Develop Reference

How to extract specific information from a file in python

I have a file with following format:
device={
id=1
tag=10
name=device1
}
device={
id=2
tag=20
name=device2
}
device={
id=3
tag=30
name=device3
}
So let's say I am only interested in device with id=2 and I want to extract its tag number(this is configurable and will be changed from some other code). So I need to extract tag number of the device id 2. How can I do this in python. I have done following:
ID='id=2'
with open("file.txt") as file:
for line in file:
if line.strip() == ID:
#Here I do not know what to write
# to extract 20
Thanks

With re.search function:
import re
with open('file.txt', 'r') as f:
id_num = 'id=2'
tag_num = re.search(r'' + id_num + '\s+tag=([0-9]+)', f.read())
print(tag_num.group(1))
The output:
20
f.read() - reads the file contents (as text)
r'' + id_num + '\s+tag=([0-9]+)' - constructing regex pattern, so it would become id=2\s+tag=([0-9]+) where \s is one or many whitespace characters(including newlines) and ([0-9]+) is the 1st captured group containing tag number
tag_num.group(1) - extracting the value of the 1st captured/parenthesized group 1 from the match object tag_num

You can read the next line using line.readline() try to use this code:
ID='id=2'
with open("file.txt") as file:
while True:
line = file.readline()
if line.strip() == ID:
nextline = file.readline()
result = nextline.strip().split('=')[1]
if line == '':
break

with open("") as file:
#print file.read()
for line in file:
#print line.split()
if line.strip()==ID:
d=file.next() #reads next line
print d.split('=')[1]
break

How to replace a string in a file?

I have 2 numbers in two similar files. There is a new.txt and original.txt. They both have the same string in them except for a number. The new.txt has a string that says boothNumber="3". The original.txt has a string that says boothNumber="1".
I want to be able to read the new.txt, pick the number 3 out of it and replace the number 1 in original.txt.
Any suggestions? Here is what I am trying.
import re # used to replace string
import sys # some of these are use for other code in my program
def readconfig():
with open("new.text") as f:
with open("original.txt", "w") as f1:
for line in f:
match = re.search(r'(?<=boothNumber=")\d+', line)
for line in f1:
pattern = re.search(r'(?<=boothNumber=")\d+', line)
if re.search(pattern, line):
sys.stdout.write(re.sub(pattern, match, line))
When I run this, my original.txt gets completely cleared of any text.
I did a traceback and I get this:
in readconfig
for line in f1:
io.UnsupportedOperationo: not readable
UPDATE
I tried:
def readconfig(original_txt_path="original.txt",
new_txt_path="new.txt"):
with open(new_txt_path) as f:
for line in f:
if not ('boothNumber=') in line:
continue
booth_number = int(line.replace('boothNumber=', ''))
# do we need check if there are more than one 'boothNumber=...' line?
break
with open(original_txt_path) as f1:
modified_lines = [line.startswith('boothNumber=') if not line
else 'boothNumber={}'.format(booth_number)
for line in f1]
with open(original_txt_path, mode='w') as f1:
f1.writelines(modified_lines)
And I get error:
booth_number = int(line.replace('boothNumber=', ''))
ValueError: invalid literal for int() with base 10: '
(workstationID="1" "1" window=1= area="" extra parts of the line here)\n
the "1" after workstationID="1" is where the boothNumber=" " would normally go. When I open up original.txt, I see that it actually did not change anything.
UPDATE 3
Here is my code in full. Note, the file names are changed but I'm still trying to do the same thing. This is another idea or revision I had that is still not working:
import os
import shutil
import fileinput
import re # used to replace string
import sys # prevents extra lines being inputed in config
# example: sys.stdout.write
def convertconfig(pattern):
source = "template.config"
with fileinput.FileInput(source, inplace=True, backup='.bak') as file:
for line in file:
match = r'(?<=boothNumber=")\d+'
sys.stdout.write(re.sub(match, pattern, line))
def readconfig():
source = "bingo.config"
pattern = r'(?<=boothNumber=")\d+' # !!!!!!!!!! This probably needs fixed
with fileinput.FileInput(source, inplace=True, backup='.bak') as file:
for line in file:
if re.search(pattern, line):
fileinput.close()
convertconfig(pattern)
def copyfrom(servername):
source = r'//' + servername + '/c$/remotedirectory'
dest = r"C:/myprogram"
file = "bingo.config"
try:
shutil.copyfile(os.path.join(source, file), os.path.join(dest, file))
except:
print ("Error")
readconfig()
# begin here
os.system('cls' if os.name == 'nt' else 'clear')
array = []
with open("serverlist.txt", "r") as f:
for servername in f:
copyfrom(servername.strip())
bingo.config is my new file
template.config is my original
It's replacing the number in template.config with the literal string "r'(?<=boothNumber=")\d+'"
So template.config ends up looking like
boothNumber="r'(?<=boothNumber=")\d+'"
instead of
boothNumber="2"

To find boothNumber value we can use next regular expression (checked with regex101)
(?<=\sboothNumber=\")(\d+)(?=\")
Something like this should work
import re
import sys # some of these are use for other code in my program
BOOTH_NUMBER_RE = re.compile('(?<=\sboothNumber=\")(\d+)(?=\")')
search_booth_number = BOOTH_NUMBER_RE.search
replace_booth_number = BOOTH_NUMBER_RE.sub
def readconfig(original_txt_path="original.txt",
new_txt_path="new.txt"):
with open(new_txt_path) as f:
for line in f:
search_res = search_booth_number(line)
if search_res is None:
continue
booth_number = int(search_res.group(0))
# do we need check if there are more than one 'boothNumber=...' line?
break
else:
# no 'boothNumber=...' line was found, so next lines will fail,
# maybe we should raise exception like
# raise Exception('no line starting with "boothNumber" was found')
# or assign some default value
# booth_number = -1
# or just return?
return
with open(original_txt_path) as f:
modified_lines = []
for line in f:
search_res = search_booth_number(line)
if search_res is not None:
line = replace_booth_number(str(booth_number), line)
modified_lines.append(line)
with open(original_txt_path, mode='w') as f:
f.writelines(modified_lines)
Test
# Preparation
with open('new.txt', mode='w') as f:
f.write('some\n')
f.write('<jack Fill workstationID="1" boothNumber="56565" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">')
with open('original.txt', mode='w') as f:
f.write('other\n')
f.write('<jack Fill workstationID="1" boothNumber="23" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">')
# Invocation
readconfig()
# Checking output
with open('original.txt') as f:
for line in f:
# stripping newline character
print(line.rstrip('\n'))
gives
other
<jack Fill workstationID="1" boothNumber="56565" window="17" Code="" area="" section="" location="" touchScreen="False" secureWorkstation="false">

python: search file for string

I have tried to create a python function which takes in 2 parameters; a file name and a search string. In this case the file name is the script itself (script.py) and the search string is 'name = "JOHN"'
#!/usr/local/bin/python2.7
import os, sys
#################
# Variable string
name = "JOHN"
#################
# Main function
def search_script_for_string(filename, searchString):
f = open(filename,'r') #open the given filename then
filedata = f.read() #assign it to variable then
f.close() #close the open filename
for lines in filedata: #loop through each line in the filedata variable
if searchString in lines: #if search string is found, then do all of this
print ('Found string: %s') % searchString
return True
else: #if not found, then do all of this
print ('Did not find: %s') % searchString
return False
break
#################
# Pass the file name and the search string parameter to the function
search_script_for_string("test.py","name = \"" + name + "\"")
The problem is that it doesn't return expected results:
$ Did not find: name = "JOHN"
When it meant to say:
$ Found string: name = "JOHN"
If anyone can help correct my understanding of where I'm going wrong here, I'd be massively appreciative. Thanks

f.read() returns the entire contents of the file as a single string. You then iterate over those contents -- but iterating over a string yields only 1 character at a time so there is no way a character will contain the substring you are looking for.
def search_script_for_string(filename, searchString):
with open(filename, 'r') as f:
return searchString in f.read()
should do the trick. Alternatively, if you want to search line-by-line:
def search_script_for_string(filename, searchString):
with open(filename, 'r') as f:
for line in f:
return searchString in line

You are iterating over each character of the file by calling for c in f.read().
Use for line in f and you will indeed iterate over each line.
Also prefer the use of with, this makes your code a lot more robust.
So this would be better:
with open('fileName') as f:
for line in f:
#process

Searching and extracting WH-word from a file line by line with Python and regex

I have a file that has one sentence per line. I am trying to read the file and search if the sentence is a question using regex and extract the wh-word from the sentences and save them back into another file according the order it appeared in the first file.
This is what I have so far..
def whWordExtractor(inputFile):
try:
openFileObject = open(inputFile, "r")
try:
whPattern = re.compile(r'(.*)who|what|how|where|when|why|which|whom|whose(\.*)', re.IGNORECASE)
with openFileObject as infile:
for line in infile:
whWord = whPattern.search(line)
print whWord
# Save the whWord extracted from inputFile into another whWord.txt file
# writeFileObject = open('whWord.txt','a')
# if not whWord:
# writeFileObject.write('None' + '\n')
# else:
# whQuestion = whWord
# writeFileObject.write(whQuestion+ '\n')
finally:
print 'Done. All WH-word extracted.'
openFileObject.close()
except IOError:
pass
The result after running the code above: set([])
Is there something I am doing wrong here? I would be grateful if someone can point it out to me.

Something like this:
def whWordExtractor(inputFile):
try:
with open(inputFile) as f1:
whPattern = re.compile(r'(.*)who|what|how|where|when|why|which|whom|whose(\.*)', re.IGNORECASE)
with open('whWord.txt','a') as f2: #open file only once, to reduce I/O operations
for line in f1:
whWord = whPattern.search(line)
print whWord
if not whWord:
f2.write('None' + '\n')
else:
#As re.search returns a sre.SRE_Match object not string, so you will have to use either
# whWord.group() or better use whPattern.findall(line)
whQuestion = whWord.group()
f2.write(whQuestion+ '\n')
print 'Done. All WH-word extracted.'
except IOError:
pass

Not sure if it's what you're looking for, but you could try something like this:
def whWordExtractor(inputFile):
try:
whPattern = re.compile(r'who|what|how|where|when|why|which|whom|whose', re.IGNORECASE)
with open(inputFile, "r") as infile:
for line in infile:
whMatch = whPattern.search(line)
if whMatch:
whWord = whMatch.group()
print whWord
# save to file
else:
# no match
except IOError:
pass

Change '(.*)who|what|how|where|when|why|which|whom|whose(\.*)' to
".*(?:who|what|how|where|when|why|which|whom|whose).*\."

how to replace (update) text in a file line by line

I am trying to replace text in a text file by reading each line, testing it, then writing if it needs to be updated. I DO NOT want to save as a new file, as my script already backs up the files first and operates on the backups.
Here is what I have so far... I get fpath from os.walk() and I guarantee that the pathmatch var returns correctly:
fpath = os.path.join(thisdir, filename)
with open(fpath, 'r+') as f:
for line in f.readlines():
if '<a href="' in line:
for test in filelist:
pathmatch = file_match(line, test)
if pathmatch is not None:
repstring = filelist[test] + pathmatch
print 'old line:', line
line = line.replace(test, repstring)
print 'new line:', line
f.write(line)
But what ends up happening is that I only get a few lines (updated correctly, mind you, but repeated from earlier in the file) corrected. I think this is a scoping issue, afaict.
*Also: I would like to know how to only replace the text upon the first instance of the match, for ex., I don't want to match the display text, only the underlying href.

First, you want to write the line whether it matches the pattern or not. Otherwise, you're writing out only the matched lines.
Second, between reading the lines and writing the results, you'll need to either truncate the file (can f.seek(0) then f.truncate()), or close the original and reopen. Picking the former, I'd end up with something like:
fpath = os.path.join(thisdir, filename)
with open(fpath, 'r+') as f:
lines = f.readlines()
f.seek(0)
f.truncate()
for line in lines:
if '<a href="' in line:
for test in filelist:
pathmatch = file_match(line, test)
if pathmatch is not None:
repstring = filelist[test] + pathmatch
line = line.replace(test, repstring)
f.write(line)

Open the file for read and copy all of the lines into memory. Close the file.
Apply your transformations on the lines in memory.
Open the file for write and write out all the lines of text in memory.
with open(filename, "r") as f:
lines = (line.rstrip() for line in f)
altered_lines = [some_func(line) if regex.match(line) else line for line in lines]
with open(filename, "w") as f:
f.write('\n'.join(altered_lines) + '\n')

A (relatively) safe way to replace a line in a file.
#!/usr/bin/python
# defensive programming style
# function to replace a line in a file
# and not destroy data in case of error
def replace_line(filepath, oldline, newline ):
"""
replace a line in a temporary file,
then copy it over into the
original file if everything goes well
"""
# quick parameter checks
assert os.exists(filepath) # !
assert ( oldline and str(oldline) ) # is not empty and is a string
assert ( newline and str(newline) )
replaced = False
written = False
try:
with open(filepath, 'r+') as f: # open for read/write -- alias to f
lines = f.readlines() # get all lines in file
if oldline not in lines:
pass # line not found in file, do nothing
else:
tmpfile = NamedTemporaryFile(delete=True) # temp file opened for writing
for line in lines: # process each line
if line == oldline: # find the line we want
tmpfile.write(newline) # replace it
replaced = True
else:
tmpfile.write(oldline) # write old line unchanged
if replaced: # overwrite the original file
f.seek(0) # beginning of file
f.truncate() # empties out original file
for tmplines in tmpfile:
f.write(tmplines) # writes each line to original file
written = True
tmpfile.close() # tmpfile auto deleted
f.close() # we opened it , we close it
except IOError, ioe: # if something bad happened.
printf ("ERROR" , ioe)
f.close()
return False
return replaced and written # replacement happened with no errors = True
(note: this replaces entire lines only , and all of the lines that match in the file)