I'm writing a log file viewer for a web application and for that I want to paginate through the lines of the log file. The items in the file are line based with the newest item at the bottom.
So I need a tail() method that can read n lines from the bottom and support an offset. This is hat I came up with:
def tail(f, n, offset=0):
"""Reads a n lines from f with an offset of offset lines."""
avg_line_length = 74
to_read = n + offset
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]
avg_line_length *= 1.3
Is this a reasonable approach? What is the recommended way to tail log files with offsets?
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')
Simple :
with open("test.txt") as f:
data = f.readlines()
tail = data[-2:]
print(''.join(tail)
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.
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)
Related
I have a text file say really_big_file.txt that contains:
line 1
line 2
line 3
line 4
...
line 99999
line 100000
I would like to write a Python script that divides really_big_file.txt into smaller files with 300 lines each. For example, small_file_300.txt to have lines 1-300, small_file_600 to have lines 301-600, and so on until there are enough small files made to contain all the lines from the big file.
I would appreciate any suggestions on the easiest way to accomplish this using Python
lines_per_file = 300
smallfile = None
with open('really_big_file.txt') as bigfile:
for lineno, line in enumerate(bigfile):
if lineno % lines_per_file == 0:
if smallfile:
smallfile.close()
small_filename = 'small_file_{}.txt'.format(lineno + lines_per_file)
smallfile = open(small_filename, "w")
smallfile.write(line)
if smallfile:
smallfile.close()
Using itertools grouper recipe:
from itertools import zip_longest
def grouper(n, iterable, fillvalue=None):
"Collect data into fixed-length chunks or blocks"
# grouper(3, 'ABCDEFG', 'x') --> ABC DEF Gxx
args = [iter(iterable)] * n
return zip_longest(fillvalue=fillvalue, *args)
n = 300
with open('really_big_file.txt') as f:
for i, g in enumerate(grouper(n, f, fillvalue=''), 1):
with open('small_file_{0}'.format(i * n), 'w') as fout:
fout.writelines(g)
The advantage of this method as opposed to storing each line in a list, is that it works with iterables, line by line, so it doesn't have to store each small_file into memory at once.
Note that the last file in this case will be small_file_100200 but will only go until line 100000. This happens because fillvalue='', meaning I write out nothing to the file when I don't have any more lines left to write because a group size doesn't divide equally. You can fix this by writing to a temp file and then renaming it after instead of naming it first like I have. Here's how that can be done.
import os, tempfile
with open('really_big_file.txt') as f:
for i, g in enumerate(grouper(n, f, fillvalue=None)):
with tempfile.NamedTemporaryFile('w', delete=False) as fout:
for j, line in enumerate(g, 1): # count number of lines in group
if line is None:
j -= 1 # don't count this line
break
fout.write(line)
os.rename(fout.name, 'small_file_{0}.txt'.format(i * n + j))
This time the fillvalue=None and I go through each line checking for None, when it occurs, I know the process has finished so I subtract 1 from j to not count the filler and then write the file.
I do this a more understandable way and using less short cuts in order to give you a further understanding of how and why this works. Previous answers work, but if you are not familiar with certain built-in-functions, you will not understand what the function is doing.
Because you posted no code I decided to do it this way since you could be unfamiliar with things other than basic python syntax given that the way you phrased the question made it seem as though you did not try nor had any clue as how to approach the question
Here are the steps to do this in basic python:
First you should read your file into a list for safekeeping:
my_file = 'really_big_file.txt'
hold_lines = []
with open(my_file,'r') as text_file:
for row in text_file:
hold_lines.append(row)
Second, you need to set up a way of creating the new files by name! I would suggest a loop along with a couple counters:
outer_count = 1
line_count = 0
sorting = True
while sorting:
count = 0
increment = (outer_count-1) * 300
left = len(hold_lines) - increment
file_name = "small_file_" + str(outer_count * 300) + ".txt"
Third, inside that loop you need some nested loops that will save the correct rows into an array:
hold_new_lines = []
if left < 300:
while count < left:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
sorting = False
else:
while count < 300:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
Last thing, again in your first loop you need to write the new file and add your last counter increment so your loop will go through again and write a new file
outer_count += 1
with open(file_name,'w') as next_file:
for row in hold_new_lines:
next_file.write(row)
note: if the number of lines is not divisible by 300, the last file will have a name that does not correspond to the last file line.
It is important to understand why these loops work. You have it set so that on the next loop, the name of the file that you write changes because you have the name dependent on a changing variable. This is a very useful scripting tool for file accessing, opening, writing, organizing etc.
In case you could not follow what was in what loop, here is the entirety of the function:
my_file = 'really_big_file.txt'
sorting = True
hold_lines = []
with open(my_file,'r') as text_file:
for row in text_file:
hold_lines.append(row)
outer_count = 1
line_count = 0
while sorting:
count = 0
increment = (outer_count-1) * 300
left = len(hold_lines) - increment
file_name = "small_file_" + str(outer_count * 300) + ".txt"
hold_new_lines = []
if left < 300:
while count < left:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
sorting = False
else:
while count < 300:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
outer_count += 1
with open(file_name,'w') as next_file:
for row in hold_new_lines:
next_file.write(row)
lines_per_file = 300 # Lines on each small file
lines = [] # Stores lines not yet written on a small file
lines_counter = 0 # Same as len(lines)
created_files = 0 # Counting how many small files have been created
with open('really_big_file.txt') as big_file:
for line in big_file: # Go throught the whole big file
lines.append(line)
lines_counter += 1
if lines_counter == lines_per_file:
idx = lines_per_file * (created_files + 1)
with open('small_file_%s.txt' % idx, 'w') as small_file:
# Write all lines on small file
small_file.write('\n'.join(stored_lines))
lines = [] # Reset variables
lines_counter = 0
created_files += 1 # One more small file has been created
# After for-loop has finished
if lines_counter: # There are still some lines not written on a file?
idx = lines_per_file * (created_files + 1)
with open('small_file_%s.txt' % idx, 'w') as small_file:
# Write them on a last small file
small_file.write('n'.join(stored_lines))
created_files += 1
print '%s small files (with %s lines each) were created.' % (created_files,
lines_per_file)
import csv
import os
import re
MAX_CHUNKS = 300
def writeRow(idr, row):
with open("file_%d.csv" % idr, 'ab') as file:
writer = csv.writer(file, delimiter=',', quotechar='\"', quoting=csv.QUOTE_ALL)
writer.writerow(row)
def cleanup():
for f in os.listdir("."):
if re.search("file_.*", f):
os.remove(os.path.join(".", f))
def main():
cleanup()
with open("large_file.csv", 'rb') as results:
r = csv.reader(results, delimiter=',', quotechar='\"')
idr = 1
for i, x in enumerate(r):
temp = i + 1
if not (temp % (MAX_CHUNKS + 1)):
idr += 1
writeRow(idr, x)
if __name__ == "__main__": main()
with open('/really_big_file.txt') as infile:
file_line_limit = 300
counter = -1
file_index = 0
outfile = None
for line in infile.readlines():
counter += 1
if counter % file_line_limit == 0:
# close old file
if outfile is not None:
outfile.close()
# create new file
file_index += 1
outfile = open('small_file_%03d.txt' % file_index, 'w')
# write to file
outfile.write(line)
I had to do the same with 650000 line files.
Use the enumerate index and integer div it (//) with the chunk size
When that number changes close the current file and open a new one
This is a python3 solution using format strings.
chunk = 50000 # number of lines from the big file to put in small file
this_small_file = open('./a_folder/0', 'a')
with open('massive_web_log_file') as file_to_read:
for i, line in enumerate(file_to_read.readlines()):
file_name = f'./a_folder/{i // chunk}'
print(i, file_name) # a bit of feedback that slows the process down a
if file_name == this_small_file.name:
this_small_file.write(line)
else:
this_small_file.write(line)
this_small_file.close()
this_small_file = open(f'{file_name}', 'a')
Set files to the number of file you want to split the master file to
in my exemple i want to get 10 files from my master file
files = 10
with open("data.txt","r") as data :
emails = data.readlines()
batchs = int(len(emails)/10)
for id,log in enumerate(emails):
fileid = id/batchs
file=open("minifile{file}.txt".format(file=int(fileid)+1),'a+')
file.write(log)
A very easy way would if you want to split it in 2 files for example:
with open("myInputFile.txt",'r') as file:
lines = file.readlines()
with open("OutputFile1.txt",'w') as file:
for line in lines[:int(len(lines)/2)]:
file.write(line)
with open("OutputFile2.txt",'w') as file:
for line in lines[int(len(lines)/2):]:
file.write(line)
making that dynamic would be:
with open("inputFile.txt",'r') as file:
lines = file.readlines()
Batch = 10
end = 0
for i in range(1,Batch + 1):
if i == 1:
start = 0
increase = int(len(lines)/Batch)
end = end + increase
with open("splitText_" + str(i) + ".txt",'w') as file:
for line in lines[start:end]:
file.write(line)
start = end
In Python files are simple iterators. That gives the option to iterate over them multiple times and always continue from the last place the previous iterator got. Keeping this in mind, we can use islice to get the next 300 lines of the file each time in a continuous loop. The tricky part is knowing when to stop. For this we will "sample" the file for the next line and once it is exhausted we can break the loop:
from itertools import islice
lines_per_file = 300
with open("really_big_file.txt") as file:
i = 1
while True:
try:
checker = next(file)
except StopIteration:
break
with open(f"small_file_{i*lines_per_file}.txt", 'w') as out_file:
out_file.write(checker)
for line in islice(file, lines_per_file-1):
out_file.write(line)
i += 1
I have to input a text file that contains comma seperated and line seperated data in the following format:
A002,R051,02-00-00,05-21-11,00:00:00,REGULAR,003169391,001097585,05-21-11,04:00:00,REGULAR,003169415,001097588,05-21-11,08:00:00,REGULAR,003169431,001097607
Multiple sets of such data is present in the text file
I need to print all this in new lines with the condition:
1st 3 elements of every set followed by 5 parameters in a new line. So solution of the above set would be:
A002,R051,02-00-00,05-21-11,00:00:00,REGULAR,003169391,001097585
A002,R051,02-00-00,05-21-11,04:00:00,REGULAR,003169415,001097588
A002,R051,02-00-00,05-21-11,08:00:00,REGULAR,003169431,001097607
My function to achieve it is given below:
def fix_turnstile_data(filenames):
for name in filenames:
f_in = open(name, 'r')
reader_in = csv.reader(f_in, delimiter = ',')
f_out = open('updated_' + name, 'w')
writer_out = csv.writer(f_out, delimiter = ',')
array=[]
for line in reader_in:
i = 0
j = -1
while i < len(line):
if i % 8 == 0:
i+=2
j+=1
del array[:]
array.append(line[0])
array.append(line[1])
array.append(line[2])
elif (i+1) % 8 == 0:
array.append(line[i-3*j])
writer_out.writerow(array)
else:
array.append(line[i-3*j])
i+=1
f_in.close()
f_out.close()
The output is wrong and there is a space of 3 lines at the end of those lines whose length is 8. I suspect it might be the writer_out.writerow(array) which is to blame.
Can anyone please help me out?
Hmm, the logic you use ends up being fairly confusing. I'd do it more along these lines (this replaces your for loop), and this is more Pythonic:
for line in reader_in:
header = line[:3]
for i in xrange(3, len(line), 5):
writer_out.writerow(header + line[i:i+5])
I have data, that is set up as the following:
//Name_1 * *
>a xyzxyzyxyzyxzzxy
>b xyxyxyzxyyxzyxyz
>c xyzyxzyxyzyxyzxy
//Name_2
>a xyzxyzyxyzxzyxyx
>b zxyzxyzxyyzxyxzx
>c zxyzxyzxyxyzyzxy
//Name_3 * *
>a xyzxyzyxyzxzyxyz
>b zxyzxyzxzyyzyxyx
>c zxyzxyzxyxyzyzxy
...
The //-line refers to an ID for the following group of sequences until the next //-line is reached.
I have been working on writing a program, that reads the position of the asterix, and print the characters on the given position for the sequences.
To simplifiy things for myself, I have been working on a subset of my data, containing only one group of sequences, so e.g.:
//Name_1 * *
>a xyzxyzyxyzyxzzxy
>b xyxyxyzxyyxzyxyz
>c xyzyxzyxyzyxyzxy
My program does what I want on this subset.
import sys
import csv
datafile = open(sys.argv[1], 'r')
outfile = open(sys.argv[1]+"_FGT_Data", 'w')
csv_out = csv.writer(outfile, delimiter=',')
csv_out.writerow(['Locus', 'Individual', 'Nucleotide', 'Position'])
with (datafile) as searchfile:
var_line = [line for line in searchfile if '*' in line]
LocusID = [line[2:13].strip() for line in var_line]
poslist = [i for line in var_line for i, x in enumerate(line) if x =='*']
datafile = open(sys.argv[1], 'r')
with (datafile) as getsnps:
lines = [line for line in getsnps.readlines() if line.startswith('>')]
for pos in poslist:
for line in lines:
snp = line[pos]
individual = line[0:7]
indistr = individual.strip()
csv_out.writerow((LocusID[0], indistr, line[pos], str(pos)))
datafile.close()
outfile.close()
However, now I am trying to modify it to work on the full dataset. I am having trouble finding a way to iterate over the data in the correct way.
I need to search through the file, and when a line containing '' is reached, I need to do as in the above code for the sequences corresponding to the given line, and then continue to the next line containing an ''. Do I need to split up my data with regards to the //-lines or what is the best approach?
I have uploaded a sample of my data to dropbox:
Data_Sample.txt contains several groups, and is the kind of data, I am trying to get the program to work on.
Data_One_Group.txt contains only one group, and is the data I have gotten the program to work on so far.
https://www.dropbox.com/sh/3j4i04s2rg6b63h/AADkWG3OcsutTiSsyTl8L2Vda?dl=0
--------EDIT---------
I am trying to implement the suggestion by #Julien Spronck below.
However, I am having trouble processing the produced block. How would I be able to search through the block line for line. E.g., why does the below not work as intended? It just prints the asterix' and not the line itself.
block =''
with open('onelocus.txt', 'r') as searchfile:
for line in searchfile:
if line.startswith('//'):
#print line
if block:
for line in block:
if '*' in line:
print line
block = line
else:
block += line
---------EDIT 2----------
I am getting closer. I understand that fact, that I need to split the string into line, to be able to search through them. The below works on one group, but when I try to itereate over several, it prints the information for the first group only. But does it for as many groups, as there are. I have tried clearing LocusID and poslist before next iteration, but this does not seem to be the solution.
block =''
with (datafile) as searchfile:
for line in searchfile:
if line.startswith('//'):
if block:
var_line = [line for line in block.splitlines() if '*' in line]
LocusID = [line[2:13].strip() for line in var_line]
print LocusID
poslist = [i for line in var_line for i, x in enumerate(line) if x == '*']
print poslist
block = line
else:
block += line
Can't you do something like:
block =''
with open(filename, 'r') as fil:
for line in fil:
if line.startswith('//'):
if block:
do_something_with(block)
block = line
else:
block += line
if block:
do_something_with(block)
In this code, I just append the lines of the file to a variable block. Once I find a line that starts with //, I process the previous block and reinitialize the block for the next iteration.
The last two lines will take care of processing the last block, which would not be processed otherwise.
do_something_with(block) could be something like this:
def do_something_with(block):
lines = block.splitlines()
j = 0
first_line = lines[j]
while first_line.strip() == '':
j += 1
first_line = lines[j]
pos = []
position = first_line.find('*')
while position != -1:
pos.append(position)
position = first_line.find('*', position+1)
for k, line in enumerate(lines):
if k > j:
for p in pos:
print line[p],
print
## prints
## z y
## x z
## z y
I have created a way to make this work with the data you provided.
You should run it with 2 file locations, 1 should be your input.txt and 2 should be your output.csv
explanation
first we create a dictionary with the locus as key and the sequences as values.
We iterate over this dictionary and get the * locations in the locus and append these to a list indexes.
We iterate over the values belonging to this key and extract the sequence
per iteration we iterate over indexes so that we gather the snps.
per iteration we append to our csv file.
We empty the indexes list so we can go to the next key.
Keep in mind
This method is highly dependant on the amount of spaces you have inside your input.txt.
You should know that this will not be the fastest way to get it done. but it does get it done.
I hope this helped, if you have any questions, feel free to ask them, and if I have time, I will happily try to answer them.
script
import sys
import csv
sequences = []
dic = {}
indexes = []
datafile = sys.argv[1]
outfile = sys.argv[2]
with open(datafile,'r') as snp_file:
lines = snp_file.readlines()
for i in range(0,len(lines)):
if lines[i].startswith("//"):
dic[lines[i].rstrip()] = sequences
del sequences[:]
if lines[i].startswith(">"):
sequences.append(lines[i].rstrip())
for key in dic:
locus = key.split(" ")[0].replace("//","")
for i, x in enumerate(key):
if x == '*':
indexes.append(i-11)
for sequence in dic[key]:
seq = sequence.split(" ")[1]
seq_id = sequence.split(" ")[0].replace(">","")
for z in indexes:
position = z+1
nucleotide = seq[z]
with open(outfile,'a')as handle:
csv_out = csv.writer(handle, delimiter=',')
csv_out.writerow([locus,seq_id,position,nucleotide])
del indexes[:]
input.txt
//Locus_1 * *
>Safr01 AATCCGTTTTAAACCAGNTCYAT
>Safr02 TTAATCCGTTTTAAACCAGNTCY
//Locus_2 * *
>Safr01 AATCCGTTTTAAACCAGNTCYAT
>Safr02 TTAATCCGTTTTAAACCAGNTCY
output.csv
Locus_1,Safr01,1,A
Locus_1,Safr01,22,A
Locus_1,Safr02,1,T
Locus_1,Safr02,22,C
Locus_2,Safr01,5,C
Locus_2,Safr01,19,T
Locus_2,Safr02,5,T
Locus_2,Safr02,19,G
This is how I ended up solving the problem:
def do_something_with(block):
lines = block.splitlines()
for line in lines:
if '*' in line:
hit = line
LocusID = hit[2:13].strip()
for i, x in enumerate(hit):
if x=='*':
poslist.append(i)
for pos in poslist:
for line in lines:
if line.startswith('>'):
individual = line[0:7].strip()
snp = line[pos]
print LocusID, individual, snp, pos,
csv_out.writerow((LocusID, individual, snp, pos))
with (datafile) as searchfile:
for line in searchfile:
if line.startswith('//'):
if block:
do_something_with(block)
poslist = list()
block = line
else:
block += line
if block:
do_something_with(block)
I want to pull all data from a text file from a specified line number until the end of a file. This is how I've tried:
def extract_values(f):
line_offset = []
offset = 0
last_line_of_heading = False
if not last_line_of_heading:
for line in f:
line_offset.append(offset)
offset += len(line)
if whatever_condition:
last_line_of_heading = True
f.seek(0)
# non-functioning pseudocode follows
data = f[offset:] # read from current offset to end of file into this variable
There is actually a blank line between the header and the data I want, so ideally I could skip this also.
Do you know the line number in advance? If so,
def extract_values(f):
line_number = # something
data = f.readlines()[line_number:]
If not, and you need to determine the line number based on the content of the file itself,
def extract_values(f):
lines = f.readlines()
for line_number, line in enumerate(lines):
if some_condition(line):
data = lines[line_number:]
break
This will not be ideal if your files are enormous (since the lines of the file are loaded into memory); in that case, you might want to do it in two passes, only storing the file data on the second pass.
Your if clause is at the wrong position:
for line in f:
if not last_line_of_heading:
Consider this code:
def extract_values(f):
rows = []
last_line_of_heading = False
for line in f:
if last_line_of_heading:
rows.append(line)
elif whatever_condition:
last_line_of_heading = True
# if you want a string instead of an array of lines:
data = "\n".join(rows)
you can use enumerate:
f=open('your_file')
for i,x in enumerate(f):
if i >= your_line:
#do your stuff
here i will store line number starting from 0 and x will contain the line
using list comprehension
[ x for i,x in enumerate(f) if i >= your_line ]
will give you list of lines after specified line
using dictionary comprehension
{ i:x for i,x in enumerate(f) if i >= your_line }
this will give you line number as key and line as value, from specified line number.
Try this small python program, LastLines.py
import sys
def main():
firstLine = int(sys.argv[1])
lines = sys.stdin.read().splitlines()[firstLine:]
for curLine in lines:
print curLine
if __name__ == "__main__":
main()
Example input, test1.txt:
a
b
c
d
Example usage:
python LastLines.py 2 < test1.txt
Example output:
c
d
This program assumes that the first line in a file is the 0th line.
I have a text file say really_big_file.txt that contains:
line 1
line 2
line 3
line 4
...
line 99999
line 100000
I would like to write a Python script that divides really_big_file.txt into smaller files with 300 lines each. For example, small_file_300.txt to have lines 1-300, small_file_600 to have lines 301-600, and so on until there are enough small files made to contain all the lines from the big file.
I would appreciate any suggestions on the easiest way to accomplish this using Python
lines_per_file = 300
smallfile = None
with open('really_big_file.txt') as bigfile:
for lineno, line in enumerate(bigfile):
if lineno % lines_per_file == 0:
if smallfile:
smallfile.close()
small_filename = 'small_file_{}.txt'.format(lineno + lines_per_file)
smallfile = open(small_filename, "w")
smallfile.write(line)
if smallfile:
smallfile.close()
Using itertools grouper recipe:
from itertools import zip_longest
def grouper(n, iterable, fillvalue=None):
"Collect data into fixed-length chunks or blocks"
# grouper(3, 'ABCDEFG', 'x') --> ABC DEF Gxx
args = [iter(iterable)] * n
return zip_longest(fillvalue=fillvalue, *args)
n = 300
with open('really_big_file.txt') as f:
for i, g in enumerate(grouper(n, f, fillvalue=''), 1):
with open('small_file_{0}'.format(i * n), 'w') as fout:
fout.writelines(g)
The advantage of this method as opposed to storing each line in a list, is that it works with iterables, line by line, so it doesn't have to store each small_file into memory at once.
Note that the last file in this case will be small_file_100200 but will only go until line 100000. This happens because fillvalue='', meaning I write out nothing to the file when I don't have any more lines left to write because a group size doesn't divide equally. You can fix this by writing to a temp file and then renaming it after instead of naming it first like I have. Here's how that can be done.
import os, tempfile
with open('really_big_file.txt') as f:
for i, g in enumerate(grouper(n, f, fillvalue=None)):
with tempfile.NamedTemporaryFile('w', delete=False) as fout:
for j, line in enumerate(g, 1): # count number of lines in group
if line is None:
j -= 1 # don't count this line
break
fout.write(line)
os.rename(fout.name, 'small_file_{0}.txt'.format(i * n + j))
This time the fillvalue=None and I go through each line checking for None, when it occurs, I know the process has finished so I subtract 1 from j to not count the filler and then write the file.
I do this a more understandable way and using less short cuts in order to give you a further understanding of how and why this works. Previous answers work, but if you are not familiar with certain built-in-functions, you will not understand what the function is doing.
Because you posted no code I decided to do it this way since you could be unfamiliar with things other than basic python syntax given that the way you phrased the question made it seem as though you did not try nor had any clue as how to approach the question
Here are the steps to do this in basic python:
First you should read your file into a list for safekeeping:
my_file = 'really_big_file.txt'
hold_lines = []
with open(my_file,'r') as text_file:
for row in text_file:
hold_lines.append(row)
Second, you need to set up a way of creating the new files by name! I would suggest a loop along with a couple counters:
outer_count = 1
line_count = 0
sorting = True
while sorting:
count = 0
increment = (outer_count-1) * 300
left = len(hold_lines) - increment
file_name = "small_file_" + str(outer_count * 300) + ".txt"
Third, inside that loop you need some nested loops that will save the correct rows into an array:
hold_new_lines = []
if left < 300:
while count < left:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
sorting = False
else:
while count < 300:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
Last thing, again in your first loop you need to write the new file and add your last counter increment so your loop will go through again and write a new file
outer_count += 1
with open(file_name,'w') as next_file:
for row in hold_new_lines:
next_file.write(row)
note: if the number of lines is not divisible by 300, the last file will have a name that does not correspond to the last file line.
It is important to understand why these loops work. You have it set so that on the next loop, the name of the file that you write changes because you have the name dependent on a changing variable. This is a very useful scripting tool for file accessing, opening, writing, organizing etc.
In case you could not follow what was in what loop, here is the entirety of the function:
my_file = 'really_big_file.txt'
sorting = True
hold_lines = []
with open(my_file,'r') as text_file:
for row in text_file:
hold_lines.append(row)
outer_count = 1
line_count = 0
while sorting:
count = 0
increment = (outer_count-1) * 300
left = len(hold_lines) - increment
file_name = "small_file_" + str(outer_count * 300) + ".txt"
hold_new_lines = []
if left < 300:
while count < left:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
sorting = False
else:
while count < 300:
hold_new_lines.append(hold_lines[line_count])
count += 1
line_count += 1
outer_count += 1
with open(file_name,'w') as next_file:
for row in hold_new_lines:
next_file.write(row)
lines_per_file = 300 # Lines on each small file
lines = [] # Stores lines not yet written on a small file
lines_counter = 0 # Same as len(lines)
created_files = 0 # Counting how many small files have been created
with open('really_big_file.txt') as big_file:
for line in big_file: # Go throught the whole big file
lines.append(line)
lines_counter += 1
if lines_counter == lines_per_file:
idx = lines_per_file * (created_files + 1)
with open('small_file_%s.txt' % idx, 'w') as small_file:
# Write all lines on small file
small_file.write('\n'.join(stored_lines))
lines = [] # Reset variables
lines_counter = 0
created_files += 1 # One more small file has been created
# After for-loop has finished
if lines_counter: # There are still some lines not written on a file?
idx = lines_per_file * (created_files + 1)
with open('small_file_%s.txt' % idx, 'w') as small_file:
# Write them on a last small file
small_file.write('n'.join(stored_lines))
created_files += 1
print '%s small files (with %s lines each) were created.' % (created_files,
lines_per_file)
import csv
import os
import re
MAX_CHUNKS = 300
def writeRow(idr, row):
with open("file_%d.csv" % idr, 'ab') as file:
writer = csv.writer(file, delimiter=',', quotechar='\"', quoting=csv.QUOTE_ALL)
writer.writerow(row)
def cleanup():
for f in os.listdir("."):
if re.search("file_.*", f):
os.remove(os.path.join(".", f))
def main():
cleanup()
with open("large_file.csv", 'rb') as results:
r = csv.reader(results, delimiter=',', quotechar='\"')
idr = 1
for i, x in enumerate(r):
temp = i + 1
if not (temp % (MAX_CHUNKS + 1)):
idr += 1
writeRow(idr, x)
if __name__ == "__main__": main()
with open('/really_big_file.txt') as infile:
file_line_limit = 300
counter = -1
file_index = 0
outfile = None
for line in infile.readlines():
counter += 1
if counter % file_line_limit == 0:
# close old file
if outfile is not None:
outfile.close()
# create new file
file_index += 1
outfile = open('small_file_%03d.txt' % file_index, 'w')
# write to file
outfile.write(line)
I had to do the same with 650000 line files.
Use the enumerate index and integer div it (//) with the chunk size
When that number changes close the current file and open a new one
This is a python3 solution using format strings.
chunk = 50000 # number of lines from the big file to put in small file
this_small_file = open('./a_folder/0', 'a')
with open('massive_web_log_file') as file_to_read:
for i, line in enumerate(file_to_read.readlines()):
file_name = f'./a_folder/{i // chunk}'
print(i, file_name) # a bit of feedback that slows the process down a
if file_name == this_small_file.name:
this_small_file.write(line)
else:
this_small_file.write(line)
this_small_file.close()
this_small_file = open(f'{file_name}', 'a')
Set files to the number of file you want to split the master file to
in my exemple i want to get 10 files from my master file
files = 10
with open("data.txt","r") as data :
emails = data.readlines()
batchs = int(len(emails)/10)
for id,log in enumerate(emails):
fileid = id/batchs
file=open("minifile{file}.txt".format(file=int(fileid)+1),'a+')
file.write(log)
A very easy way would if you want to split it in 2 files for example:
with open("myInputFile.txt",'r') as file:
lines = file.readlines()
with open("OutputFile1.txt",'w') as file:
for line in lines[:int(len(lines)/2)]:
file.write(line)
with open("OutputFile2.txt",'w') as file:
for line in lines[int(len(lines)/2):]:
file.write(line)
making that dynamic would be:
with open("inputFile.txt",'r') as file:
lines = file.readlines()
Batch = 10
end = 0
for i in range(1,Batch + 1):
if i == 1:
start = 0
increase = int(len(lines)/Batch)
end = end + increase
with open("splitText_" + str(i) + ".txt",'w') as file:
for line in lines[start:end]:
file.write(line)
start = end
In Python files are simple iterators. That gives the option to iterate over them multiple times and always continue from the last place the previous iterator got. Keeping this in mind, we can use islice to get the next 300 lines of the file each time in a continuous loop. The tricky part is knowing when to stop. For this we will "sample" the file for the next line and once it is exhausted we can break the loop:
from itertools import islice
lines_per_file = 300
with open("really_big_file.txt") as file:
i = 1
while True:
try:
checker = next(file)
except StopIteration:
break
with open(f"small_file_{i*lines_per_file}.txt", 'w') as out_file:
out_file.write(checker)
for line in islice(file, lines_per_file-1):
out_file.write(line)
i += 1