Das deutsche Python-Forum

Code: Alles auswählen

to_delete = ['ich', 'du', 'er', 'sie', 'es']
fo = open('C:\\Download\\testdatei.txt', 'r')
lines = fo.readlines()
fo.close()
for s in to_delete:
    lines = [x for x in lines if x.lower().find(s) == -1]
print(lines)
fo = open('C:\\Download\\testdatei.txt', 'w')
fo.writelines(lines)
fo.close()

Code: Alles auswählen

INPUT_FILE = r'C:\Download\testdatei.txt'
OUTPUT_FILE = r'C:\Download\testdatei.txt'

def some_filter(line):
    return len(line)%2 == 0

def main():
    with open(INPUT_FILE, 'r') as input_lines:
        with open(OUTPUT_FILE, 'w') as output_file:
            for line in input_lines:
                if some_filter(line):
                    ouput_file.write(line)

if __name__ == '__main__':
    main()

Code: Alles auswählen

with open('pruned', 'w') as pruned:
    with open('origin') as origin:
      for line in origin:
          parts = line.split()
          if not any(w in parts for w in to_delete):
              pruned.write(line)

Code: Alles auswählen

def main():
    to_delete = {'ich', 'du', 'er', 'sie', 'es'}
    with open('test_f.txt') as f:
        result = [line.strip() for line in f.readlines() if not any(map(lambda x: x in to_delete, line.split())) ]
    print(result)

if __name__ == '__main__':
    main()

Code: Alles auswählen

def main():
    to_delete = {'ich', 'du', 'er', 'sie', 'es'}
    with open('test_f.txt') as f:
        result = [line.strip() for line in f if not any(item in to_delete for item in line.split())]
    print(result)

if __name__ == '__main__':
    main()

Code: Alles auswählen

# ******************************************************************************

INPUT_FILE = r'C:\Download\testdatei - Kopie.txt'
OUTPUT_FILE = r'C:\Download\new.txt'

# ******************************************************************************

def filter(line):

    to_delete = ['ich', 'du', 'er', 'sie', 'es']
    parts = line.lower().split()
    return not any(w in parts for w in to_delete)

# ******************************************************************************

def main():
    with open(INPUT_FILE, 'r') as input_lines:
        with open(OUTPUT_FILE, 'w') as output_file:
            for line in input_lines:
                if filter(line):
                    output_file.write(line)

# ******************************************************************************

if __name__ == '__main__':
    main()

Code: Alles auswählen

In [13]: cat foo
Hallo
Welt!
In [14]: with open("foo") as infile, open("bar", "w") as outfile:
   ....:     outfile.write(infile.read())
   ....:     

In [15]: cat bar
Hallo
Welt!

Code: Alles auswählen

import re

# ******************************************************************************

INPUT_FILE = r'C:\Download\testdatei - Kopie.txt'
OUTPUT_FILE = r'C:\Download\testdatei - Kopie_neu.txt'
TO_DELETE = set(['ich', 'du', 'er', 'sie', 'es'])

# ******************************************************************************

def some_filter(line, args):

    result = True

    for arg in args:
        if re.search('{1}{0}{1}'.format(arg, r'\b'), line, re.I):
           result = False
           break

    return result

# ******************************************************************************

def main():
    with open(INPUT_FILE, 'r') as input_lines, open(OUTPUT_FILE, 'w') as \
        output_file:
        for line in input_lines:
            if some_filter(line, TO_DELETE):
                output_file.write(line)

# ******************************************************************************

if __name__ == '__main__':
    main()

Code: Alles auswählen

def some_filter(line, args):
    return not re.search(r'\b({})\b'.format('|'.join(map(re.escape, args))), line. re.I)

Code: Alles auswählen

#!/usr/bin/env python
import re
from itertools import ifilterfalse


def iter_lines(filename):
    with open(filename, 'r') as lines:
        for line in lines:
            yield line


def create_line_test(words):
    return re.compile(
        r'\b({0})\b'.format('|'.join(re.escape(word) for word in words)),
        re.IGNORECASE
    ).search


def save_lines(filename, lines):
    with open(filename, 'w') as out_file:
        out_file.writelines(lines)


def main():
    to_delete = ['ich', 'du', 'er', 'sie', 'es']
    save_lines(
        'test2.txt',
        ifilterfalse(create_line_test(to_delete), iter_lines('test.txt'))
    )


if __name__ == '__main__':
    main()

Code: Alles auswählen

In [1]: values = list(range(10000000))

In [3]: some_value = 9999999

In [4]: timeit some_value in values
1 loops, best of 3: 305 ms per loop

In [5]: values = set(range(10000000))

In [6]: timeit some_value in values
10000000 loops, best of 3: 147 ns per loop

Code: Alles auswählen

In [14]: some_value = 999999

In [15]: values = list(range(1000000))

In [16]: timeit some_value in values
10 loops, best of 3: 30.6 ms per loop

In [17]: values = set(range(1000000))

In [18]: timeit some_value in values
10000000 loops, best of 3: 145 ns per loop

Code: Alles auswählen

def main():
    to_delete = ['ich', 'du', 'er', 'sie', 'es']
    lines = iter_lines('test.txt')
    filtered_lines = ifilterfalse(create_line_test(to_delete), lines)
    save_lines('test2.txt', filtered_lines)