Get last n lines of a file, similar to tail

This may be quicker than yours. Makes no assumptions about line length. Backs through the file one block at a time till it's found the right number of '\n' characters.

def tail( f, lines=20 ):
    total_lines_wanted = lines

    BLOCK_SIZE = 1024
    f.seek(0, 2)
    block_end_byte = f.tell()
    lines_to_go = total_lines_wanted
    block_number = -1
    blocks = [] # blocks of size BLOCK_SIZE, in reverse order starting
                # from the end of the file
    while lines_to_go > 0 and block_end_byte > 0:
        if (block_end_byte - BLOCK_SIZE > 0):
            # read the last block we haven't yet read
            f.seek(block_number*BLOCK_SIZE, 2)
            blocks.append(f.read(BLOCK_SIZE))
        else:
            # file too small, start from begining
            f.seek(0,0)
            # only read what was not read
            blocks.append(f.read(block_end_byte))
        lines_found = blocks[-1].count('\n')
        lines_to_go -= lines_found
        block_end_byte -= BLOCK_SIZE
        block_number -= 1
    all_read_text = ''.join(reversed(blocks))
    return '\n'.join(all_read_text.splitlines()[-total_lines_wanted:])

I don't like tricky assumptions about line length when -- as a practical matter -- you can never know things like that.

Generally, this will locate the last 20 lines on the first or second pass through the loop. If your 74 character thing is actually accurate, you make the block size 2048 and you'll tail 20 lines almost immediately.

Also, I don't burn a lot of brain calories trying to finesse alignment with physical OS blocks. Using these high-level I/O packages, I doubt you'll see any performance consequence of trying to align on OS block boundaries. If you use lower-level I/O, then you might see a speedup.

UPDATE

for Python 3.2 and up, follow the process on bytes as In text files (those opened without a "b" in the mode string), only seeks relative to the beginning of the file are allowed (the exception being seeking to the very file end with seek(0, 2)).:

eg: f = open('C:/.../../apache_logs.txt', 'rb')

 def tail(f, lines=20):
    total_lines_wanted = lines

    BLOCK_SIZE = 1024
    f.seek(0, 2)
    block_end_byte = f.tell()
    lines_to_go = total_lines_wanted
    block_number = -1
    blocks = []
    while lines_to_go > 0 and block_end_byte > 0:
        if (block_end_byte - BLOCK_SIZE > 0):
            f.seek(block_number*BLOCK_SIZE, 2)
            blocks.append(f.read(BLOCK_SIZE))
        else:
            f.seek(0,0)
            blocks.append(f.read(block_end_byte))
        lines_found = blocks[-1].count(b'\n')
        lines_to_go -= lines_found
        block_end_byte -= BLOCK_SIZE
        block_number -= 1
    all_read_text = b''.join(reversed(blocks))
    return b'\n'.join(all_read_text.splitlines()[-total_lines_wanted:])

Assumes a unix-like system on Python 2 you can do:

import os
def tail(f, n, offset=0):
  stdin,stdout = os.popen2("tail -n "+n+offset+" "+f)
  stdin.close()
  lines = stdout.readlines(); stdout.close()
  return lines[:,-offset]

For python 3 you may do:

import subprocess
def tail(f, n, offset=0):
    proc = subprocess.Popen(['tail', '-n', n + offset, f], stdout=subprocess.PIPE)
    lines = proc.stdout.readlines()
    return lines[:, -offset]

Here is my answer. Pure python. Using timeit it seems pretty fast. Tailing 100 lines of a log file that has 100,000 lines:

>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=10)
0.0014600753784179688
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=100)
0.00899195671081543
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=1000)
0.05842900276184082
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=10000)
0.5394978523254395
>>> timeit.timeit('tail.tail(f, 100, 4098)', 'import tail; f = open("log.txt", "r");', number=100000)
5.377126932144165

Here is the code:

import os


def tail(f, lines=1, _buffer=4098):
    """Tail a file and get X lines from the end"""
    # place holder for the lines found
    lines_found = []

    # block counter will be multiplied by buffer
    # to get the block size from the end
    block_counter = -1

    # loop until we find X lines
    while len(lines_found) < lines:
        try:
            f.seek(block_counter * _buffer, os.SEEK_END)
        except IOError:  # either file is too small, or too many lines requested
            f.seek(0)
            lines_found = f.readlines()
            break

        lines_found = f.readlines()

        # we found enough lines, get out
        # Removed this line because it was redundant the while will catch
        # it, I left it for history
        # if len(lines_found) > lines:
        #    break

        # decrement the block counter to get the
        # next X bytes
        block_counter -= 1

    return lines_found[-lines:]

If reading the whole file is acceptable then use a deque.

from collections import deque
deque(f, maxlen=n)

Prior to 2.6, deques didn't have a maxlen option, but it's easy enough to implement.

import itertools
def maxque(items, size):
    items = iter(items)
    q = deque(itertools.islice(items, size))
    for item in items:
        del q[0]
        q.append(item)
    return q

If it's a requirement to read the file from the end, then use a gallop (a.k.a exponential) search.

def tail(f, n):
    assert n >= 0
    pos, lines = n+1, []
    while len(lines) <= n:
        try:
            f.seek(-pos, 2)
        except IOError:
            f.seek(0)
            break
        finally:
            lines = list(f)
        pos *= 2
    return lines[-n:]

S.Lott's answer above almost works for me but ends up giving me partial lines. It turns out that it corrupts data on block boundaries because data holds the read blocks in reversed order. When ''.join(data) is called, the blocks are in the wrong order. This fixes that.

def tail(f, window=20):
    """
    Returns the last `window` lines of file `f` as a list.
    f - a byte file-like object
    """
    if window == 0:
        return []
    BUFSIZ = 1024
    f.seek(0, 2)
    bytes = f.tell()
    size = window + 1
    block = -1
    data = []
    while size > 0 and bytes > 0:
        if bytes - BUFSIZ > 0:
            # Seek back one whole BUFSIZ
            f.seek(block * BUFSIZ, 2)
            # read BUFFER
            data.insert(0, f.read(BUFSIZ))
        else:
            # file too small, start from begining
            f.seek(0,0)
            # only read what was not read
            data.insert(0, f.read(bytes))
        linesFound = data[0].count('\n')
        size -= linesFound
        bytes -= BUFSIZ
        block -= 1
    return ''.join(data).splitlines()[-window:]

The code I ended up using. I think this is the best so far:

def tail(f, n, offset=None):
    """Reads a n lines from f with an offset of offset lines.  The return
    value is a tuple in the form ``(lines, has_more)`` where `has_more` is
    an indicator that is `True` if there are more lines in the file.
    """
    avg_line_length = 74
    to_read = n + (offset or 0)

    while 1:
        try:
            f.seek(-(avg_line_length * to_read), 2)
        except IOError:
            # woops.  apparently file is smaller than what we want
            # to step back, go to the beginning instead
            f.seek(0)
        pos = f.tell()
        lines = f.read().splitlines()
        if len(lines) >= to_read or pos == 0:
            return lines[-to_read:offset and -offset or None], \
                   len(lines) > to_read or pos > 0
        avg_line_length *= 1.3

Simple and fast solution with mmap:

import mmap
import os

def tail(filename, n):
    """Returns last n lines from the filename. No exception handling"""
    size = os.path.getsize(filename)
    with open(filename, "rb") as f:
        # for Windows the mmap parameters are different
        fm = mmap.mmap(f.fileno(), 0, mmap.MAP_SHARED, mmap.PROT_READ)
        try:
            for i in xrange(size - 1, -1, -1):
                if fm[i] == '\n':
                    n -= 1
                    if n == -1:
                        break
            return fm[i + 1 if i else 0:].splitlines()
        finally:
            fm.close()

Update @papercrane solution to python3. Open the file with open(filename, 'rb') and:

def tail(f, window=20):
    """Returns the last `window` lines of file `f` as a list.
    """
    if window == 0:
        return []

    BUFSIZ = 1024
    f.seek(0, 2)
    remaining_bytes = f.tell()
    size = window + 1
    block = -1
    data = []

    while size > 0 and remaining_bytes > 0:
        if remaining_bytes - BUFSIZ > 0:
            # Seek back one whole BUFSIZ
            f.seek(block * BUFSIZ, 2)
            # read BUFFER
            bunch = f.read(BUFSIZ)
        else:
            # file too small, start from beginning
            f.seek(0, 0)
            # only read what was not read
            bunch = f.read(remaining_bytes)

        bunch = bunch.decode('utf-8')
        data.insert(0, bunch)
        size -= bunch.count('\n')
        remaining_bytes -= BUFSIZ
        block -= 1

    return ''.join(data).splitlines()[-window:]

The simplest way is to use deque:

from collections import deque

def tail(filename, n=10):
    with open(filename) as f:
        return deque(f, n)

Posting an answer at the behest of commenters on my answer to a similar question where the same technique was used to mutate the last line of a file, not just get it.

For a file of significant size, mmap is the best way to do this. To improve on the existing mmap answer, this version is portable between Windows and Linux, and should run faster (though it won't work without some modifications on 32 bit Python with files in the GB range, see the other answer for hints on handling this, and for modifying to work on Python 2).

import io  # Gets consistent version of open for both Py2.7 and Py3.x
import itertools
import mmap

def skip_back_lines(mm, numlines, startidx):
    '''Factored out to simplify handling of n and offset'''
    for _ in itertools.repeat(None, numlines):
        startidx = mm.rfind(b'\n', 0, startidx)
        if startidx < 0:
            break
    return startidx

def tail(f, n, offset=0):
    # Reopen file in binary mode
    with io.open(f.name, 'rb') as binf, mmap.mmap(binf.fileno(), 0, access=mmap.ACCESS_READ) as mm:
        # len(mm) - 1 handles files ending w/newline by getting the prior line
        startofline = skip_back_lines(mm, offset, len(mm) - 1)
        if startofline < 0:
            return []  # Offset lines consumed whole file, nothing to return
            # If using a generator function (yield-ing, see below),
            # this should be a plain return, no empty list

        endoflines = startofline + 1  # Slice end to omit offset lines

        # Find start of lines to capture (add 1 to move from newline to beginning of following line)
        startofline = skip_back_lines(mm, n, startofline) + 1

        # Passing True to splitlines makes it return the list of lines without
        # removing the trailing newline (if any), so list mimics f.readlines()
        return mm[startofline:endoflines].splitlines(True)
        # If Windows style \r\n newlines need to be normalized to \n, and input
        # is ASCII compatible, can normalize newlines with:
        # return mm[startofline:endoflines].replace(os.linesep.encode('ascii'), b'\n').splitlines(True)

This assumes the number of lines tailed is small enough you can safely read them all into memory at once; you could also make this a generator function and manually read a line at a time by replacing the final line with:

        mm.seek(startofline)
        # Call mm.readline n times, or until EOF, whichever comes first
        # Python 3.2 and earlier:
        for line in itertools.islice(iter(mm.readline, b''), n):
            yield line

        # 3.3+:
        yield from itertools.islice(iter(mm.readline, b''), n)

Lastly, this read in binary mode (necessary to use mmap) so it gives str lines (Py2) and bytes lines (Py3); if you want unicode (Py2) or str (Py3), the iterative approach could be tweaked to decode for you and/or fix newlines:

        lines = itertools.islice(iter(mm.readline, b''), n)
        if f.encoding:  # Decode if the passed file was opened with a specific encoding
            lines = (line.decode(f.encoding) for line in lines)
        if 'b' not in f.mode:  # Fix line breaks if passed file opened in text mode
            lines = (line.replace(os.linesep, '\n') for line in lines)
        # Python 3.2 and earlier:
        for line in lines:
            yield line
        # 3.3+:
        yield from lines

Note: I typed this all up on a machine where I lack access to Python to test. Please let me know if I typoed anything; this was similar enough to my other answer that I think it should work, but the tweaks (e.g. handling an offset) could lead to subtle errors. Please let me know in the comments if there are any mistakes.

An even cleaner python3 compatible version that doesn't insert but appends & reverses:

def tail(f, window=1):
    """
    Returns the last `window` lines of file `f` as a list of bytes.
    """
    if window == 0:
        return b''
    BUFSIZE = 1024
    f.seek(0, 2)
    end = f.tell()
    nlines = window + 1
    data = []
    while nlines > 0 and end > 0:
        i = max(0, end - BUFSIZE)
        nread = min(end, BUFSIZE)

        f.seek(i)
        chunk = f.read(nread)
        data.append(chunk)
        nlines -= chunk.count(b'\n')
        end -= nread
    return b'\n'.join(b''.join(reversed(data)).splitlines()[-window:])

use it like this:

with open(path, 'rb') as f:
    last_lines = tail(f, 3).decode('utf-8')

based on S.Lott's top voted answer (Sep 25 '08 at 21:43), but fixed for small files.

def tail(the_file, lines_2find=20):  
    the_file.seek(0, 2)                         #go to end of file
    bytes_in_file = the_file.tell()             
    lines_found, total_bytes_scanned = 0, 0
    while lines_2find+1 > lines_found and bytes_in_file > total_bytes_scanned: 
        byte_block = min(1024, bytes_in_file-total_bytes_scanned)
        the_file.seek(-(byte_block+total_bytes_scanned), 2)
        total_bytes_scanned += byte_block
        lines_found += the_file.read(1024).count('\n')
    the_file.seek(-total_bytes_scanned, 2)
    line_list = list(the_file.readlines())
    return line_list[-lines_2find:]

    #we read at least 21 line breaks from the bottom, block by block for speed
    #21 to ensure we don't get a half line

Hope this is useful.

There are some existing implementations of tail on pypi which you can install using pip:

mtFileUtil

multitail

log4tailer

...

Depending on your situation, there may be advantages to using one of these existing tools.

Simple :

with open("test.txt") as f:
data = f.readlines()
tail = data[-2:]
print(''.join(tail)

I found the Popen above to be the best solution. It's quick and dirty and it works For python 2.6 on Unix machine i used the following

def GetLastNLines(self, n, fileName):
    """
    Name:           Get LastNLines
    Description:        Gets last n lines using Unix tail
    Output:         returns last n lines of a file
    Keyword argument:
    n -- number of last lines to return
    filename -- Name of the file you need to tail into
    """
    p = subprocess.Popen(['tail','-n',str(n),self.__fileName], stdout=subprocess.PIPE)
    soutput, sinput = p.communicate()
    return soutput

soutput will have will contain last n lines of the code. to iterate through soutput line by line do:

for line in GetLastNLines(50,'myfile.log').split('\n'):
    print line

For efficiency with very large files (common in logfile situations where you may want to use tail), you generally want to avoid reading the whole file (even if you do do it without reading the whole file into memory at once) However, you do need to somehow work out the offset in lines rather than characters. One possibility is reading backwards with seek() char by char, but this is very slow. Instead, its better to process in larger blocks.

I've a utility function I wrote a while ago to read files backwards that can be used here.

import os, itertools

def rblocks(f, blocksize=4096):
    """Read file as series of blocks from end of file to start.

    The data itself is in normal order, only the order of the blocks is reversed.
    ie. "hello world" -> ["ld","wor", "lo ", "hel"]
    Note that the file must be opened in binary mode.
    """
    if 'b' not in f.mode.lower():
        raise Exception("File must be opened using binary mode.")
    size = os.stat(f.name).st_size
    fullblocks, lastblock = divmod(size, blocksize)

    # The first(end of file) block will be short, since this leaves 
    # the rest aligned on a blocksize boundary.  This may be more 
    # efficient than having the last (first in file) block be short
    f.seek(-lastblock,2)
    yield f.read(lastblock)

    for i in range(fullblocks-1,-1, -1):
        f.seek(i * blocksize)
        yield f.read(blocksize)

def tail(f, nlines):
    buf = ''
    result = []
    for block in rblocks(f):
        buf = block + buf
        lines = buf.splitlines()

        # Return all lines except the first (since may be partial)
        if lines:
            result.extend(lines[1:]) # First line may not be complete
            if(len(result) >= nlines):
                return result[-nlines:]

            buf = lines[0]

    return ([buf]+result)[-nlines:]


f=open('file_to_tail.txt','rb')
for line in tail(f, 20):
    print line

[Edit] Added more specific version (avoids need to reverse twice)

you can go to the end of your file with f.seek(0, 2) and then read off lines one by one with the following replacement for readline():

def readline_backwards(self, f):
    backline = ''
    last = ''
    while not last == '\n':
        backline = last + backline
        if f.tell() <= 0:
            return backline
        f.seek(-1, 1)
        last = f.read(1)
        f.seek(-1, 1)
    backline = last
    last = ''
    while not last == '\n':
        backline = last + backline
        if f.tell() <= 0:
            return backline
        f.seek(-1, 1)
        last = f.read(1)
        f.seek(-1, 1)
    f.seek(1, 1)
    return backline

Based on Eyecue answer (Jun 10 '10 at 21:28): this class add head() and tail() method to file object.

class File(file):
    def head(self, lines_2find=1):
        self.seek(0)                            #Rewind file
        return [self.next() for x in xrange(lines_2find)]

    def tail(self, lines_2find=1):  
        self.seek(0, 2)                         #go to end of file
        bytes_in_file = self.tell()             
        lines_found, total_bytes_scanned = 0, 0
        while (lines_2find+1 > lines_found and
               bytes_in_file > total_bytes_scanned): 
            byte_block = min(1024, bytes_in_file-total_bytes_scanned)
            self.seek(-(byte_block+total_bytes_scanned), 2)
            total_bytes_scanned += byte_block
            lines_found += self.read(1024).count('\n')
        self.seek(-total_bytes_scanned, 2)
        line_list = list(self.readlines())
        return line_list[-lines_2find:]

Usage:

f = File('path/to/file', 'r')
f.head(3)
f.tail(3)

Several of these solutions have issues if the file doesn't end in \n or in ensuring the complete first line is read.

def tail(file, n=1, bs=1024):
    f = open(file)
    f.seek(-1,2)
    l = 1-f.read(1).count('\n') # If file doesn't end in \n, count it anyway.
    B = f.tell()
    while n >= l and B > 0:
            block = min(bs, B)
            B -= block
            f.seek(B, 0)
            l += f.read(block).count('\n')
    f.seek(B, 0)
    l = min(l,n) # discard first (incomplete) line if l > n
    lines = f.readlines()[-l:]
    f.close()
    return lines

Here is a pretty simple implementation:

with open('/etc/passwd', 'r') as f:
  try:
    f.seek(0,2)
    s = ''
    while s.count('\n') < 11:
      cur = f.tell()
      f.seek((cur - 10))
      s = f.read(10) + s
      f.seek((cur - 10))
    print s
  except Exception as e:
    f.readlines()

There is very useful module that can do this:

from file_read_backwards import FileReadBackwards

with FileReadBackwards("/tmp/file", encoding="utf-8") as frb:

# getting lines by lines starting from the last line up
for l in frb:
    print(l)

Update for answer given by A.Coady

Works with python 3.

This uses Exponential Search and will buffer only N lines from back and is very efficient.

import time
import os
import sys

def tail(f, n):
    assert n >= 0
    pos, lines = n+1, []

    # set file pointer to end

    f.seek(0, os.SEEK_END)

    isFileSmall = False

    while len(lines) <= n:
        try:
            f.seek(f.tell() - pos, os.SEEK_SET)
        except ValueError as e:
            # lines greater than file seeking size
            # seek to start
            f.seek(0,os.SEEK_SET)
            isFileSmall = True
        except IOError:
            print("Some problem reading/seeking the file")
            sys.exit(-1)
        finally:
            lines = f.readlines()
            if isFileSmall:
                break

        pos *= 2

    print(lines)

    return lines[-n:]




with open("stream_logs.txt") as f:
    while(True):
        time.sleep(0.5)
        print(tail(f,2))

I had to read a specific value from the last line of a file, and stumbled upon this thread. Rather than reinventing the wheel in Python, I ended up with a tiny shell script, saved as /usr/local/bin/get_last_netp:

#! /bin/bash
tail -n1 /home/leif/projects/transfer/export.log | awk {'print $14'}

And in the Python program:

from subprocess import check_output

last_netp = int(check_output("/usr/local/bin/get_last_netp"))

Not the first example using a deque, but a simpler one. This one is general: it works on any iterable object, not just a file.

#!/usr/bin/env python
import sys
import collections
def tail(iterable, N):
    deq = collections.deque()
    for thing in iterable:
        if len(deq) >= N:
            deq.popleft()
        deq.append(thing)
    for thing in deq:
        yield thing
if __name__ == '__main__':
    for line in tail(sys.stdin,10):
        sys.stdout.write(line)

This is my version of tailf

import sys, time, os

filename = 'path to file'

try:
    with open(filename) as f:
        size = os.path.getsize(filename)
        if size < 1024:
            s = size
        else:
            s = 999
        f.seek(-s, 2)
        l = f.read()
        print l
        while True:
            line = f.readline()
            if not line:
                time.sleep(1)
                continue
            print line
except IOError:
    pass

import time

attemps = 600
wait_sec = 5
fname = "YOUR_PATH"

with open(fname, "r") as f:
    where = f.tell()
    for i in range(attemps):
        line = f.readline()
        if not line:
            time.sleep(wait_sec)
            f.seek(where)
        else:
            print line, # already has newline

import itertools
fname = 'log.txt'
offset = 5
n = 10
with open(fname) as f:
    n_last_lines = list(reversed([x for x in itertools.islice(f, None)][-(offset+1):-(offset+n+1):-1]))

abc = "2018-06-16 04:45:18.68"
filename = "abc.txt"
with open(filename) as myFile:
    for num, line in enumerate(myFile, 1):
        if abc in line:
            lastline = num
print "last occurance of work at file is in "+str(lastline) 

Another Solution

if your txt file looks like this: mouse snake cat lizard wolf dog

you could reverse this file by simply using array indexing in python '''

contents=[]
def tail(contents,n):
    with open('file.txt') as file:
        for i in file.readlines():
            contents.append(i)

    for i in contents[:n:-1]:
        print(i)

tail(contents,-5)

result: dog wolf lizard cat

Well! I had a similar problem, though I only required LAST LINE ONLY, so I came up with my own solution

def get_last_line(filepath):
    try:
        with open(filepath,'rb') as f:
            f.seek(-1,os.SEEK_END)
            text = [f.read(1)]
            while text[-1] != '\n'.encode('utf-8') or len(text)==1:
                f.seek(-2, os.SEEK_CUR)
                text.append(f.read(1))
    except Exception as e:
        pass
    return ''.join([t.decode('utf-8') for t in text[::-1]]).strip()

This function return last string in a file I have a log file of 1.27gb and it took very very less time to find the last line (not even half a second)