I am trying to merge all the values into one list when I run my for loop. However I keep getting to separate brackets in one list.
For example, when I run this code:
import glob
import re
#import PyPDF2
folder_path='/Users/my_path/cb_files'
file_pattern = "/*"
folder_contents = glob.glob(folder_path + file_pattern, recursive=True)
#IP Bank
import re
ip = re.compile(r"((?:^|\b)(?:h[tTxX]ps?://)?(?:\d{1,3}\[?\.\]?){3}\d{1,3}(?:\b|$))")
hash_ = re.compile(r"((?:^|\b)[a-fA-F0-9]{32,64}(?:\b|$))")
domain = re.compile(r"((?:^|\b)(?:h[xXtT]{2}ps?:|meows?:)?//(?:[a-zA-Z0-9\u00A0-\uD7FF\uF900-\uFDFC\uFDF0-\uFFEF_.\[\]-]+)(?:\[?\.\]?[a-z]+)+(?::\d+)?(?:[/?][^\s]*)?)")
ip_list=[]
for file in folder_contents:
if re.search(r".*(?=pdf$)",file):
#this is pdf
pdfFileObj = open('pdf.pdf', 'rb')
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
pageObj = pdfReader.getPage(0)
read_file=pageObj.extractText()
elif '.' not in file:
continue
else:
read_file = open(file, 'rt', encoding="latin-1").read()
if ip.findall(read_file) or hash_.findall(read_file) or domain.findall(read_file):
ips =ip.findall(read_file)
hashs= hash_.findall(read_file)
domains=domain.findall(read_file)
# print("IPS",', '.join(ips))
ip_list.append(ips)
print(ip_list)
Here is my output:
[['000.000.0.1', '111.111.1.1'], ['222.222.2.2','333.333.3.3']]
So it looks like for each file it loops over, it is putting it in its own list.
I want the output to look like this:
['000.000.0.1', '111.111.1.1','222.222.2.2','333.333.3.3']
Any changes in my code that will produce these results?
Try changing:-
ip_list.append(ips)
to
ip_list.extend(ips)
Related
My goal is to change multiple csv files in a folder into JSON.
First, I needed to list my csv files
for file in os.listdir("C:/Users/folder_to_csv"):
filename = os.fsdecode(file)
if filename.endswith(".csv"):
#check if csv files are listed correctly
print(os.path.join("C:/Users/folder_to_csv", filename))
With this, I was able to call csv files in that folder.
Result:
C:/Users/folder_to_csv\file_1.csv C:/Users/folder_to_csv\file_2.csv C:/Users/folder_to_csv\file_3.csv
Then, I wanted to use all of the csv files in 'csvlist' to jsonObj, however for some reason, my codes are only using the first file (C:/Users/folder_to_csv\file_1.csv)
This is what I have tried so far:
import json
import csv
import requests
import threading
import os
for file in os.listdir("C:/Users/folder_to_csv"):
filename = os.fsdecode(file)
if filename.endswith(".csv"):
csvlist = os.path.join("C:/Users/folder_to_csv", filename)
data = {}
def main():
#loop csv list so my codes can read all csv files
length = len(csvlist)
for i in range(length):
i += 1
path = csvlist
#switch csv to json
with open(path, mode='r') as f:
reader = csv.DictReader(f)
processdata = [row for row in reader]
dlist = processdata
jsonObj = json.dumps(dlist)
})
print(jsonObj)
main()
In the initial loop, you keep redefining the csvlist variable. I suppose you want it to be a list? Then just create an initial empty list and append to it instead of redefining
csvlist = []
...
csvlist.append(os.path.join("C:/Users/folder_to_csv", filename))
I am trying to count the number of specific words in a given report. Does anyone know why defining a list within the code makes the second part of the following code run faster than reading the list from a file? Is there a solution? The list contains the same words is a lot longer than two words in the following example.
# Example code: Within code list
import csv
import glob
import re
import time
TARGET_FILES = r'C:/Users/s170760/Desktop/Reports_Cleaned/*.*'
OUTPUT_FILE = r'C:/Users/s170760/Desktop/Parser.csv'
OUTPUT_FIELDS = ['file name', 'create']
create = {'agile', 'skills'}
def main():
f_out = open(OUTPUT_FILE, 'w')
wr = csv.writer(f_out, lineterminator='\n')
wr.writerow(OUTPUT_FIELDS)
file_list = glob.glob(TARGET_FILES)
for file in file_list:
print(file)
with open(file, 'r', encoding='UTF-8', errors='ignore') as f_in:
doc = f_in.read()
doc = doc.lower()
output_data = get_data(doc)
output_data[0] = file
wr.writerow(output_data)
def get_data(doc):
_odata = [0] * 2
tokens = re.findall('\w(?:[-\w]*\w)?', doc)
for token in tokens:
if token in create:
_odata[1] += 1
return _odata
Here is the other way:
# Example code: Reading list from a file
import csv
import glob
import re
import time
TARGET_FILES = r'C:/Users/s170760/Desktop/Reports_Cleaned/*.*'
OUTPUT_FILE = r'C:/Users/s170760/Desktop/Parser.csv'
OUTPUT_FIELDS = ['file name', 'create']
create = open('C:/Users/s170760/Desktop/Create.txt', 'r').read().splitlines()
def main():
f_out = open(OUTPUT_FILE, 'w')
wr = csv.writer(f_out, lineterminator='\n')
wr.writerow(OUTPUT_FIELDS)
file_list = glob.glob(TARGET_FILES)
for file in file_list:
print(file)
with open(file, 'r', encoding='UTF-8', errors='ignore') as f_in:
doc = f_in.read()
doc = doc.lower()
output_data = get_data(doc)
output_data[0] = file
wr.writerow(output_data)
def get_data(doc):
_odata = [0] * 2
tokens = re.findall('\w(?:[-\w]*\w)?', doc)
for token in tokens:
if token in create:
_odata[1] += 1
return _odata
As pointed out by Mark in the comments, the first code snippet uses a set of strings, while the second code snippet loads a file into a list of strings.
Why sets are faster than lists in this use case, is well explained in this Stack Overflow answer. Parsing the output of open to a set can indeed solve your problem.
So replace:
create = open('C:/Users/s170760/Desktop/Create.txt', 'r').read().splitlines()
With:
create = set(open('C:/Users/s170760/Desktop/Create.txt', 'r').read().splitlines())
I have the following code:
import os
import json
import ipaddress
iplist = []
ipiflist = []
mydict = {}
for filename in os.listdir('data/'):
with open(os.path.join('data/', filename), 'r') as f:
data = json.load(f)
mydict.update(data)
print(mydict)
In the data directory there are several JSON files that I open in this loop.
I update the dict in every loop and for this reason I get the following output:
{'ipif_1001': '10.10.160.129', 'ipif_1002': '10.10.160.142', 'ipif_1003': '10.10.160.169', 'ipif_1004': '10.10.160.173', 'ipif_3334': '10.10.160.194', 'IpIf3337': '10.10.160.126'}
{'ipif_1001': '10.10.160.129', 'ipif_1002': '10.10.160.142', 'ipif_1003': '10.10.160.170', 'ipif_1004': '10.10.160.174', 'ipif_3334': '10.10.160.194', 'IpIf3337': '10.10.160.126', 'ipif_1005': '10.10.160.178', 'ipif_1006': '10.10.160.182'}
{'ipif_1001': '10.10.160.129', 'ipif_1002': '10.10.160.142', 'ipif_1003': '10.10.160.170', 'ipif_1004': '10.10.160.174', 'ipif_3334': '10.10.160.194', 'IpIf3337': '10.10.160.126', 'ipif_1005': '10.10.160.178', 'ipif_1006': '10.10.160.182', 'IpIf1001': '10.10.160.138', 'IpIf1002': '10.10.160.141', 'IpIf1003': '10.10.160.153', 'IpIf1006': '10.10.160.181', 'IpIf_CPEDCN': '10.10.160.241', 'IpIf_DCNMgt': '10.10.191.253', 'ipif1164': '10.10.160.166', 'IpIf1010': '10.10.170.1'}
I only need the summarized output from the last loop. How can I only access this?
Thanks for your help
The for loop in python has an else statement, which will only be executed when the loop was successful. Thus there you can plot your last resut?
for filename in os.listdir('data/'):
with open(os.path.join('data/', filename), 'r') as f:
data = json.load(f)
mydict.update(data)
else:
print(mydict)
import os
import json
import ipaddress
iplist = []
ipiflist = []
mydict = {}
list = os.listdir('data/')
for filename in os.listdir('data/'):
with open(os.path.join('data/', filename), 'r') as f:
data = json.load(f)
if list[list.count-1] == filename: #check last filename in the directory with the current filename in the loop
mydict.update(data)
print(mydict)
Try it like this
This is my code:
file_input1 = open('Amazon_Indi_Seller.py', 'r')
f1 = file_input1.read().lower()
file_input2 = open('Amazon_Prices.py', 'r')
f2 = file_input2.read().lower()
documents = [f1, f2]
import nltk, string, numpy
stemmer = nltk.stem.porter.PorterStemmer()
lemmer = nltk.stem.WordNetLemmatizer()
def LemTokens(tokens):
return [lemmer.lemmatize(token) for token in tokens]
remove_punct_dict = dict((ord(punct), None) for punct in string.punctuation)
def LemNormalize(text):
return
LemTokens(nltk.word_tokenize(text.lower().translate(remove_punct_dict)))
from sklearn.feature_extraction.text import CountVectorizer
LemVectorizer = CountVectorizer(tokenizer=LemNormalize,
stop_words='english')
LemVectorizer.fit_transform(documents)
Instead of reading 2 files i want to read all the files in a directory. And read them individually so that later I can add those variables in a list named documents.
You can use the code mentioned below,
import os
def read_files(file):
file_input1 = open(file, 'r')
f1 = file_input1.read()
return f1
files = ['sample.py', 'Amazon_Indi_Seller.py']
data = list()
for file in files:
data.append(read_files(file))
print(data)
The above code will used to read the files mentioned in the list
import os
def read_files(file):
file_input1 = open(file, 'r')
f1 = file_input1.read()
return f1
src = r'DIRECTORY PATH'
data = list()
for file in os.listdir(src):
data.append(read_files(file))
print(data)
And the above code will read all the files from the directory mentioned
You could collect all the in a list, for example:
lst = []
for file in os.listdir():
file_input = open(file,"r")
lst.append(file_input.read())
One extra recommendation - in general it might be wise to store the contents of a file as a collection of its lines by for example using file_input.readlines() which returns a list of lines.
Create a list of all filenames and then iterate over filename list and add their content in a dictionary.
from collections import defaultdict #imported default dictionary
result = defaultdict() #created empty default dictionary
filenames = ['name1.py', 'name2.py', 'name3.py'] #added filenames to a list
for name in filenames: #iterate over filename list
with open(name, 'r') as stream: #open each file
data = stream.readlines() #read contents lines by line (readlines return list of lines)
result[name] = data # set name as key and content as value in dictionary
print(result)
In this way you will have a dictionary with keys as filenames and values as their contents
If the directory may include other directories with files, which you want to read to - use os.walk
Here is sample code from the official documentation:
import os
from os.path import join, getsize
for root, dirs, files in os.walk('python/Lib/email'):
print root, "consumes",
print sum(getsize(join(root, name)) for name in files),
print "bytes in", len(files), "non-directory files"
if 'CVS' in dirs:
dirs.remove('CVS') # don't visit CVS directories
I am trying to assign the elements of a list as names for some files that live in a directory, so far I created a function that recover the name of a each file from a directory and returns them in a list:
def retrive(directory_path):
path_names = []
for filename in sorted(glob.glob(os.path.join(directory_path, '*.pdf'))):
retrieved_files = filename.split('/')[-1]
path_names.append(retrieved_files)
print (path_names)
The above function returns in a list the names of each file, then I am writing the files into another directory as follows:
path = os.path.join(new_dir_path, "list%d.txt" % i)
#This is the path of each new file:
#print(path)
with codecs.open(path, "w", encoding='utf8') as filename:
for item in [a_list]:
filename.write(item+"\n")
Finally, my question is: how can I assign as a name of each file, each element of path_names?, something like this line:
path = os.path.join(new_dir_path, "list%d.txt" % i)
I also tried to use the format() function. However I still cant assign the the correct name to each file.
Here's the full script:
def transform_directoy(input_directory, output_directory):
import codecs, glob, os
from tika import parser
all_texts = []
for filename in sorted(glob.glob(os.path.join(input_directory, '*.pdf'))):
parsed = parser.from_file(filename)
texts = parsed['content']
all_texts.append(texts)
for i , a_list in enumerate(all_texts):
new_dir_path = output_directory
#print(new_dir_path)
path = os.path.join(new_dir_path, "list%d.txt" % i)
with codecs.open(path, "w", encoding='utf8') as filename:
for item in [a_list]:
filename.write(item+"\n")
The desired output will consist of the actual names of each processed file.
You’re almost there:
for path_name in path_names:
path = os.path.join(new_dir_path, "list%s.txt" % path_name)
#This is the path of each new file:
#print(path)
with codecs.open(path, "w", encoding='utf8') as f:
for item in [a_list]:
f.write(item+"\n")
Update based on updated code sample. You are using different loops here, and that is not ideal unless you are doing processing in between the two loops. Since I am going to keep that structure, we are going to have to make sure to associate each block of content with the original filename. The best structure for that is a dict, and in case order is important, we use an OrderedDict. Now, when we’re looping over the filename, content pairs in the OrderedDict we’ll want to change the extension of the file to match the new file type. Luckily, python has some nice utilities for file/path manipulation in the os.path module. os.path.basename can be used to strip off the directory from a file and os.path.splitext will strip off an extension from a filename. We use both of those to get just the filename without the extension and then append .txt to designate the new file type. Putting it all together, we get :
def transform_directoy(input_directory, output_directory):
import codecs, glob, os
from collections import OrderedDict
from tika import parser
all_texts = OrderedDict()
for filename in sorted(glob.glob(os.path.join(input_directory, '*.pdf'))):
parsed = parser.from_file(filename)
filename = os.path.basename(filename)
texts = parsed['content']
all_texts[filename] = texts
for i, (original_filename, a_list) in enumerate(all_texts.items()):
new_filename, _ = os.path.splitext(original_filename)
new_filename += '.txt'
new_dir_path = output_directory
#print(new_dir_path)
path = os.path.join(new_dir_path, new_filename)
# Print out the name of the file we are processing
print('Transforming %s => %s' % (original_filename, path,))
with codecs.open(path, "w", encoding='utf8') as filename:
for item in [a_list]:
filename.write(item+"\n")
Second update: OP asked how I would write this code if this was all that there was, so here goes:
# move imports to top of file: PEP 8
import codecs, glob, os
from tika import parser
def transform_directoy(input_directory, output_directory):
for filename in sorted(glob.glob(os.path.join(input_directory, '*.pdf'))):
parsed = parser.from_file(filename)
parsed_content = parsed['content']
original_filename = os.path.basename(filename)
new_filename, _ = os.path.splitext(original_filename)
new_filename += '.txt'
path = os.path.join(output_directory, new_filename)
# Print out the name of the file we are processing
print('Transforming %s => %s' % (original_filename, path,))
# no need for a second loop since we can piggy back off the first loop
with codecs.open(path, "w", encoding='utf8') as filename:
# No need for a for loop here since our list only has one item
filename.write(parsed_content)
filename.write("\n")