Imagine that another filename in the same directory is inside the txt file we're currently in:
For example, let file A be the following:
B.txt
computer
science
How would it be possible to read the other lines and go into B.txt after we're done reading?
If you want to read first line separately, you can do it with readline(). Loop then proceeds to read the file from the second line to the end of file:
import os
def read_files_to_list(wordlist, file):
with open(file, "r") as f:
newfile = f.readline()
newfile = newfile.strip() # removes \n and whitespaces
if not os.path.exists(newfile):
wordlist.append(newfile)
newfile = None
for line in f:
line_clean = line.strip()
wordlist.append(line_clean)
return wordlist, newfile
next_file = "A.txt"
listofwords = []
while next_file is not None:
listofwords, next_file = read_files_to_list(listofwords, next_file)
Related
I have copied a certain part of a .txt file into a list. I need to go to particular line and paste/append it.
file = open(filepath, 'r')
with open(filepath) as f: # SEARCH IF STAGE1 & STAGE2 EXIST OR NOT
if 'stage1' in f.read():
print("stage 1")
data = file.readlines()[11:26]
print(*data, sep='')
with open(filepath) as f:
srno = f.readlines()[7:8]
print(*srno, sep='')
Now that I've copied lines 11-26 and line 7-8.. I want to paste/append it in the text file above line 5. How would I go about doing that?
I've written this but it only appends it to the end of the text file.
with open(filepath, 'a+') as fa:
fa.writelines(srno)
fa.writelines("M0\n\n")
for i in data:
fa.writelines(i)
file.close()
I want to write what I've copied in 'data' and 'srno' to line 5 in the text file.
I have this content in a dat file I can access easily, it's not at the beggining of the file but in the middle. I insert only the part of the file that I need to modify.
{
....,
",>=,",
",>=,",
.......
}
Instead of a line with ",>=,", I wish I could insert a custom string like for example
"M,<=,5", from python code, as I would have to do this on many files/many times.
I can read the file through this script, but I don't understand how to find the line I want to change in the python code and how to overwrite in it the string of my interest.
prefixed = [filename for filename in os.listdir('.') if filename.startswith("CRY")] #NQ, DIV, ecc..
for i in range(len(prefixed)):
with open(prefixed[i], 'r') as file:
lines = file.readlines()
print(lines)
prefixed = [filename for filename in os.listdir('.') if filename.startswith("CRY")] #NQ, DIV, ecc..
for i in range(len(prefixed)):
# Read lines
file = open(prefixed[i], 'r')
file_content = file.readlines()
file.close()
# Treatment
for pos, line in enumerate(file_content):
if ",>=," in line:
file_content[pos] = line.replace(",>=,", "myCustomString")
# Write lines
file = open(prefixed[i], 'w')
file.writelines(file_content)
file.close()
To modify only the first element:
prefixed = [filename for filename in os.listdir('.') if filename.startswith("CRY")] #NQ, DIV, ecc..
for i in range(len(prefixed)):
# Read lines
file = open(prefixed[i], 'r')
file_content = file.readlines()
file.close()
# Treatment
for pos, line in enumerate(file_content):
if ",>=," in line:
file_content[pos] = line.replace(",>=,", "myCustomString")
# Add break to quit loop after first replacement
break
# Write lines
file = open(prefixed[i], 'w')
file.writelines(file_content)
file.close()
I'm reading the file in my HDFS using Python language.
Each file has a header and I'm trying to merge the files. However, the header in each file also gets merged.
Is there a way to skip the header from second file?
hadoop = sc._jvm.org.apache.hadoop
conf = hadoop.conf.Configuration()
fs = hadoop.fs.FileSystem.get(conf)
src_dir = "/mnt/test/"
out_stream = fs.create(hadoop.fs.Path(dst_file), overwrite)
files = []
for f in fs.listStatus(hadoop.fs.Path(src_dir)):
if f.isFile():
files.append(f.getPath())
for file in files:
in_stream = fs.open(file)
hadoop.io.IOUtils.copyBytes(in_stream, out_stream, conf, False)
Currently I have solved the problem with below logic, however would like to know if there is any better and efficient solution? appreciate your help
for idx,file in enumerate(files):
if debug:
print("Appending file {} into {}".format(file, dst_file))
# remove header from the second file
if idx>0:
file_str = ""
with open('/'+str(file).replace(':',''),'r+') as f:
for idx,line in enumerate(f):
if idx>0:
file_str = file_str + line
with open('/'+str(file).replace(':',''), "w+") as f:
f.write(file_str)
in_stream = fs.open(file) # InputStream object and copy the stream
try:
hadoop.io.IOUtils.copyBytes(in_stream, out_stream, conf, False) # False means don't close out_stream
finally:
in_stream.close()
What you are doing now is appending repeatedly to a string. This is a fairly slow process. Why not write directly to the output file as you are reading?
for file_idx, file in enumerate(files):
with open(...) as out_f, open(...) as in_f:
for line_num, line in enumerate(in_f):
if file_idx == 0 or line_num > 0:
f_out.write(line)
If you can load the file all at once, you can also skip the first line by using readline followed by readlines:
for file_idx, file in enumerate(files):
with open(...) as out_f, open(...) as in_f:
if file_idx != 0:
f_in.readline()
f_out.writelines(f_in.readlines())
I would like to read a file line by line but ignore any that contain a colon (:).
I'm currently opening one file, reading it, and trying to print it before eventually put it into a new file.
def shoppinglist():
infile = open('filename.txt')
contents = infile.readline()
output = open('outputfilename.txt', 'w')
while ":" not in contents:
contents = infile.readline()
else:
contentstr = contents.split()
print(contentstr)
output.write(contents)
infile.close()
output.close()
As it is, one line is repeated over and over and over.
Try:
def shoppinglist():
contents = ""
with open('filename.txt', 'r') as infile:
for line in infile.readlines():
if ":" not in line:
contents += line
with open('outputfilename.txt', 'w') as output_file:
output_file.write(contents)
I am very new to programming and the python language.
I know how to open a file in python, but the question is how can I open the file as a parameter of a function?
example:
function(parameter)
Here is how I have written out the code:
def function(file):
with open('file.txt', 'r') as f:
contents = f.readlines()
lines = []
for line in f:
lines.append(line)
print(contents)
You can easily pass the file object.
with open('file.txt', 'r') as f: #open the file
contents = function(f) #put the lines to a variable.
and in your function, return the list of lines
def function(file):
lines = []
for line in f:
lines.append(line)
return lines
Another trick, python file objects actually have a method to read the lines of the file. Like this:
with open('file.txt', 'r') as f: #open the file
contents = f.readlines() #put the lines to a variable (list).
With the second method, readlines is like your function. You don't have to call it again.
Update
Here is how you should write your code:
First method:
def function(file):
lines = []
for line in f:
lines.append(line)
return lines
with open('file.txt', 'r') as f: #open the file
contents = function(f) #put the lines to a variable (list).
print(contents)
Second one:
with open('file.txt', 'r') as f: #open the file
contents = f.readlines() #put the lines to a variable (list).
print(contents)
Hope this helps!
Python allows to put multiple open() statements in a single with. You comma-separate them. Your code would then be:
def filter(txt, oldfile, newfile):
'''\
Read a list of names from a file line by line into an output file.
If a line begins with a particular name, insert a string of text
after the name before appending the line to the output file.
'''
with open(newfile, 'w') as outfile, open(oldfile, 'r', encoding='utf-8') as infile:
for line in infile:
if line.startswith(txt):
line = line[0:len(txt)] + ' - Truly a great person!\n'
outfile.write(line)
# input the name you want to check against
text = input('Please enter the name of a great person: ')
letsgo = filter(text,'Spanish', 'Spanish2')
And no, you don't gain anything by putting an explicit return at the end of your function. You can use return to exit early, but you had it at the end, and the function will exit without it. (Of course with functions that return a value, you use the return to specify the value to return.)
def fun(file):
contents = None
with open(file, 'r') as fp:
contents = fp.readlines()
## if you want to eliminate all blank lines uncomment the next line
#contents = [line for line in ''.join(contents).splitlines() if line]
return contents
print fun('test_file.txt')
or you can even modify this, such a way it takes file object as a function arguement as well
Here's a much simpler way of opening a file without defining your own function in Python 3.4:
var=open("A_blank_text_document_you_created","type_of_file")
var.write("what you want to write")
print (var.read()) #this outputs the file contents
var.close() #closing the file
Here are the types of files:
"r": just to read a file
"w": just to write a file
"r+": a special type which allows both reading and writing of the file
For more information see this cheatsheet.
def main():
file=open("chirag.txt","r")
for n in file:
print (n.strip("t"))
file.close()
if __name__== "__main__":
main()
the other method is
with open("chirag.txt","r") as f:
for n in f:
print(n)