读取一个文件10秒钟

Question

我现在在和Logfiles一起工作。我的需要是，我想逐行读取一个指定的时间段，比如10s。如果有办法在Python中实现这一点，有人能帮我吗？

Answer 1

使用tail或tac运行Popen并对输出进行迭代，直到找到要停止的行为止。下面是一个示例片段。

filename = '/var/log/nginx/access.log'
# Command to read file from the end
cmd = sys.platform == 'darwin' and ['tail', '-r', filename] or ['tac', filename]
# But if you want read it from beginning, use the following
#cmd = ['cat', filename]

proc = Popen(cmd, close_fds=True, stdout=PIPE, stderr=PIPE)
output = proc.stdout

FORMAT = [
    # 'foo',
    # 'bar',
]
def extract_log_data(line):
    '''Extact data in you log format, normalize it.
    '''
    return dict(zip(FORMAT, line))

csv.register_dialect('nginx', delimiter=' ', quoting=csv.QUOTE_MINIMAL)
lines = csv.reader(output, dialect='nginx')
started_at = dt.datetime.utcnow()
for line in lines:
    data = extract_log_data(line)
    print data
    if (dt.datetime.utcnow() - started_at) >= dt.timedelta(seconds=10):
        break

output.close()
proc.terminate()

Answer 2

代码

from multiprocessing import Process
import time

def read_file(path):
    try:
        # open file for writing
        f = open(path, "r")
        try:
            for line in f:
                # do something
                pass

        # always close the file when leaving the try block 
        finally:
            f.close()

    except IOError:
        print "Failed to open/read from file '%s'" % (path)

def read_file_limited_time(path, max_seconds):

    # init Process
    p = Process(target=read_file, args=(path,))

    # start process
    p.start()

    # for max seconds 
    for i in range(max_seconds):

        # sleep for 1 seconds (you may change the sleep time to suit your needs)
        time.sleep(1)

        # if process is not alive, we can break the loop
        if not p.is_alive():
            break

    # if process is still alive after max_seconds, kiil it!
    if p.is_alive():
        p.terminate()

def main():
    path = "f1.txt"
    read_file_limited_time(path,10)

if __name__ == "__main__":
    main()

备注

我们每1秒“醒来”并检查我们开始的进程是否还活着的原因仅仅是为了阻止我们在进程结束时继续睡眠。如果过程在1秒后结束，则睡眠时间浪费9秒。