结果列表，即
#'map（int，“01”，“02”，“03”）`=>`[1,2,3]`
return datetime.datetime（1900,1,1，*map（int，timestr.split（“：”））
def流程（流入、流出）：
有些人可能认为，正则表达式不是Python的。
#但就我而言，这似乎是一个明智的选择
#用例。
时间=重新编译（“^这在python中是可能的吗？是的，当然是可能的。事实上这很容易。你可以在datetime模块中检查函数？你的问题是什么？你有没有尝试过什么不起作用？@KlausD。我添加了一些代码。Thanks@Chaker.谢谢，我已经试过了，效果很好，但是我不能让代码正常工作。谢谢你的支持帮助，我不知道如何让它工作。你能看看我更新的代码吗？现在它几乎可以作为一个初学者：-）谢谢“我不知道如何让它工作，虽然”嗯，它是相当有文档记录的虽然。。。你试过用它吗？
 for line in my_opened_file:
     do_something_with(line)

# -*- coding: utf-8 -*-
import os
import sys
import datetime
import re
import tempfile


def totime(timestr):
    """ returns a datetime object for a "HH:MM:SS" string """

    # we actually need datetime objects for substraction
    # so let's use the first available bogus date

    # notes:
    # `timestr.split(":")` will returns a list `["MM", "HH", "SS]`
    # `map(int, ...)` will apply `int()` on each item
    #    of the sequence (second argument) and return 
    #    the resulting list, ie 
    #    `map(int, "01", "02", "03")` => `[1, 2, 3]`

    return datetime.datetime(1900, 1, 1, *map(int, timestr.split(":")))

def process(instream, outstream):
    # some may consider that regexps are not that pythonic
    # but as far as I'm concerned it seems like a sensible
    # use case.
    time_re = re.compile("^<(?P<time>\d{2}:\d{2}:\d{2})\.")
    first = None

    # iterate over our input stream lines
    for line in instream:
        # should we handle this line at all ?
        # (nb a bit redundant but faster than re.match)
        if not line.startswith("<"):
            continue

        # looks like a candidate, let's try and
        # extract the 'time' value from it
        match = time_re.search(line)
        if not match:
            # starts with '<' BUT not followed by 'HH:MM:SS.' ?
            # unexpected from the sample source but well, we
            # can't do much about it either
            continue

        # retrieve the captured "time" (HH:MM:SS) part
        current = totime(match.group("time"))

        # store the first occurrence so we can
        # compute the elapsed time
        if first is None:
            first = current

        # `(current - first)` yields a `timedelta` object
        # we now just have to retrieve it's `seconds` attribute
        seconds = (current - first).seconds

        # inject the seconds before the line
        # and write the whole thing tou our output stream
        newline = "{}{}".format(seconds, line)
        outstream.write(newline)

def usage(err=None):
    if err:
        print >> sys.stderr, err
    print >> sys.stderr, "usage: python retime.py <filename>"
    # unix standards process exit codes 
    return 2 if err else 0

def main(*args):
    # our entry point... 
    # gets the source filename, process it 
    # (storing the results in a temporary file),
    # and if everything's ok replace the source file
    # by the temporary file.

    try:
        sourcename = args[0]
    except IndexError as e:
        return usage("missing <filename> argument")

    # `delete=False` prevents the tmp file to be
    # deleted on closing.    
    dest = tempfile.NamedTemporaryFile(delete=False)

    with open(sourcename) as source:
        try:
            process(source, dest)
        except Exception as e:
            dest.close()
            os.remove(dest)
            raise

    # ok done
    dest.close()
    os.rename(dest.name, sourcename)
    return 0


if __name__ == "__main__":
    # only execute main() if we are called as a script
    # (so we can also import this file as a module)
    sys.exit(main(*sys.argv[1:]))