How to open every file in a folder
Question:
I have a python script parse.py, which in the script open a file, say file1, and then do something maybe print out the total number of characters.
filename = 'file1'
f = open(filename, 'r')
content = f.read()
print filename, len(content)
Right now, I am using stdout to direct the result to my output file – output
python parse.py >> output
However, I don’t want to do this file by file manually, is there a way to take care of every single file automatically? Like
ls | awk '{print}' | python parse.py >> output
Then the problem is how could I read the file name from standardin?
or there are already some built-in functions to do the ls and those kind of work easily?
Thanks!
Answers:
Os
You can list all files in the current directory using os.listdir
:
import os
for filename in os.listdir(os.getcwd()):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
Glob
Or you can list only some files, depending on the file pattern using the glob
module:
import os, glob
for filename in glob.glob('*.txt'):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
It doesn’t have to be the current directory you can list them in any path you want:
import os, glob
path = '/some/path/to/file'
for filename in glob.glob(os.path.join(path, '*.txt')):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
Pipe
Or you can even use the pipe as you specified using fileinput
import fileinput
for line in fileinput.input():
# do your stuff
And you can then use it with piping:
ls -1 | python parse.py
You should try using os.walk
.
import os
yourpath = 'path'
for root, dirs, files in os.walk(yourpath, topdown=False):
for name in files:
print(os.path.join(root, name))
stuff
for name in dirs:
print(os.path.join(root, name))
stuff
You can actually just use os module to do both:
- list all files in a folder
- sort files by file type, file name etc.
Here’s a simple example:
import os #os module imported here
location = os.getcwd() # get present working directory location here
counter = 0 #keep a count of all files found
csvfiles = [] #list to store all csv files found at location
filebeginwithhello = [] # list to keep all files that begin with 'hello'
otherfiles = [] #list to keep any other file that do not match the criteria
for file in os.listdir(location):
try:
if file.endswith(".csv"):
print "csv file found:t", file
csvfiles.append(str(file))
counter = counter+1
elif file.startswith("hello") and file.endswith(".csv"): #because some files may start with hello and also be a csv file
print "csv file found:t", file
csvfiles.append(str(file))
counter = counter+1
elif file.startswith("hello"):
print "hello files found: t", file
filebeginwithhello.append(file)
counter = counter+1
else:
otherfiles.append(file)
counter = counter+1
except Exception as e:
raise e
print "No files found here!"
print "Total files found:t", counter
Now you have not only listed all the files in a folder but also have them (optionally) sorted by starting name, file type and others. Just now iterate over each list and do your stuff.
I was looking for this answer:
import os,glob
folder_path = '/some/path/to/file'
for filename in glob.glob(os.path.join(folder_path, '*.htm')):
with open(filename, 'r') as f:
text = f.read()
print (filename)
print (len(text))
you can choose as well ‘*.txt’ or other ends of your filename
import pyautogui
import keyboard
import time
import os
import pyperclip
os.chdir("target directory")
# get the current directory
cwd=os.getcwd()
files=[]
for i in os.walk(cwd):
for j in i[2]:
files.append(os.path.abspath(j))
os.startfile("C:Program Files (x86)AdobeAcrobat 11.0AcrobatAcrobat.exe")
time.sleep(1)
for i in files:
print(i)
pyperclip.copy(i)
keyboard.press('ctrl')
keyboard.press_and_release('o')
keyboard.release('ctrl')
time.sleep(1)
keyboard.press('ctrl')
keyboard.press_and_release('v')
keyboard.release('ctrl')
time.sleep(1)
keyboard.press_and_release('enter')
keyboard.press('ctrl')
keyboard.press_and_release('p')
keyboard.release('ctrl')
keyboard.press_and_release('enter')
time.sleep(3)
keyboard.press('ctrl')
keyboard.press_and_release('w')
keyboard.release('ctrl')
pyperclip.copy('')
The code below reads for any text files available in the directory which contains the script we are running. Then it opens every text file and stores the words of the text line into a list. After store the words we print each word line by line
import os, fnmatch
listOfFiles = os.listdir('.')
pattern = "*.txt"
store = []
for entry in listOfFiles:
if fnmatch.fnmatch(entry, pattern):
_fileName = open(entry,"r")
if _fileName.mode == "r":
content = _fileName.read()
contentList = content.split(" ")
for i in contentList:
if i != 'n' and i != "rn":
store.append(i)
for i in store:
print(i)
If you would like to open files in a directory and append them into a list, do this:
mylist=[]
for filename in os.listdir('path/here/'):
with open(os.path.join('path/here/', filename), 'r') as f:
mylist.append(f.read())
you may try another approach of using os.walk and os.path.join which is a little different from the above options:
for root, dirs, files in os.walk(EnterYourPath):
for name in files:
with open(os.path.join(root,name))as f:
text = f.read()
text variable includes all the files in the folder in the directory.
I have a python script parse.py, which in the script open a file, say file1, and then do something maybe print out the total number of characters.
filename = 'file1'
f = open(filename, 'r')
content = f.read()
print filename, len(content)
Right now, I am using stdout to direct the result to my output file – output
python parse.py >> output
However, I don’t want to do this file by file manually, is there a way to take care of every single file automatically? Like
ls | awk '{print}' | python parse.py >> output
Then the problem is how could I read the file name from standardin?
or there are already some built-in functions to do the ls and those kind of work easily?
Thanks!
Os
You can list all files in the current directory using os.listdir
:
import os
for filename in os.listdir(os.getcwd()):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
Glob
Or you can list only some files, depending on the file pattern using the glob
module:
import os, glob
for filename in glob.glob('*.txt'):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
It doesn’t have to be the current directory you can list them in any path you want:
import os, glob
path = '/some/path/to/file'
for filename in glob.glob(os.path.join(path, '*.txt')):
with open(os.path.join(os.getcwd(), filename), 'r') as f: # open in readonly mode
# do your stuff
Pipe
Or you can even use the pipe as you specified using fileinput
import fileinput
for line in fileinput.input():
# do your stuff
And you can then use it with piping:
ls -1 | python parse.py
You should try using os.walk
.
import os
yourpath = 'path'
for root, dirs, files in os.walk(yourpath, topdown=False):
for name in files:
print(os.path.join(root, name))
stuff
for name in dirs:
print(os.path.join(root, name))
stuff
You can actually just use os module to do both:
- list all files in a folder
- sort files by file type, file name etc.
Here’s a simple example:
import os #os module imported here
location = os.getcwd() # get present working directory location here
counter = 0 #keep a count of all files found
csvfiles = [] #list to store all csv files found at location
filebeginwithhello = [] # list to keep all files that begin with 'hello'
otherfiles = [] #list to keep any other file that do not match the criteria
for file in os.listdir(location):
try:
if file.endswith(".csv"):
print "csv file found:t", file
csvfiles.append(str(file))
counter = counter+1
elif file.startswith("hello") and file.endswith(".csv"): #because some files may start with hello and also be a csv file
print "csv file found:t", file
csvfiles.append(str(file))
counter = counter+1
elif file.startswith("hello"):
print "hello files found: t", file
filebeginwithhello.append(file)
counter = counter+1
else:
otherfiles.append(file)
counter = counter+1
except Exception as e:
raise e
print "No files found here!"
print "Total files found:t", counter
Now you have not only listed all the files in a folder but also have them (optionally) sorted by starting name, file type and others. Just now iterate over each list and do your stuff.
I was looking for this answer:
import os,glob
folder_path = '/some/path/to/file'
for filename in glob.glob(os.path.join(folder_path, '*.htm')):
with open(filename, 'r') as f:
text = f.read()
print (filename)
print (len(text))
you can choose as well ‘*.txt’ or other ends of your filename
import pyautogui
import keyboard
import time
import os
import pyperclip
os.chdir("target directory")
# get the current directory
cwd=os.getcwd()
files=[]
for i in os.walk(cwd):
for j in i[2]:
files.append(os.path.abspath(j))
os.startfile("C:Program Files (x86)AdobeAcrobat 11.0AcrobatAcrobat.exe")
time.sleep(1)
for i in files:
print(i)
pyperclip.copy(i)
keyboard.press('ctrl')
keyboard.press_and_release('o')
keyboard.release('ctrl')
time.sleep(1)
keyboard.press('ctrl')
keyboard.press_and_release('v')
keyboard.release('ctrl')
time.sleep(1)
keyboard.press_and_release('enter')
keyboard.press('ctrl')
keyboard.press_and_release('p')
keyboard.release('ctrl')
keyboard.press_and_release('enter')
time.sleep(3)
keyboard.press('ctrl')
keyboard.press_and_release('w')
keyboard.release('ctrl')
pyperclip.copy('')
The code below reads for any text files available in the directory which contains the script we are running. Then it opens every text file and stores the words of the text line into a list. After store the words we print each word line by line
import os, fnmatch
listOfFiles = os.listdir('.')
pattern = "*.txt"
store = []
for entry in listOfFiles:
if fnmatch.fnmatch(entry, pattern):
_fileName = open(entry,"r")
if _fileName.mode == "r":
content = _fileName.read()
contentList = content.split(" ")
for i in contentList:
if i != 'n' and i != "rn":
store.append(i)
for i in store:
print(i)
If you would like to open files in a directory and append them into a list, do this:
mylist=[]
for filename in os.listdir('path/here/'):
with open(os.path.join('path/here/', filename), 'r') as f:
mylist.append(f.read())
you may try another approach of using os.walk and os.path.join which is a little different from the above options:
for root, dirs, files in os.walk(EnterYourPath):
for name in files:
with open(os.path.join(root,name))as f:
text = f.read()
text variable includes all the files in the folder in the directory.