Reading the first lines of bz2 files in python

Question

I am trying to extract the 10,000 first lines from a bz2 file.

   import bz2       
   file = "file.bz2"
   file_10000 = "file.txt"

   output_file = codecs.open(file_10000,'w+','utf-8')

   source_file = bz2.open(file, "r")
   count = 0
   for line in source_file:
       count += 1
       if count < 10000:
           output_file.writerow(line)

But I get an error message. The module object does not have an open attribute. Do you have ideas? Or maybe I could save the 10,000 first lines in a txt file in some other way? I am on Windows.

Answer 1

Here is a complete working example that includes writing and reading a test file that is much smaller than your 10,000 lines. It's nice to have working examples in questions so we can easily test.

import bz2
import itertools
import codecs

file = "file.bz2"
file_10000 = "file.txt"

# write test file with 9 lines
with bz2.BZ2File(file, "w") as fp:
    fp.write('\n'.join('123456789'))

# the original script using BZ2File ... and 3 lines for test
# ...and fixing bugs:
#     1) it only writes 9999 instead of 10000
#     2) files don't do writerow
#     3) close the files

output_file = codecs.open(file_10000,'w+','utf-8')

source_file = bz2.BZ2File(file, "r")
count = 0
for line in source_file:
    count += 1
    if count <= 3:
       output_file.write(line)
source_file.close()
output_file.close()

# show what you got
print('---- Test 1 ----')
print(repr(open(file_10000).read()))   

- for . :

# a faster way to read first 3 lines
with bz2.BZ2File(file) as source_file,\
        codecs.open(file_10000,'w+','utf-8') as output_file:
    output_file.writelines(itertools.islice(source_file, 3))

# show what you got
print('---- Test 2 ----')
print(repr(open(file_10000).read()))   

Answer 2

, , , , Python2/3. , , >= 10 000 .

from bz2 import BZ2File as bzopen

# writing to a file
with bzopen("file.bz2", "w") as bzfout:
    for i in range(123456):
        bzfout.write(b"%i\n" % i)

# reading a bz2 archive
with bzopen("file.bz2", "r") as bzfin:
    """ Handle lines here """
    lines = []
    for i, line in enumerate(bzfin):
        if i == 10000: break
        lines.append(line.rstrip())

print(lines)

Answer 3

Another variation.

import bz2

myfile =  'c:\\users\\rafporti\\documents\\random.txt.bz2'
newfile = 'c:\\users\\rafporti\\documents\\random_10000.txt'

stream = bz2.BZ2File(myfile)
with open(newfile, 'w') as f:
  for i in range(1,10000):
    f.write(stream.readline())

Answer 4

This worked for me:

sudo apt-get install python-dev
sudo pip install backports.lzma