I'm searching occurrences of different words in a text file.
I'm not good at python but i did that on google colab.
import os
from google.colab import drive
drive.mount('/content/drive/', force_remount=True)
if not os.path.exists('/content/drive/My Drive/Miserables'):
os.makedirs('/content/drive/My Drive/Miserables')
root_dir = '/content/drive/My Drive/Miserables/'
os.listdir('/content/drive/My Drive/Miserables')
with open("/content/drive/My Drive/Miserables/miserable.txt", 'r') as f:
myString = f.readlines()
print(len(myString))
searchWords = ["example"]
for word in searchWords:
print(f"Word '{word}' appeared {myString.count(word)} time/s.")
The thing is python doesnt actually count the number of words, and i have 0 in results when i know that those words are actually in the text.
Can somebody help me please? Thanks you.
I guess the problem is that you use f.readlines() to get the file content.
This function returns a list of every line in the file.
e.g.
["foo foo faa", "faa foo faa"]
This means youre searching for the word in this list.
Try f.read() instead.
f.readlines() gives you the list with every element representing the line.
For ex. if the text is:
I'm here
this is here too
Bye buddy
will give you the list:
[
"I'm here",
"this is here too",
"Bye buddy"
]
To solve it either use f.read() instead of f.readlines()
import os
from google.colab import drive
drive.mount('/content/drive/', force_remount=True)
if not os.path.exists('/content/drive/My Drive/Miserables'):
os.makedirs('/content/drive/My Drive/Miserables')
root_dir = '/content/drive/My Drive/Miserables/'
os.listdir('/content/drive/My Drive/Miserables')
with open("/content/drive/My Drive/Miserables/miserable.txt", 'r') as f:
myString = f.read()
print(len(myString))
searchWords = ["example"]
for word in searchWords:
print(f"Word '{word}' appeared {myString.count(word)} time/s.")
Or
Loop it:
import os
from google.colab import drive
drive.mount('/content/drive/', force_remount=True)
if not os.path.exists('/content/drive/My Drive/Miserables'):
os.makedirs('/content/drive/My Drive/Miserables')
root_dir = '/content/drive/My Drive/Miserables/'
os.listdir('/content/drive/My Drive/Miserables')
with open("/content/drive/My Drive/Miserables/miserable.txt", 'r') as f:
myString = f.readlines()
print(len(myString))
searchWords = "example"
count = 0
for i in myString:
count += i.count(searchWords)
print(f"Word '{word}' appeared {count} time/s.")
I have a text file which contains list of urls which looks like as follows:
https://www.ebay.com/itm/Egyptian-Comfort-1800-Count-4-Piece-Bed-Sheet-Set-Deep-Pocket-Bed-Sheets/142436469971?epid=1760442729&hash=item2129e00cd3%3Ag%3A7gIAAOSw3YBdRVJd&_trkparms=%2526rpp_cid%253D601435485fceeb223c6f4511&var=442541824291
Here i only want to print epid=1760442729 while reading the text file.
I have tried:
result = []`
with open('deals.txt', 'r') as f:
for line in f:
if line.startswith('?epid='):
break
result.append(line)
print(result[0].split('epid='))
But i am not getting as expected result.
Any help or suggestions will be helpful for me.
Thanks in advance
import re
s = """https://www.ebay.com/itm/Egyptian-Comfort-1800-Count-4-Piece-Bed-Sheet-Set-Deep-Pocket-Bed-Sheets/142436469971?epid=1760442729&hash=item2129e00cd3%3Ag%3A7gIAAOSw3YBdRVJd&_trkparms=%2526rpp_cid%253D601435485fceeb223c6f4511&var=442541824291
https://www.ebay.com/itm/Egyptian-Comfort-1800-Count-4-Piece-Bed-Sheet-Set-Deep-Pocket-Bed-Sheets/142436469971?epid=172442729&hash=item2129e00cd3%3Ag%3A7gIAAOSw3YBdRVJd&_trkparms=%2526rpp_cid%253D601435485fceeb223c6f4511&var=442541824291"""
for i in re.findall(r'epid=(\d+)&', s, re.MULTILINE):
print(f'epid = {i}')
epid = 1760442729
epid = 172442729
I would do it with a substring if the same structure is always used
result = []
with open('deals.txt', 'r') as f:
for line in f:
a= line.find('epid=')
b= line.find('&hash=')
print(line[a:b])
result.append(line)
Use the library that was designed to parse URL.
Example:
from urllib.parse import urlparse, parse_qs
URL='https://www.ebay.com/itm/Egyptian-Comfort-1800-Count-4-Piece-Bed-Sheet-Set-Deep-Pocket-Bed-Sheets/142436469971?epid=1760442729&hash=item2129e00cd3%3Ag%3A7gIAAOSw3YBdRVJd&_trkparms=%2526rpp_cid%253D601435485fceeb223c6f4511&var=442541824291'
url_component = urlparse(URL)
query_component = parse_qs(url_component.query)
epid_data = query_component['epid'][0]
print(f'epid = {epid_data}')
I have a file "BatchLink.txt" which contains urls in new lines.I want to read these lines by lines and pass the argument linewise to a batch script.
Let's say, my batchlink.txt contains this data :-
http://link1
http://link2
http://link3
http://link4
Now, I want to read linewise and send this to a batch file one line at a time.This question is the continuation of my previous question Here.
Right Now, I have this code :-
import requests
from bs4 import BeautifulSoup
import subprocess
file = open("BatchLinks.txt", "w")
r = requests.get('http://www.crunchyroll.com/i-cant-understand-what-my-husband-is-saying')
soup = BeautifulSoup(r.text)
print soup.title
subtitles = soup.findAll('div',{'class':'wrapper container-shadow hover-classes'})
for episode in subtitles:
x = episode.find_all('a')
for a in x:
#print a['href']
z = a['href']
l = 'http://www.crunchyroll.com'+ z
print l
file.write(l+'\n')
print '-----------------------------------------------------------------------------'
file.close()
file = open('BatchLinks.txt', "r")
lines = file.readlines()
print lines
if __name__ =="__main__":
response = lines
print(lines)
p = subprocess.Popen("_start.bat", stdin = subprocess.PIPE)
time.sleep(1)
p.stdin.write(response) #Answer the question
time.sleep(20)
But, right now, the problem is that it reads the lines simultaneosuly and send it to the batch file.Which returns me the output [] . I can't seem to get it work.Any help/guidance would be appreciated.
file = open('BatchLinks.txt', "r")
lines = file.readlines()
Change that to a more up-to-date version:
with open('BatchLinks.txt', "r") as inf:
for line in inf:
do something with line
file = open('BatchLinks.txt', "r")
lines = file.readlines()
Change that to a more up-to-date version:
with open('BatchLinks.txt', "r") as inf:
for line in inf:
do something with line
This is very basic stuff. Use the manual! https://docs.python.org/2/library/stdtypes.html#file-objects
I see two issues: you need to write to the pipe line by line, and need to close the pipe after done.
Replace the following line:
p.stdin.write(response) #Answer the question
with this one:
for line in response:
p.stdin.write(line)
p.stdin.close()
When you do - lines = file.readlines() - it reads all the lines from the file and returns it as a list , so lines is a list of all the lines in the file.
Then you are doing - p.stdin.write(response) - this sends the complete list over to the other process, you should iterate over the lines and send each line to a new process.
Example -
if __name__ =="__main__":
for line in lines:
print(line)
p = subprocess.Popen("_start.bat", stdin = subprocess.PIPE)
time.sleep(1)
p.stdin.write(line.strip())
time.sleep(20)
How do I search and replace text in a file using Python 3?
Here is my code:
import os
import sys
import fileinput
print ("Text to search for:")
textToSearch = input( "> " )
print ("Text to replace it with:")
textToReplace = input( "> " )
print ("File to perform Search-Replace on:")
fileToSearch = input( "> " )
#fileToSearch = 'D:\dummy1.txt'
tempFile = open( fileToSearch, 'r+' )
for line in fileinput.input( fileToSearch ):
if textToSearch in line :
print('Match Found')
else:
print('Match Not Found!!')
tempFile.write( line.replace( textToSearch, textToReplace ) )
tempFile.close()
input( '\n\n Press Enter to exit...' )
Input file:
hi this is abcd hi this is abcd
This is dummy text file.
This is how search and replace works abcd
When I search and replace 'ram' by 'abcd' in above input file, it works as a charm. But when I do it vice-versa i.e. replacing 'abcd' by 'ram', some junk characters are left at the end.
Replacing 'abcd' by 'ram'
hi this is ram hi this is ram
This is dummy text file.
This is how search and replace works rambcd
As pointed out by michaelb958, you cannot replace in place with data of a different length because this will put the rest of the sections out of place. I disagree with the other posters suggesting you read from one file and write to another. Instead, I would read the file into memory, fix the data up, and then write it out to the same file in a separate step.
# Read in the file
with open('file.txt', 'r') as file :
filedata = file.read()
# Replace the target string
filedata = filedata.replace('abcd', 'ram')
# Write the file out again
with open('file.txt', 'w') as file:
file.write(filedata)
Unless you've got a massive file to work with which is too big to load into memory in one go, or you are concerned about potential data loss if the process is interrupted during the second step in which you write data to the file.
fileinput already supports inplace editing. It redirects stdout to the file in this case:
#!/usr/bin/env python3
import fileinput
with fileinput.FileInput(filename, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(text_to_search, replacement_text), end='')
As Jack Aidley had posted and J.F. Sebastian pointed out, this code will not work:
# Read in the file
filedata = None
with file = open('file.txt', 'r') :
filedata = file.read()
# Replace the target string
filedata.replace('ram', 'abcd')
# Write the file out again
with file = open('file.txt', 'w') :
file.write(filedata)`
But this code WILL work (I've tested it):
f = open(filein,'r')
filedata = f.read()
f.close()
newdata = filedata.replace("old data","new data")
f = open(fileout,'w')
f.write(newdata)
f.close()
Using this method, filein and fileout can be the same file, because Python 3.3 will overwrite the file upon opening for write.
You can do the replacement like this
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
for line in f1:
f2.write(line.replace('old_text', 'new_text'))
f1.close()
f2.close()
You can also use pathlib.
from pathlib2 import Path
path = Path(file_to_search)
text = path.read_text()
text = text.replace(text_to_search, replacement_text)
path.write_text(text)
(pip install python-util)
from pyutil import filereplace
filereplace("somefile.txt","abcd","ram")
Will replace all occurences of "abcd" with "ram".
The function also supports regex by specifying regex=True
from pyutil import filereplace
filereplace("somefile.txt","\\w+","ram",regex=True)
Disclaimer: I'm the author (https://github.com/MisterL2/python-util)
Open the file in read mode. Read the file in string format. Replace the text as intended. Close the file. Again open the file in write mode. Finally, write the replaced text to the same file.
try:
with open("file_name", "r+") as text_file:
texts = text_file.read()
texts = texts.replace("to_replace", "replace_string")
with open(file_name, "w") as text_file:
text_file.write(texts)
except FileNotFoundError as f:
print("Could not find the file you are trying to read.")
Late answer, but this is what I use to find and replace inside a text file:
with open("test.txt") as r:
text = r.read().replace("THIS", "THAT")
with open("test.txt", "w") as w:
w.write(text)
DEMO
With a single with block, you can search and replace your text:
with open('file.txt','r+') as f:
filedata = f.read()
filedata = filedata.replace('abc','xyz')
f.truncate(0)
f.write(filedata)
Your problem stems from reading from and writing to the same file. Rather than opening fileToSearch for writing, open an actual temporary file and then after you're done and have closed tempFile, use os.rename to move the new file over fileToSearch.
My variant, one word at a time on the entire file.
I read it into memory.
def replace_word(infile,old_word,new_word):
if not os.path.isfile(infile):
print ("Error on replace_word, not a regular file: "+infile)
sys.exit(1)
f1=open(infile,'r').read()
f2=open(infile,'w')
m=f1.replace(old_word,new_word)
f2.write(m)
Using re.subn it is possible to have more control on the substitution process, such as word splitted over two lines, case-(in)sensitive match. Further, it returns the amount of matches which can be used to avoid waste of resources if the string is not found.
import re
file = # path to file
# they can be also raw string and regex
textToSearch = r'Ha.*O' # here an example with a regex
textToReplace = 'hallo'
# read and replace
with open(file, 'r') as fd:
# sample case-insensitive find-and-replace
text, counter = re.subn(textToSearch, textToReplace, fd.read(), re.I)
# check if there is at least a match
if counter > 0:
# edit the file
with open(file, 'w') as fd:
fd.write(text)
# summary result
print(f'{counter} occurence of "{textToSearch}" were replaced with "{textToReplace}".')
Some regex:
add the re.I flag, short form of re.IGNORECASE, for a case-insensitive match
for multi-line replacement re.subn(r'\n*'.join(textToSearch), textToReplace, fd.read()), depending on the data also '\n{,1}'. Notice that for this case textToSearch must be a pure string, not a regex!
Besides the answers already mentioned, here is an explanation of why you have some random characters at the end:
You are opening the file in r+ mode, not w mode. The key difference is that w mode clears the contents of the file as soon as you open it, whereas r+ doesn't.
This means that if your file content is "123456789" and you write "www" to it, you get "www456789". It overwrites the characters with the new input, but leaves any remaining input untouched.
You can clear a section of the file contents by using truncate(<startPosition>), but you are probably best off saving the updated file content to a string first, then doing truncate(0) and writing it all at once.
Or you can use my library :D
I got the same issue. The problem is that when you load a .txt in a variable you use it like an array of string while it's an array of character.
swapString = []
with open(filepath) as f:
s = f.read()
for each in s:
swapString.append(str(each).replace('this','that'))
s = swapString
print(s)
I tried this and used readlines instead of read
with open('dummy.txt','r') as file:
list = file.readlines()
print(f'before removal {list}')
for i in list[:]:
list.remove(i)
print(f'After removal {list}')
with open('dummy.txt','w+') as f:
for i in list:
f.write(i)
you can use sed or awk or grep in python (with some restrictions). Here is a very simple example. It changes banana to bananatoothpaste in the file. You can edit and use it. ( I tested it worked...note: if you are testing under windows you should install "sed" command and set the path first)
import os
file="a.txt"
oldtext="Banana"
newtext=" BananaToothpaste"
os.system('sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
#print(f'sed -i "s/{oldtext}/{newtext}/g" {file}')
print('This command was applied: sed -i "s/{}/{}/g" {}'.format(oldtext,newtext,file))
if you want to see results on the file directly apply: "type" for windows/ "cat" for linux:
####FOR WINDOWS:
os.popen("type " + file).read()
####FOR LINUX:
os.popen("cat " + file).read()
I have done this:
#!/usr/bin/env python3
import fileinput
import os
Dir = input ("Source directory: ")
os.chdir(Dir)
Filelist = os.listdir()
print('File list: ',Filelist)
NomeFile = input ("Insert file name: ")
CarOr = input ("Text to search: ")
CarNew = input ("New text: ")
with fileinput.FileInput(NomeFile, inplace=True, backup='.bak') as file:
for line in file:
print(line.replace(CarOr, CarNew), end='')
file.close ()
I modified Jayram Singh's post slightly in order to replace every instance of a '!' character to a number which I wanted to increment with each instance. Thought it might be helpful to someone who wanted to modify a character that occurred more than once per line and wanted to iterate. Hope that helps someone. PS- I'm very new at coding so apologies if my post is inappropriate in any way, but this worked for me.
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'w')
n = 1
# if word=='!'replace w/ [n] & increment n; else append same word to
# file2
for line in f1:
for word in line:
if word == '!':
f2.write(word.replace('!', f'[{n}]'))
n += 1
else:
f2.write(word)
f1.close()
f2.close()
def word_replace(filename,old,new):
c=0
with open(filename,'r+',encoding ='utf-8') as f:
a=f.read()
b=a.split()
for i in range(0,len(b)):
if b[i]==old:
c=c+1
old=old.center(len(old)+2)
new=new.center(len(new)+2)
d=a.replace(old,new,c)
f.truncate(0)
f.seek(0)
f.write(d)
print('All words have been replaced!!!')
I have worked this out as an exercise of a course: open file, find and replace string and write to a new file.
class Letter:
def __init__(self):
with open("./Input/Names/invited_names.txt", "r") as file:
# read the list of names
list_names = [line.rstrip() for line in file]
with open("./Input/Letters/starting_letter.docx", "r") as f:
# read letter
file_source = f.read()
for name in list_names:
with open(f"./Output/ReadyToSend/LetterTo{name}.docx", "w") as f:
# replace [name] with name of the list in the file
replace_string = file_source.replace('[name]', name)
# write to a new file
f.write(replace_string)
brief = Letter()
Like so:
def find_and_replace(file, word, replacement):
with open(file, 'r+') as f:
text = f.read()
f.write(text.replace(word, replacement))
def findReplace(find, replace):
import os
src = os.path.join(os.getcwd(), os.pardir)
for path, dirs, files in os.walk(os.path.abspath(src)):
for name in files:
if name.endswith('.py'):
filepath = os.path.join(path, name)
with open(filepath) as f:
s = f.read()
s = s.replace(find, replace)
with open(filepath, "w") as f:
f.write(s)