Develop Reference

Unable to download all documents from eml file

I have a .eml file with 3 attachments in it. I was able to download one of the attachment but unable to download all the attachments.
import os
import email
import base64
# Get list of all files
files = [f for f in os.listdir('.') if os.path.isfile(f)]
# Create output directory
if os.path.exists("output"):
pass
else:
os.makedirs("output")
for eml_file in files:
if eml_file.endswith(".eml"):
with open(eml_file) as f:
email = f.read()
ext=".docx"
if ext is not "":
# Extract the base64 encoding part of the eml file
encoding = email.split(ext+'"')[-1]
if encoding:
# Remove all whitespaces
encoding = "".join(encoding.strip().split())
encoding = encoding.split("=", 1)[0]
# Convert base64 to string
if len(encoding) % 4 != 0: #check if multiple of 4
while len(encoding) % 4 != 0:
encoding = encoding + "="
try:
decoded = base64.b64decode(encoding)
except:
print(encoding)
for i in range(100):
print('\n')
# Save it as docx
path = os.path.splitext(eml_file)[0]
if path:
path = os.path.join("output", path + ext)
try:
os.remove(path)
except OSError:
pass
with open(path, "wb") as f:
f.write(decoded)
else:
print("File not done: " + eml_file)
How can I download all the attachments?
edit: I have initialized the eml_file still not downloading all files.

You import the email module. So why do you ignore it and try to write an email parser yourself? In addition:
You can use glob to list all files with a given extension.
Use should have used not operator in the condition: (if not os.path.exists("output"): os.makedirs("output")), but even this is not necessary, because makedirs has exist_ok parameter.
import os
import glob
import email
from email import policy
indir = '.'
outdir = os.path.join(indir, 'output')
os.makedirs(outdir, exist_ok=True)
files = glob.glob(os.path.join(indir, '*.eml'))
for eml_file in files:
# This will not work in Python 2
msg = email.message_from_file(open(eml_file), policy=policy.default)
for att in msg.iter_attachments():
# Tabs may be added for indentation and not stripped automatically
filename = att.get_filename().replace('\t', '')
# Here we suppose for simplicity sake that each attachment has a valid unique filename,
# which, generally speaking, is not true.
with open(os.path.join(outdir, filename), 'wb') as f:
f.write(att.get_content())

Compare dictionary values

As part of a wider project (to learn) I am building a script to discover discovering the files recursively in a folder. Then adding the filename (including the path) and the size in bytes to a CSV file.
I've then loaded that CSV file as a python dictionary.
What I would like to do now, is have python parse over each value in the dictionary (which is the size) and compare it to all others in the dictionary. If it finds a match, I want it to show me which keys (file name) have the matching values. I'll then do an MD5 hash on those that appear to have the same size.
The code below is as far as I've got - can anyone assist please?
#!/usr/bin/env python3
import argparse
import os
import sys
import csv
import fnmatch
def verify_args():
parser = argparse.ArgumentParser(description='Compare files recursively.')
parser.add_argument('path', help='Location to begin file comparison from.')
check = parser.parse_args()
if os.path.isdir(check.path):
print(check.path,'is a valid path - continuing' + '\n')
else:
print(check.path,'is an invalid path - exiting' + '\n')
sys.exit()
return parser.parse_args()
def listfiles(file_path):
print ('Starting comparison')
pattern = '*'
with open('/tmp/foo','w') as fo:
fo.write('file,size' + '\n')
for root, dirs, files in os.walk(file_path):
for filename in fnmatch.filter(files, pattern):
fo.write(os.path.join(root, filename) + ',' + str(os.path.getsize(os.path.join(root, filename))) + '\n')
files = {}
with open('/tmp/foo') as csvfile:
reader = csv.DictReader(csvfile)
for row in reader:
files[row['file']] = row['size']
x = files.keys()
print(x)
# Not sure now what to do
def main():
args = verify_args()
file_path = args.path
listfiles(file_path)
if __name__ == '__main__':
main()

How do I apply my python code to all of the files in a folder at once, and how do I create a new name for each subsequent output file?

The code I am working with takes in a .pdf file, and outputs a .txt file. My question is, how do I create a loop (probably a for loop) which runs the code over and over again on all files in a folder which end in ".pdf"? Furthermore, how do I change the output each time the loop runs so that I can write a new file each time, that has the same name as the input file (ie. 1_pet.pdf > 1_pet.txt, 2_pet.pdf > 2_pet.txt, etc.)
Here is the code so far:
path="2_pet.pdf"
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()

The following script solve your problem:
import os
sourcedir = 'pdfdir'
dl = os.listdir('pdfdir')
for f in dl:
fs = f.split(".")
if fs[1] == "pdf":
path_in = os.path.join(dl,f)
content = getPDFContent(path_in)
encoded = content.encode("utf-8")
path_out = os.path.join(dl,fs[0] + ".txt")
text_file = open(path_out, 'w')
text_file.write(encoded)
text_file.close()

Create a function that encapsulates what you want to do to each file.
import os.path
def parse_pdf(filename):
"Parse a pdf into text"
content = getPDFContent(filename)
encoded = content.encode("utf-8")
## split of the pdf extension to add .txt instead.
(root, _) = os.path.splitext(filename)
text_file = open(root + ".txt", "w")
text_file.write(encoded)
text_file.close()
Then apply this function to a list of filenames, like so:
for f in files:
parse_pdf(f)

One way to operate on all PDF files in a directory is to invoke glob.glob() and iterate over the results:
import glob
for path in glob.glob('*.pdf')
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()
Another way is to allow the user to specify the files:
import sys
for path in sys.argv[1:]:
...
Then the user runs your script like python foo.py *.pdf.

You could use a recursive function to search the folders and all subfolders for files that end with pdf. Than take those files and then create a text file for it.
It could be something like:
import os
def convert_PDF(path, func):
d = os.path.basename(path)
if os.path.isdir(path):
[convert_PDF(os.path.join(path,x), func) for x in os.listdir(path)]
elif d[-4:] == '.pdf':
funct(path)
# based entirely on your example code
def convert_to_txt(path):
content = getPDFContent(path)
encoded = content.encode("utf-8")
file_path = os.path.dirname(path)
# replace pdf with txt extension
file_name = os.path.basename(path)[:-4]+'.txt'
text_file = open(file_path +'/'+file_name, "w")
text_file.write(encoded)
text_file.close()
convert_PDF('path/to/files', convert_to_txt)
Because the actual operation is changeable, you can replace the function with whatever operation you need to perform (like using a different library, converting to a different type, etc.)

I have a ".txt "file which consists of various filenames and I want to search each filename in a folder where these files are actually kept

Suppose I have a text file aiq_hits.txt.
Each line in this file corresponds a filename
ant1.aiq
ant2.aiq
ant3.aiq
ant4.aiq
I want to match each line of my textfile (ant1.aiq,ant2.aiq and so on) with filenames which are present at some specific place(R:\Sample) and extract matching files into some other place (R:\sample\wsa).
I have an idea that I need to use functions like os.walk() and fnmatch.fnmatch(), shutil.copy() but I am not able to implement them
My code:
import os
import shutil
import fnmatch
with open("aiq_hits.txt","r") as in_file:
for line in in_file:
I am stuck here

import os
import shutil
sourceDir = "R:\\Sample"
targetDir = "R:\\Sample\\wsa"
existingFiles = set(f for f in os.listdir(sourceDir) if os.path.isfile(os.path.join(sourceDir, f)))
infilepath = "aiq_hits.txt"
with open(infilepath) as infile:
for line in infile:
fname = line.strip()
if fname not in existingFiles: continue
shutil.move(os.path.join(sourceDir, fname), os.path.join(targetDir, fname))

I hope this will suffice:
import os
def match_files(url,file_read, dest):
f = open(file_read, 'rb')
file_list = os.listdir(url)
print(file_list)
saved_path = os.getcwd()
print("Current working directory is " + saved_path)
os.chdir(url)
match = []
for file_name in f:
file_name = file_name.strip()
if file_name in file_list:
match.append(file_name)
os.rename(os.path.join(url, file_name), os.path.join(dest, file_name))
os.chdir(saved_path)
print match
here, url is source directory or folder from which u want to match files, file_read is the name of file (with path) in which list of file names is given, dest is the destination folder.
this code moves the matching files from url to dest, i.e. these files won't remin in url after running the code.

Alternatively you could use the glob module which allows you to enter in a expression for the file name\extension which will then return a list that you can loop over.
I'd use this module if the source directory can have files with the same extension that you want to exclude from being looped over
Also I'm assuming that the file name list is not large and so storing it in a list wont be an issue
eg (I haven't tested the below )
from glob import glob
import os
import shutil
src = 'R:\\Sample'
dst = "R:\\Sample\\wsa"
in_file_list = "aiq_hits.txt"
list_Of_files = glob(os.path.join(src, 'ant*.aiq'))
data = []
with open(in_file_list) as reader:
data += reader.readlines()
for row in list_Of_files:
file_path, file_name = os.path.split(row)
if file_name in data:
shutil.copy2(row, os.path.join(dst, file_name))
# or if you want to move the file
# shutil.move(row, os.path.join(dst, file_name))

Run file inside a zipfile?

Is it possible to run a .html or .exe for example, that is inside a zipfile? I'm using the Zipfile module.
Here's my sample code:
import zipfile
z = zipfile.ZipFile("c:\\test\\test.zip", "r")
x = ""
g = ""
for filename in z.namelist():
#print filename
y = len(filename)
x = str(filename)[y - 5:]
if x == ".html":
g = filename
f = z.open(g)
After f = z.open(g), I don't know what to do next. I tried using the .read() but it only reads whats inside of the html, what I need is for it to run or execute.
Or is there any othere similar ways to do this?

The best approach will be to extract the required file to the Windows temp directory and execute it. I have modified your original code to create a temp file and execute it:
import zipfile
import shutil
import os
z = zipfile.ZipFile("c:\\test\\test.zip", "r")
x = ""
g = ""
basename = ""
for filename in z.namelist():
print filename
y = len(filename)
x = str(filename)[y - 5:]
if x == ".html":
basename = os.path.basename(filename) #get the file name and extension from the return path
g = filename
print basename
break #found what was needed, no need to run the loop again
f = z.open(g)
temp = os.path.join(os.environ['temp'], basename) #create temp file name
tempfile = open(temp, "wb")
shutil.copyfileobj(f, tempfile) #copy unzipped file to Windows 'temp' folder
tempfile.close()
f.close()
os.system(temp) #run the file

Run the first .html file in a zip archive specified at the command line:
#!/usr/bin/env python
import os
import shutil
import sys
import tempfile
import webbrowser
import zipfile
from subprocess import check_call
from threading import Timer
with zipfile.ZipFile(sys.argv[1], 'r') as z:
# find the first html file in the archive
member = next(m for m in z.infolist() if m.filename.endswith('.html'))
# create temporary directory to extract the file to
tmpdir = tempfile.mkdtemp()
# remove tmpdir in 5 minutes
t = Timer(300, shutil.rmtree, args=[tmpdir], kwargs=dict(ignore_errors=True))
t.start()
# extract the file
z.extract(member, path=tmpdir)
filename = os.path.join(tmpdir, member.filename)
# run the file
if filename.endswith('.exe'):
check_call([filename]) # run as a program; wait it to complete
else: # open document using default browser
webbrowser.open_new_tab(filename) #NOTE: returns immediately
Example
T:\> open-from-zip.py file.zip
As an alternative to webbrowser you could use os.startfile(os.path.normpath(filename)) on Windows.