Using the following bit of code:
for root, dirs, files in os.walk(corpus_name):
for file in files:
if file.endswith(".v4_gold_conll"):
f= open(file)
lines = f.readlines()
tokens = [line.split()[3] for line in lines if line.strip()
and not line.startswith("#")]
print(tokens)
I get the following error:
Traceback (most recent call last): File "text_statistics.py", line
28, in
corpus_reading_pos(corpus_name, option) File "text_statistics.py", line 13, in corpus_reading_pos
f= open(file) FileNotFoundError: [Errno 2] No such file or directory: 'abc_0001.v4_gold_conll'
As you can see, the file was, in fact, located, but then when I try to open the file, it... can't find it?
Edit:
using this updated code, it stops after reading 7 files, but there are 172 files.
def corpus_reading_token_count(corpus_name, option="token"):
for root, dirs, files in os.walk(corpus_name):
tokens = []
file_count = 0
for file in files:
if file.endswith(".v4_gold_conll"):
with open((os.path.join(root, file))) as f:
tokens += [line.split()[3] for line in f if line.strip() and not line.startswith("#")]
file_count += 1
print(tokens)
print("File count:", file_count)
file is just the file without the directory, which is root in your code. Try this:
f = open(os.path.join(root, file)))
Also, you should better use with to open the file, and not use file as a variable name, shadowing the builtin type. Also, judging from your comment, you should probably extend the list of tokens (use += instead of =):
tokens = []
for root, dirs, files in os.walk(corpus_name):
for filename in files:
if filename.endswith(".v4_gold_conll"):
with open(os.path.join(root, filename))) as f:
tokens += [line.split()[3] for line in f if line.strip() and not line.startswith("#")]
print(tokens)
You'll have to join the root with the filename.
for root, dirs, files in os.walk(corpus_name):
for file in files:
if file.endswith(".v4_gold_conll"):
with open(os.path.join(root, file)) as f:
tokens = [
line.split()[3]
for line in f
if line.strip() and not line.startswith("#")
]
print(tokens)
Related
I want all files in directory "path" to have the string "error" removed from them and the result to be saved in the same file that was editted. My current code (below) ends up clearing up the entire file, rather than just removing the string and keeping everything else the same.
import os
path = "path"
files = os.listdir(path)
error = "string"
for index, file in enumerate(files):
with open(os.path.join(path, file)) as fin, open(os.path.join(path, file), "w+") as fout:
for line in fin:
line = line.replace(error, "f")
fout.write(line)
import os
path = "path"
files = os.listdir(path)
error = "string"
for index, file in enumerate(files):
with open(os.path.join(path, file), 'r') as fin:
d = din.read()
with open(os.path.join(path, file), "w") as fout:
d = d.replace(error, "")
fout.write(d)
This is the correct way to do this:
import os
path = "path"
for file in os.listdir(path):
if not os.path.isdir(file):
with open(file, 'r+') as fd:
contents = fd.read().replace('error', '')
fd.seek(0)
fd.write(contents)
fd.truncate()
it's a python script.
I am writing the content of all the files with a special extension to a txt file skipping the first line in files, removing duplicates and special Paths
import os
skipLines = "/home/YY"
mainDir = "C:/XX"
directory = os.fsencode(mainDir)
endFile = mainDir+"/endFile.txt"
open(endFile, 'w').close()
fileoutput = open(endFile, "a")
for file in os.listdir(directory):
filename = os.fsdecode(file)
fileFullPath = mainDir+"/"+filename
if filename.endswith(".dep"):
print("working on : ", filename)
file = open(fileFullPath, "r")
next(file)
for line in file:
if skipLines not in line:
fileoutput.write(line)
else:
continue
file.close()
fileoutput.close()
lines_seen = set()
with open("C:/XX/endFile.txt", "r+") as f:
d = f.readlines()
f.seek(0)
for i in d:
if i not in lines_seen:
f.write(i)
lines_seen.add(i)
f.truncate()
fileoutput.close()
my end file looks like this:
F0/XXX.c
../../F1/F2/X/Test.h
../../F1/F2/Z/Test1.h
../../../F1/F3/Y/Test3.h
.
.
.
Here is my question:
how can I copy these file from the paths indicated in each line, and create a folder and create the same file path and copy the files in the corresponding paths?
I wrote a python code which will take input of a txt file and print to excel . I'm able to achieve for one txt file giving as input . But the requirement I have will have around a million of txt files in a folder . SO I don't know how to change the python code to take the input from a folder .
The below code handles input 1.txt file . I want to run multiple txt files from a folder , That's my requirement .
with open('C:/test/1.txt') as infile:
registrations = []
fields = OrderedDict()
d = {}
for line in infile:
line = line.strip()
if line:
key, value = [s.strip() for s in line.split(':', 1)]
d[key] = value
fields[key] = None
else:
if d:
registrations.append(d)
print(d)
d = {}
if ',' not in line:
print('line without ,:', line)
continue
else:
if d: # handle EOF
registrations.append(d)
with open('C:/registrations.csv', 'w') as outfile:
writer = DictWriter(outfile, fieldnames=fields)
writer.writeheader()
writer.writerows(registrations)
Thanks,
Meera
Use the pathlib module:
from pathlib import Path
FOLDER = Path('your/folder/here')
for file in FOLDER.glob('*.txt'):
# Do your thing
pass
Based on your source code, I optimized it. I use os.walk to access each .txt file and then read it line by line in those txt files and save it in an enum. Then I will check each line in that enum.
import os
extension = [".txt"]
path = "C:/test"
for subdir, dirs, files in os.walk(path):
for file in files:
file_path = os.path.join(subdir, file)
ext = os.path.splitext(file)[-1].lower()
if ext in extension:
with open(file_path, "r") as f:
try:
f_content = f.readlines()
except Exception as e:
print(e)
for l_idx, line in enumerate(f_content):
# ..................................
# l_idx: return position line
# line: content in line
i am a beginner in python.
So what I want to do is a script that finds a specific line in multiple files and delete it and rewrite the file with the same name. Something like this but for more files:
similar to problem "Deleting a line in multiple files in python"
i traid quith this code that i can find in the before question
but it didn't work
import os
os.chdir('C:\escenarie')
source = "*.mgt"
for root, dirs, filenames in os.walk(source):
for f in filenames:
this_file = open(os.path.join(source, f), "r")
this_files_data = this_file.readlines()
this_file.close()
# rewrite the file with all line except the one you don't want
this_file = open(os.path.join(source, f), "w")
for line in this_files_data:
if line != " 1.200 5 0.00000"":
this_file.write(line)
this_file.close()
You ought to learn basic file operations in Python. The code example below should help.
#open file
with open(filename, 'r') as f:
lines = f.readlines()
#find index of line to remove
for index, line in enumerate(lines):
if 'delete me' in line:
#remove line
lines.pop(index)
break
#write new file
with open(filename, 'w') as f:
f.write(''.join(lines))
And to perform this operation on multiple files:
filenames = ['file1.txt', 'file2.txt']
for filename in filenames:
# ... see code above
I have a directory with many subdirectories, containing files. I want to open the files ending with "root.vrpj" or "root.vprj", in "App_integrations" folder and copy the lines containing the word "table" to another file.
Until now I've managed to visit each file with this code:
for root, dirs, files in os.walk(movedir):
for filename in files:
if filename.endswith(("root.vrpj", "root.vprj")):
The problem is that what I have now are just the names of the files I want to visit and I'm stuck here.
You can try this:
f = open('final_file.txt', 'w')
for root, dirs, files in os.walk(movedir):
for filename in files:
if filename.endswith("root.vrpj") or filename.endswith("root.vprj"):
with open(filename) as data:
for line in data:
if "table" in data:
f.write('{}\n'.format(data))
f.close()
This is a version of Ajax' code that closes the files you open in the loop (and fixes a couple of other minor issues):
with open('final_file.txt', 'w') as f:
for root, dirs, files in os.walk(movedir):
for filename in files:
if filename.endswith(("root.vrpj"), ("root.vprj")):
with open(os.path.join(root, filename)) as finput:
for line in finput:
if 'table' in line:
f.write(line)
however, when you see 8 levels of indentation you need to refactor, e.g.:
def find_files(startdir, *extensions):
for root, dirs, files in os.walk(movedir):
for filename in files:
if filename.endswith(extensions):
yield os.path.join(root, filename)
def find_lines(fname, text):
with open(fname) as fp:
return [line for line in fp if text in line]
with open('final_file.txt', 'w') as f:
for fname in find_files(movedir, 'root.vrpj', 'root.vprj'):
f.writelines(find_lines(fname, 'table'))
I finally solved it
import os
rootdir = my root folder
# creates a file f that contains all the lines of the files
# with "root.vrpj" or "root.vprj" in their name
# and who are inside "App_integrations" folders
# without duplicates
#creating the big file with all the file containing the lines I need
f = open('final_file.txt', 'a')
for root, dirs, files in os.walk(rootdir):
for filename in files:
if (filename.endswith(("root.vrpj", "root.vprj")) and ("App_Integration" in os.path.join(root, filename))):
full_name = os.path.join(root, filename)
data = open(full_name).read()
f.write(data + "\n")
f.close()
#copying the lines I need to f1 without duplicates
lines_seen = set()
f = open('final_file.txt')
f1 = open('testread1.txt', 'a')
doIHaveToCopyTheLine=False
for line in f.readlines():
if (("Table" in line) and (line not in lines_seen)):
doIHaveToCopyTheLine=True
if doIHaveToCopyTheLine:
f1.write(line)
lines_seen.add(line)
f1.close()
f.close()
Find the files
from pathlib import Path
import itertools
source_dir = Path(<source_dir>)
patterns = ['**/*root.vrpj', '**/*root.vprj']
files = itertools.chain.from_iterables(source_dir.glob(pat) for pat in patterns))
Filter the files:
def filter_lines(files):
for file in files:
if not 'App_Integration' in file.parts:
continue
with file.open('r') as file_handle:
for line in file_handle:
if 'table' in line:
yield line
Write the output
def save_lines(lines, output_file=sys.std_out):
for line in lines:
output_file.write(line)
with Path(<output_file>).open('w') as output_file:
save_lines(filter_lines(files), as output_file)