Develop Reference

python slice a string and use .find to get last three letters to determine the type of file

what i am asking is how can i correct my if statement, essentially i have a file attachment called 'fileName' and i am trying to get the last 3 letters from that file to determine if that type of file is in my config (csv, txt).
valid_filename = myconfig file (csv, txt)
def load_file():
try:
# get file from read email and assign a directory path (attachments/file)
for fileName in os.listdir(config['files']['folder_path']):
# validate the file extension per config
# if valid_filename: else send email failure
valid_filename = config['valid_files']['valid']
if fileName[-3:].find(valid_filename):
file_path = os.path.join(config['files']['folder_path'], fileName)
# open file path and read it as csv file using csv.reader
with open(file_path, "r") as csv_file:
csvReader = csv.reader(csv_file, delimiter=',')
first_row = True
let me know if i can clarify anything better

Try pathlib, for example
Assuming the config file is in the form:
[valid_files]
valid = .csv, .txt
[files]
forder_path = .
# other imports
import pathlib
def load_file():
valid_suffixes = [e.strip() for e in config['valid_files']['valid'].split(",")]
folder_path = config['files']['folder_path']
for fileName in os.listdir(folder_path):
if pathlib.Path(filename).suffix in valid_suffixes:
file_path = os.path.join(folder_path, fileName)
with open(file_path, "r") as csv_file:
...

find() method returns -1 if the string you're searching for is not found. To check if the element exists in the string, check if find returns -1.

Iterating Over List of Parsed Files Python

This program scans through a log file and finds faults and timestamps for the faults. The problem I am having with my program is finding a way to modify my program so that it can iterate over multiple files given via the command line and wildcard. In the state the code is now, it can accept a single file and build the dictionary with my my desired info successfully. I have been struggling finding a way to perform this with multiple files simultaneously. The goal is to able to enter into the command line the filename with a wildcard to parse files associated. For example on the command line after the executable I would enter, -f filename.*txt**. However, I cannot find a way to parse multiple files through my fault finder. I have been successful in parsing multiple files and proved it by printing out the list of files parsed. But when it comes to using multiple files and building the dictionary, I am stumped. I would like to use my program and have the same result as it would when parsing a singular file.
import sys
import argparse
_TIME_STAMP_LENGTH = 16
_FAULT_STRING_HEADER_LENGTH = 15
class FaultList():
fault_dict = {}
fault_dict_counter = {}
def __init__(self, file):
self.file = file
self.find_faults()
print self.fault_dict
def find_faults(self):
with open(self.file) as f:
for line in f.readlines():
fault_index = line.find("Fault Cache id")
if(fault_index != -1):
time_stamp = line[:_TIME_STAMP_LENGTH]
fault_data = line[fault_index+_FAULT_STRING_HEADER_LENGTH:-11][:-1] #need the [:-1] to remove new line from string
self.handle_new_fault_found(fault_data, time_stamp)
def handle_new_fault_found(self, fault, time_stamp):
try:
self.fault_dict[fault] = [fault]
self.fault_dict[fault].append(int(time_stamp))
self.fault_dict_counter[0] += 1
except KeyError:
self.fault_dict_counter[fault] = [1, [time_stamp]]
def main(file_names):
parser = argparse.ArgumentParser()
parser.add_argument("-f", "--file", dest="file_names",
help="The binary file to be writen to flash")
args = parser.parse_args()
fault_finder = FaultList(args.file_names)
args = parser.parse_args()
if __name__ == '__main__':
main(sys.argv[1:])
Here is the output of dictionary when parsing a singular file
{'fault_01_17_00 Type:Warning': ['fault_01_17_00 Type:Warning', 37993146319], 'fault_0E_00_00 Type:Warning': ['fault_0E_00_00 Type:Warning', 38304267561], 'fault_05_01_00 Typ': ['fault_05_01_00 Typ', 38500887160]}

You can use the os module for listing files.
import os
# finds all files in a directory
files = [file for file in os.listdir('path of the files') if os.path.isfile(file)]
# filter them looking for files that end with 'txt'
txt_files = [file for file in files if file.endswith('txt')]

delete a user defined text from a text file in python

def Delete_con():
contact_to_delete= input("choose name to delete from contact")
to_Delete=list(contact_to_delete)
with open("phonebook1.txt", "r+") as file:
content = file.read()
for line in content:
if not any(line in line for line in to_Delete):
content.write(line)
I get zero error. but the line is not deleted. This function ask the user what name he or she wants to delete from the text file.

This should help.
def Delete_con():
contact_to_delete= input("choose name to delete from contact")
contact_to_delete = contact_to_delete.lower() #Convert input to lower case
with open("phonebook1.txt", "r") as file:
content = file.readlines() #Read lines from text
content = [line for line in content if contact_to_delete not in line.lower()] #Check if user input is in line
with open("phonebook1.txt", "w") as file: #Write back content to text
file.writelines(content)

Assuming that:
you want the user to supply just the name, and not the full 'name:number' pair
your phonebook stores one name:number pair per line
I'd do something like this:
import os
from tempfile import NamedTemporaryFile
def delete_contact():
contact_name = input('Choose name to delete: ')
# You probably want to pass path in as an argument
path = 'phonebook1.txt'
base_dir = os.path.dirname(path)
with open(path) as phonebook, \
NamedTemporaryFile(mode='w+', dir=base_dir, delete=False) as tmp:
for line in phonebook:
# rsplit instead of split supports names containing ':'
# if numbers can also contain ':' you need something smarter
name, number = line.rsplit(':', 1)
if name != contact_name:
tmp.write(line)
os.replace(tmp.name, path)
Using a tempfile like this means that if something goes wrong while processing the file you aren't left with a half-written phonebook, you'll still have the original file unchanged. You're also not reading the entire file into memory with this approach.
os.replace() is Python 3.3+ only, if you're using something older you can use os.rename() as long as you're not using Windows.
Here's the tempfile documentation. In this case, you can think of NamedTemporaryFile(mode='w+', dir=base_dir, delete=False) as something like open('tmpfile.txt', mode='w+'). NamedTemporaryFile saves you from having to find a unique name for your tempfile (so that you don't overwrite an existing file). The dir argument creates the tempfile in the same directory as phonebook1.txt which is a good idea because os.replace() can fail when operating across two different filesystems.

Error when trying to read and write multiple files

I modified the code based on the comments from experts in this thread. Now the script reads and writes all the individual files. The script reiterates, highlight and write the output. The current issue is, after highlighting the last instance of the search item, the script removes all the remaining contents after the last search instance in the output of each file.
Here is the modified code:
import os
import sys
import re
source = raw_input("Enter the source files path:")
listfiles = os.listdir(source)
for f in listfiles:
filepath = source+'\\'+f
infile = open(filepath, 'r+')
source_content = infile.read()
color = ('red')
regex = re.compile(r"(\b be \b)|(\b by \b)|(\b user \b)|(\bmay\b)|(\bmight\b)|(\bwill\b)|(\b's\b)|(\bdon't\b)|(\bdoesn't\b)|(\bwon't\b)|(\bsupport\b)|(\bcan't\b)|(\bkill\b)|(\betc\b)|(\b NA \b)|(\bfollow\b)|(\bhang\b)|(\bbelow\b)", re.I)
i = 0; output = ""
for m in regex.finditer(source_content):
output += "".join([source_content[i:m.start()],
"<strong><span style='color:%s'>" % color[0:],
source_content[m.start():m.end()],
"</span></strong>"])
i = m.end()
outfile = open(filepath, 'w+')
outfile.seek(0)
outfile.write(output)
print "\nProcess Completed!\n"
infile.close()
outfile.close()
raw_input()

The error message tells you what the error is:
No such file or directory: 'sample1.html'
Make sure the file exists. Or do a try statement to give it a default behavior.

The reason why you get that error is because the python script doesn't have any knowledge about where the files are located that you want to open.
You have to provide the file path to open it as I have done below. I have simply concatenated the source file path+'\\'+filename and saved the result in a variable named as filepath. Now simply use this variable to open a file in open().
import os
import sys
source = raw_input("Enter the source files path:")
listfiles = os.listdir(source)
for f in listfiles:
filepath = source+'\\'+f # This is the file path
infile = open(filepath, 'r')
Also there are couple of other problems with your code, if you want to open the file for both reading and writing then you have to use r+ mode. More over in case of Windows if you open a file using r+ mode then you may have to use file.seek() before file.write() to avoid an other issue. You can read the reason for using the file.seek() here.

Extract zip to memory, parse contents

I want to read the contents of a zip file into memory rather than extracting them to disc, find a particular file in the archive, open the file and extract a line from it.
Can a StringIO instance be opened and parsed? Suggestions? Thanks in advance.
zfile = ZipFile('name.zip', 'r')
for name in zfile.namelist():
if fnmatch.fnmatch(name, '*_readme.xml'):
name = StringIO.StringIO()
print name # prints StringIO instances
open(name, 'r') # IO Error: No such file or directory...
I found a few similar posts, but none that seem to address this issue: Extracting a zipfile to memory?

IMO just using read is enough:
zfile = ZipFile('name.zip', 'r')
files = []
for name in zfile.namelist():
if fnmatch.fnmatch(name, '*_readme.xml'):
files.append(zfile.read(name))
This will make a list with contents of files that match the pattern.
Test:
You can then parse contents afterwards by iterating through the list:
for file in files:
print(file[0:min(35,len(file))].decode()) # "parsing"
Or better use a functor:
import zipfile as zip
import os
import fnmatch
zip_name = os.sys.argv[1]
zfile = zip.ZipFile(zip_name, 'r')
def parse(contents, member_name = ""):
if len(member_name) > 0:
print( "Parsed `{}`:".format(member_name) )
print(contents[0:min(35, len(contents))].decode()) # "parsing"
for name in zfile.namelist():
if fnmatch.fnmatch(name, '*.cpp'):
parse(zfile.read(name), name)
This way there is no data kept in memory for no reason and memory foot print is smaller. It might be important if the files are big.

Don't overthink it. It Just Works:
import zipfile
# 1) I want to read the contents of a zip file ...
with zipfile.ZipFile('A-Zip-File.zip') as zipper:
# 2) ... find a particular file in the archive, open the file ...
with zipper.open('A-Particular-File.txt') as fp:
# 3) ... and extract a line from it.
first_line = fp.readline()
print first_line

The question you link shows you that you need to read the file. Depending on your use case that may already be enough. In your code you replace the loop variable holding a filename with an empty string buffer. Try something like this:
zfile = ZipFile('name.zip', 'r')
for name in zfile.namelist():
if fnmatch.fnmatch(name, '*_readme.xml'):
ex_file = zfile.open(name) # this is a file like object
content = ex_file.read() # now file-contents are a single string
If you really want a buffer that you can manipulate, then simply instantiate it with the contents:
buf = StringIO(zfile.open(name).read())
You may also want to look at BytesIO and note that there are differences between Python 2 and 3.

Thank you to everyone that contributed solutions. This is what ended up working for me:
zfile = ZipFile('name.zip', 'r')
for name in zfile.namelist():
if fnmatch.fnmatch(name, '*_readme.xml'):
zopen = zfile.open(name)
for line in zopen:
if re.match('(.*)<foo>(.*)</foo>(.*)', line):
print line