I have a function that checks if the text is in file.txt or not.
The function works like this: If the text is contained in the file, the file is closed. If the text is not contained in the file, it is added.
But it doesn't work.
import urllib2, re
from bs4 import BeautifulSoup as BS
def SaveToFile(fileToSave, textToSave):
datafile = file(fileToSave)
for line in datafile:
if textToSave in line:
datafile.close()
else:
datafile.write(textToSave + '\n')
datafile.close()
urls = ['url1', 'url2'] # i dont want to public the links.
patGetTitle = re.compile(r'<title>(.*)</title>')
for url in urls:
u = urllib2.urlopen(url)
webpage = u.read()
title = re.findall(patGetTitle, webpage)
SaveToFile('articles.txt', title)
# so here. If the title of the website is already in articles.txt
# the function should close the file.
# But if the title is not found in articles.txt the function should add it.
You can change the SaveToFile function like this
Your title is a list and not a string so you should call it like this SaveToFile('articles.txt', title[0]) to get the first element of the list
def SaveToFile(fileToSave, textToSave):
with open(fileToSave, "r+") as datafile:
for line in datafile:
if textToSave in line:
break
else:
datafile.write(textToSave + '\n')
Notes:
Since you very looping over an empty file the loop did not even run once.
i.e.)
for i in []:
print i # This will print nothing since it is iterating over empty list same as yours
You have passed a list and not a string since re.findall returns a list object you have to pass the first element of the list to the function.
I have used for..else here if the loop is not terminated properly the else case will work.
i.e.)
for i in []:
print i
else:
print "Nooooo"
Output:
Nooooo
Just use r+ mode like this:
def SaveToFile(fileToSave, textToSave):
with open(fileToSave, 'r+') as datafile:
if textToSave not in datafile.read():
datafile.write(textToSave + '\n')
About that file mode, from this answer:
``r+'' Open for reading and writing. The stream is positioned at the
beginning of the file.
And re.find_all() always return a list, so if you're trying to write a list instead of string you'll get an error.
So you could use:
def SaveToFile(fileToSave, textToSave):
if len(textToSave) => 1:
textToSave = textToSave[0]
else:
return
with open(fileToSave, 'r+') as datafile:
if textToSave not in datafile.read():
datafile.write(textToSave + '\n')
You should refactor your SaveToFile function to like this.
def SaveToFile(fileToSave, titleList):
with open(fileToSave, 'a+') as f:
data = f.read()
for titleText in titleList:
if titleText not in data:
f.write(titleText + '\n')
f.close()
This function read a content of file (if exist or created if not) and checks whether textToSave is in the file contents. If it found textToSave then, close file otherwise write content to file.
This seems closer to your problem.
This checks if the text in the file:
def is_text_in_file(file_name, text):
with open(file_name) as fobj:
for line in fobj:
if text in line:
return True
return False
This use the function above to check and writes the text to end of the file if it is not in file yet.
def save_to_file(file_name, text):
if not is_text_in_file in (file_name, text):
with open(file_name, 'a') as fobj:
fobj.write(text + '\n')
Related
As the title says, I made a file editing program with python.
Here is the code that I'm have a problem with:
#fileEditing.py
def fileError(file):
raise OSError("file {} does not exist".format(file))
class AccessFile():
def fileExists(self, file):
import os
return bool(os.path.exists(file))
def filecreate(self, file):
if not self.fileExists(file):
with open(file, "w") as f:
f.close()
else: raise OSError("file {} already exists".format(file))
def filedelete(self, file):
import os
if self.fileExists(file):
os.remove(file)
else: fileError(file)
def fileread(self, file):
#check if file exists
if self.fileExists(file):
#detect length of file
with open(file, "r") as f:
line = " "
x = 0
while line != "":
line = f.readline()
x += 1
#piece lines together in a list
filelines = []
with open(file, "r") as f:
for i in range(x - 1):
filelines.append(str(f.readline()))
#return a tuple
return tuple(filelines)
else: fileError(file)
def filewrite(self, file, line, text):
''' BUG: apparently this either overwrites the line its writing or appends
to the line its writing... make up your mind!'''
if self.fileExists(file):
#get file contents
filelines = list(self.fileread(file))
#see if line parameter is out of range or not
try:
filelines[line] = text
except IndexError:
for i in range(line - len(filelines)):
filelines.append("")
filelines.append(str(text) + "\n")
#apply changes
with open(file, "w") as f:
f.write("") #delete contents
with open(file, "w") as f:
for l in filelines:
f.write(l)
else: fileError(file)
def fileoverwrite(self, file, data):
#if there is no file to delete, it will make a new one
try:
self.filedelete(file)
except:
pass
self.filecreate(file)
x = 0
for line in data:
print(line)
self.filewrite(file, x, line)
x += 1
accessfile = AccessFile()
The bug is in the filewrite(self, file, line, text) function. When called, it either writes a new line (which is what I want it to do), appends to the line its supposed to replace, or just doesn't write any lines at all.
Say I want to write a python file with this program:
#pytesting.py
from fileEditing import *
file = "/Users/ashton/Desktop/Atom/Python/FileEditing/FileManager.py"
data = [
"from fileEditing import *",
"",
"class FileEditing():",
" def __init__(options, immutable_files):",
" self.options, self.immutable_files = options, immutable_files",
" ",
" def prompt():",
" ",
"",
"while True:",
" pass"
]
accessfile.fileoverwrite(file, data)
When I run it, it makes a file with accessfile.fileoverwrite(file, data), like its supposed to.
But thats where things get whacky.
(FileManager.py below)
from fileEditing import *
class FileEditing():
def __init__(options, immutable_files): self.options, self.immutable_files = options, immutable_files
def prompt():
while True:
If you know how to fix the filewrite(self, file, line, text), please let me know.
(I use python 2.7 but python 3 is fine)
So this is definitely a Python 3.x solution but you said that it is fine, don't know if it will work in Python 2.x but it is so simple it should:
def file_overwrite(self, file, data):
with open(file, 'w') as file:
file.write('\n'.join(data))
And you seemingly also need to fix that data list because it is missing a few commas. Also the fact that this is all in a class is a bit weird, you do nothing with the instance, they all might as well be separate functions or #classmethods or #staticmethods. Also several things could be improved with your other functions. For example you shouldn't open the file twice and count its lines to read it. Just do file.readlines() at it will return a list of all lines:
def fileread(self, file):
if self.fileExists(file):
with open(file) as file:
return file.readlines()
else:
fileError(file)
Then also import os once at the start of the file, you don't need to import it in every function where you use os, also:
with open(file, "w") as f:
f.close()
f.close() is completely pointless because the context manger closes the file anyways and also there is mode "x" which is specifically made for file creation and will raise an error if the file already exists: https://www.w3schools.com/python/python_file_handling.asp
I am looking to replace one text file with the contents of another if they are not the same.
Whenever I run this script, "['" and "']" are added on to the old_text.txt file, which means it will never match with new_text.txt file.
How do I remove these characters so the .txt files have the exact same contents after running this script?
old_text = open('old_text.txt', 'r+')
new_text = open('new_text.txt', 'r+')
old_text_compare = str(old_text.readlines())
new_text_compare = str(new_text.readlines())
if old_text_compare != new_text_compare:
print("difference")
old_text = open('old_text.txt', 'w')
old_text.write(str(new_text_compare))
else:
print("no difference")
If you want to compare file contents directly, use .read() rather than .readlines()
with open('old_text.txt', 'r+') as f1, open('new_text.txt', 'r+') as f2:
old = f1.read()
new = f2.read()
if old != new:
with open('new_text.txt', 'w') as f1:
f1.write(old)
else:
print("no difference")
You want to compare the list of lines directly, like so:
if old_text.readlines() != new_text.readlines():
...
I have a problem with some of my python code. I want it to open a file, with few lines of text, and add header + footer to each line in that file.
The problem is that 'create_output()' function returns only the first line with additional content. If I switch 'return' to 'print' at the end of this function it properly displays all lines from my file. What could be the reason? I want to understand what am I doing wrong here.
file_path = '/home/user/Desktop/text.txt'
file_path_edited = '/home/user/Desktop/text_new.txt'
header = 'http://'
footer = '.com'
def open_file():
opened_file = open(file_path)
return opened_file
def edit_file():
edited_file = open(file_path_edited, 'w')
return edited_file
def create_output():
for line in open_file():
line = line.strip()
edited_line = header+line+footer
to_file = edit_file()
to_file.writelines(edited_line)
to_file.close()
return edited_line
print (create_output())
OK, I changed it to something like this, now it works fine.
Thanks your feedback, now I know what I'm doing wrong.
file_path = '/home/user/Desktop/text.txt'
file_path_edited = '/home/user/Desktop/text_new.txt'
header = 'http://'
footer = '.com'
def CreateContent():
with open(file_path) as read_file:
with open(file_path_edited, 'w') as write_file:
for line in read_file.readlines():
new_line = "{}{}{}".format(header, line.strip(), footer)
print(new_line)
write_file.write("{}\n".format(new_line))
CreateContent()
You get only one line, because you reopen the write-file all the time instead of letting it open, "w" will truncate the file on open - so last line lives, rest is useless IO. Also you never close your reader afaics.
open(filename, mode) from https://docs.python.org/2/tutorial/inputoutput.html#reading-and-writing-files:
mode can be 'r' when the file will only be read, 'w' for only writing (an existing file with the same name will be erased), and 'a' opens the file for appending; any data written to the file is automatically added to the end. 'r+' opens the file for both reading and writing. The mode argument is optional; 'r' will be assumed if it’s omitted.
Do not split the file open into extra functions, use with open(...) as bla: bla.write(...) so they get closed as soon as you leave the block or some exception happens.
Use string-formatting - either 'this {} ist repleaced with'.format("something") or the inline variant - see below.
def create_output():
modLines = []
with open('/home/user/Desktop/text.txt',"r") as reader, \
open('/home/user/Desktop/text_new.txt',"w") as writer:
for line in reader:
line = line.strip().rstrip('\n') # rstrip might be better if you only cut \n
modline = f'http://{line}.com' # 3.6 inline string formatting, for 2.7 use
modLines.append(modline) # 'http://{}.com'.format(line)
writer.write(modline+"\n") # write does not autoappend \n
return modlines # return a list of written https...
print (create_output())
Should do the trick.
Links:
Format string syntax
Reading and writing files
You could further improve your code as follows:
file_path = '/home/user/Desktop/text.txt'
file_path_edited = '/home/user/Desktop/text_new.txt'
header = 'http://'
footer = '.com'
def CreateContent():
with open(file_path) as read_file, open(file_path_edited, 'w') as write_file:
for line in read_file:
write_file.write("{}{}{}\n".format(header, line.strip(), footer))
CreateContent()
I created a notepad text document called "connections.txt". I need to have some initial information inside it, several lines of just URLs. Each URL has it's own line. I put that in manually. Then in my program I have a function that checks if a URL is in the file:
def checkfile(string):
datafile = file(f)
for line in datafile:
if string in line:
return True
return False
where f is declared at the beginning of the program:
f = "D:\connections.txt"
Then I tried to write to the document like this:
file = open(f, "w")
if checkfile(user) == False:
usernames.append(user)
file.write("\n")
file.write(user)
file.close()
but it hasn't really been working correctly..I'm not sure what's wrong..am I doing it wrong?
I want the information in the notepad document to stay there ACROSS runs of the program. I want it to build up.
Thanks.
EDIT: I found something wrong... It needs to be file = f, not datafile = file(f)
But the problem is... It clears the text document every time I rerun the program.
f = "D:\connections.txt"
usernames = []
def checkfile(string):
file = f
for line in file:
if string in line:
return True
print "True"
return False
print "False"
file = open(f, "w")
user = "aasdf"
if checkfile(user) == False:
usernames.append(user)
file.write("\n")
file.write(user)
file.close()
I was working with the file command incorrectly...here is the code that works.
f = "D:\connections.txt"
usernames = []
def checkfile(string):
datafile = file(f)
for line in datafile:
if string in line:
print "True"
return True
print "False"
return False
user = "asdf"
if checkfile(user) == False:
usernames.append(user)
with open(f, "a") as myfile:
myfile.write("\n")
myfile.write(user)
The code that checks for a specific URL is ok!
If the problem is not erasing everything:
To write to the document without erasing everything you have to use the .seek() method:
file = open("D:\connections.txt", "w")
# The .seek() method sets the cursor to the wanted position
# seek(offset, [whence]) where:
# offset = 2 is relative to the end of file
# read more here: http://docs.python.org/2/library/stdtypes.html?highlight=seek#file.seek
file.seek(2)
file.write("*The URL you want to write*")
Implemented on your code will be something like:
def checkfile(URL):
# your own function as it is...
if checkfile(URL) == False:
file = open("D:\connections.txt", "w")
file.seek(2)
file.write(URL)
file.close()
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)