Develop Reference

Cannot save modifications made in xlsx file

I read a .xlsx file, update it but Im not able to save it
from xml.dom import minidom as md
[... some code ....]
sheet = workDir + '/xl/worksheets/sheet'
sheet1 = sheet + '1.xml'
importSheet1 = open(sheet1,'r')
whole_file= importSheet1.read()
data_Sheet = md.parseString(whole_file)
[... some code ....]
self.array_mem_name = []
y = 1
x = 5 #first useful row
day = int(day)
found = 0
while x <= len_array_shared:
readrow = data_Sheet.getElementsByTagName('row')[x]
c_data = readrow.getElementsByTagName('c')[0]
c_attrib = c_data.getAttribute('t')
if c_attrib == 's':
vName = c_data.getElementsByTagName('v')[0].firstChild.nodeValue
#if int(vName) != broken:
mem_name = self.array_shared[int(vName)]
if mem_name != '-----':
if mem_name == old:
c_data = readrow.getElementsByTagName('c')[day]
c_attrib = c_data.getAttribute('t')
if (c_attrib == 's'):
v_Attrib = c_data.getElementsByTagName('v')[0].firstChild.nodeValue
if v_Attrib != '':
#loc = self.array_shared[int(v_Attrib)]
index = self.array_shared.index('--')
c_data.getElementsByTagName('v')[0].firstChild.nodeValue = index
with open(sheet1, 'w') as f:
f.write(whole_file)
As you can see I use f.write(whole_file) but whole_file has not the changes made with index.
Checking the debug I see that the new value has been added to the node, but I can't save sheet1 with the modified value

I switched to using openpyxl instead, as was suggested in a comment by Lei Yang. I found that this tool worked better for my jobs. With openpyxl, reading cell values is much easier than with xml.dom.minidom.
My only concern is that openpyxl seems really slower than the dom to load the workbook. Maybe the memory was overloaded. But, I was more interested in using something simpler than this minor performance issue.

Python CSV get particular row data

This is csv file
name,country,code
Georgina,Saint Helena,ET
Brooks,Austria,LR
Rosaline,Peru,DZ
How to get a particular row data without looping the whole csv file?
Looking for following syntax:
If searchName exist in csv, extract the data
searchName = 'Brooks'
with open('name.csv', 'r') as file:
reader = csv.DictReader(file)
for row in reader:
if (row['name']) == searchName :
print(row['name'] + ' >> ' + row['country'])
Thanks
Update panda solution for those who interested
import pandas as pd
df = pd.read_csv('a.csv')
select_row = df.loc[df['name'] == 'Brooks']
if select_row.empty:
print('No records')
else:
print('Print Record')
print(select_row.country)

Get first instance
search_name = 'Brooks'
with open('name.csv', 'r') as file:
output = re.search(f'{search_name}.*', file.read())
row = output.group().split(',')
print(row[0], '>>' ,row[1])
Get all instances
search_name = 'Brooks'
with open('name.csv', 'r') as file:
output = re.findall(f'{search_name}.*', file.read())
for row in output:
items = row.split(',')
print(items[0], '>>' ,items[1])
Using DataFrames
import pandas as pd
search_name = 'Brooks'
df = pd.read_csv('name.csv')
output = df[df.name == search_name].iloc[0]
print(output['name'], '>>', output['country'])

You could try using pandas and make your life easier, try something like this :
import pandas as pd
df = pd.read_csv('name.csv')
if df.iloc[5, 6]:
# execute condition
else
# execute another condition
I have given you an outline,you can try to use this and come up with a solution for your issue.

Although dataframe seems to be the best option, if you treat the csv as a simple text file, This should help you:
searchName = 'Brooks'
with open('name.csv', 'r') as f:
foo = f.read()
items=re.findall(f"{searchName}.*$",foo,re.MULTILINE)
print(items)
Output:
['Brooks,Austria,LR']

Can't figure out how to properly output my data

I'm a relative novice at python but yet, somehow managed to build a scraper for Instagram. I now want to take this one step further and output the 5 most commonly used hashtags from an IG profile into my CSV output file.
Current output:
I've managed to isolate the 5 most commonly used hashtags, but I get this result in my csv:
[('#striveforgreatness', 3), ('#jamesgang', 3), ('#thekidfromakron',
2), ('#togetherwecanchangetheworld', 1), ('#halloweenchronicles', 1)]
Desired output:
What I'm looking to end up with in the end is having 5 columns at the end of my .CSV outputting the X-th most commonly used value.
So something in the lines of this:
I've Googled for a while and managed to isolate them separately, but I always end up with '('#thekidfromakron', 2)' as an output. I seem to be missing some part of the puzzle :(.
Here is what I'm working with at the moment:
import csv
import requests
from bs4 import BeautifulSoup
import json
import re
import time
from collections import Counter
ts = time.gmtime()
def get_csv_header(top_numb):
fieldnames = ['USER','MEDIA COUNT','FOLLOWERCOUNT','TOTAL LIKES','TOTAL COMMENTS','ER','ER IN %', 'BIO', 'ALL CAPTION TEXT','HASHTAGS COUNTED','MOST COMMON HASHTAGS']
return fieldnames
def write_csv_header(filename, headers):
with open(filename, 'w', newline='') as f_out:
writer = csv.DictWriter(f_out, fieldnames=headers)
writer.writeheader()
return
def read_user_name(t_file):
with open(t_file) as f:
user_list = f.read().splitlines()
return user_list
if __name__ == '__main__':
# HERE YOU CAN SPECIFY YOUR USERLIST FILE NAME,
# Which contains a list of usernames's BY DEFAULT <current working directory>/userlist.txt
USER_FILE = 'userlist.txt'
# HERE YOU CAN SPECIFY YOUR DATA FILE NAME, BY DEFAULT (data.csv)', Where your final result stays
DATA_FILE = 'users_with_er.csv'
MAX_POST = 12 # MAX POST
print('Starting the engagement calculations... Please wait until it finishes!')
users = read_user_name(USER_FILE)
""" Writing data to csv file """
csv_headers = get_csv_header(MAX_POST)
write_csv_header(DATA_FILE, csv_headers)
for user in users:
post_info = {'USER': user}
url = 'https://www.instagram.com/' + user + '/'
#for troubleshooting, un-comment the next two lines:
#print(user)
#print(url)
try:
r = requests.get(url)
if r.status_code != 200:
print(timestamp,' user {0} not found or page unavailable! Skipping...'.format(user))
continue
soup = BeautifulSoup(r.content, "html.parser")
scripts = soup.find_all('script', type="text/javascript", text=re.compile('window._sharedData'))
stringified_json = scripts[0].get_text().replace('window._sharedData = ', '')[:-1]
j = json.loads(stringified_json)['entry_data']['ProfilePage'][0]
timestamp = time.strftime("%d-%m-%Y %H:%M:%S", ts)
except ValueError:
print(timestamp,'ValueError for username {0}...Skipping...'.format(user))
continue
except IndexError as error:
# Output expected IndexErrors.
print(timestamp, error)
continue
if j['graphql']['user']['edge_followed_by']['count'] <=0:
print(timestamp,'user {0} has no followers! Skipping...'.format(user))
continue
if j['graphql']['user']['edge_owner_to_timeline_media']['count'] <12:
print(timestamp,'user {0} has less than 12 posts! Skipping...'.format(user))
continue
if j['graphql']['user']['is_private'] is True:
print(timestamp,'user {0} has a private profile! Skipping...'.format(user))
continue
media_count = j['graphql']['user']['edge_owner_to_timeline_media']['count']
accountname = j['graphql']['user']['username']
followercount = j['graphql']['user']['edge_followed_by']['count']
bio = j['graphql']['user']['biography']
i = 0
total_likes = 0
total_comments = 0
all_captiontext = ''
while i <= 11:
total_likes += j['graphql']['user']['edge_owner_to_timeline_media']['edges'][i]['node']['edge_liked_by']['count']
total_comments += j['graphql']['user']['edge_owner_to_timeline_media']['edges'][i]['node']['edge_media_to_comment']['count']
captions = j['graphql']['user']['edge_owner_to_timeline_media']['edges'][i]['node']['edge_media_to_caption']
caption_detail = captions['edges'][0]['node']['text']
all_captiontext += caption_detail
i += 1
engagement_rate_percentage = '{0:.4f}'.format((((total_likes + total_comments) / followercount)/12)*100) + '%'
engagement_rate = (((total_likes + total_comments) / followercount)/12*100)
#isolate and count hashtags
hashtags = re.findall(r'#\w*', all_captiontext)
hashtags_counted = Counter(hashtags)
most_common = hashtags_counted.most_common(5)
with open('users_with_er.csv', 'a', newline='', encoding='utf-8') as data_out:
print(timestamp,'Writing Data for user {0}...'.format(user))
post_info["USER"] = accountname
post_info["FOLLOWERCOUNT"] = followercount
post_info["MEDIA COUNT"] = media_count
post_info["TOTAL LIKES"] = total_likes
post_info["TOTAL COMMENTS"] = total_comments
post_info["ER"] = engagement_rate
post_info["ER IN %"] = engagement_rate_percentage
post_info["BIO"] = bio
post_info["ALL CAPTION TEXT"] = all_captiontext
post_info["HASHTAGS COUNTED"] = hashtags_counted
csv_writer = csv.DictWriter(data_out, fieldnames=csv_headers)
csv_writer.writerow(post_info)
""" Done with the script """
print('ALL DONE !!!! ')
The code that goes before this simply scrapes the webpage, and compiles all the captions from the last 12 posts into "all_captiontext".
Any help to solve this (probably simple) issue would be greatly appreciated as I've been struggling with this for days (again, I'm a noob :') ).

Replace line
post_info["MOST COMMON HASHTAGS"] = most_common
with:
for i, counter_tuple in enumerate(most_common):
tag_name = counter_tuple[0].replace('#','')
label = "Top %d" % (i + 1)
post_info[label] = tag_name
There's also a bit of code missing. For example, your code doesn't include csv_headers variable, which I suppose would be
csv_headers = post_info.keys()
It also seems that you're opening a file to write just one row. I don't think that's intended, so what you would like to do is to collect the results into a list of dictionaries. A cleaner solution would be to use pandas' dataframe, which you can output straight into a csv file.

most_common being the output of the call to hashtags_counted.most_common, I had a look at the doc here: https://docs.python.org/2/library/collections.html#collections.Counter.most_common
Output if formatted the following : [(key, value), (key, value), ...] and ordered in decreasing importance of number of occurences.
Hence, to get only the name and not the number of occurence, you should replace:
post_info["MOST COMMON HASHTAGS"] = most_common
by
post_info["MOST COMMON HASHTAGS"] = [x[0] for x in most_common]
You have a list of tuple. This statement builds on the fly the list of the first element of each tuple, keeping the sorting order.

Txt file to excel conversion in python

I'm trying to convert text file to excel sheet in python. The txt file contains data in the below specified formart
Column names: reg no, zip code, loc id, emp id, lastname, first name. Each record has one or more error numbers. Each record have their column names listed above the values. I would like to create an excel sheet containing reg no, firstname, lastname and errors listed in separate rows for each record.
How can I put the records in excel sheet ? Should I be using regular expressions ? And how can I insert error numbers in different rows for that corresponding record?
Expected output:
Here is the link to the input file:
https://github.com/trEaSRE124/Text_Excel_python/blob/master/new.txt
Any code snippets or suggestions are kindly appreciated.

Here is a draft code. Let me know if any changes needed:
# import pandas as pd
from collections import OrderedDict
from datetime import date
import csv
with open('in.txt') as f:
with open('out.csv', 'wb') as csvfile:
spamwriter = csv.writer(csvfile, delimiter=',', quoting=csv.QUOTE_MINIMAL)
#Remove inital clutter
while("INPUT DATA" not in f.readline()):
continue
header = ["REG NO", "ZIP CODE", "LOC ID", "EMP ID", "LASTNAME", "FIRSTNAME", "ERROR"]; data = list(); errors = list()
spamwriter.writerow(header)
print header
while(True):
line = f.readline()
errors = list()
if("END" in line):
exit()
try:
int(line.split()[0])
data = line.strip().split()
f.readline() # get rid of \n
line = f.readline()
while("ERROR" in line):
errors.append(line.strip())
line = f.readline()
spamwriter.writerow(data + errors)
spamwriter.flush()
except:
continue
# while(True):
# line = f.readline()
Use python-2 to run. The errors are appended as subsequent columns. It's slightly complicated the way you want it. I can fix it if still needed
Output looks like:

You can do this using the openpyxl library which is capable of depositing items directly into a spreadsheet. This code shows how to do that for your particular situation.
NEW_PERSON, ERROR_LINE = 1,2
def Line_items():
with open('katherine.txt') as katherine:
for line in katherine:
line = line.strip()
if not line:
continue
items = line.split()
if items[0].isnumeric():
yield NEW_PERSON, items
elif items[:2] == ['ERROR', 'NUM']:
yield ERROR_LINE, line
else:
continue
from openpyxl import Workbook
wb = Workbook()
ws = wb.active
ws['A2'] = 'REG NO'
ws['B2'] = 'LASTNAME'
ws['C2'] = 'FIRSTNAME'
ws['D2'] = 'ERROR'
row = 2
for kind, data in Line_items():
if kind == NEW_PERSON:
row += 2
ws['A{:d}'.format(row)] = int(data[0])
ws['B{:d}'.format(row)] = data[-2]
ws['C{:d}'.format(row)] = data[-1]
first = True
else:
if first:
first = False
else:
row += 1
ws['D{:d}'.format(row)] = data
wb.save(filename='katherine.xlsx')
This is a screen snapshot of the result.

Edit CSV file in python which reads values from another json file in python

I wanted to edit a csv file which reads the value from one of my another json file in python 2.7
my csv is : a.csv
a,b,c,d
,10,12,14
,11,14,15
my json file is a.json
{"a":20}
i want my where the column 'a' will try to match in json file. if their is a match. it should copy that value from json and paste it to my csv file and the final output of my csv file should be looks like this.
a,b,c,d
20,10,12,14
20,11,14,15
Till now I what I have tried is
fileCSV = open('a.csv', 'a')
fileJSON = open('a.json', 'r')
jsonData = fileJSON.json()
for k in range(jsonData):
for i in csvRow:
for j in jsonData.keys():
if i == j:
if self.count == 0:
self.data = jsonData[j]
self.count = 1
else:
self.data = self.data + "," + jsonData[j]
self.count = 0
fileCSV.write(self.data)
fileCSV.write("\n")
k += 1
fileCSV.close()
print("File created successfully")
I will be really thankful if anyone can help me for this.
please ignore any syntactical and indentation error.
Thank You.

Some basic string parsing will get you here.. I wrote a script which works for the simple scenario which you refer to.
check if this solves your problem:
import json
from collections import OrderedDict
def list_to_csv(listdat):
csv = ""
for val in listdat:
csv = csv+","+str(val)
return csv[1:]
lines = []
csvfile = "csvfile.csv"
outcsvfile = "outcsvfile.csv"
jsonfile = "jsonfile.json"
with open(csvfile, encoding='UTF-8') as a_file:
for line in a_file:
lines.append(line.strip())
columns = lines[0].split(",")
data = lines[1:]
whole_data = []
for row in data:
fields = row.split(",")
i = 0
rowData = OrderedDict()
for column in columns:
rowData[columns[i]] = fields[i]
i += 1
whole_data.append(rowData)
with open(jsonfile) as json_file:
jsondata = json.load(json_file)
keys = list(jsondata.keys())
for key in keys:
value = jsondata[key]
for each_row in whole_data:
each_row[key] = value
with open(outcsvfile, mode='w', encoding='UTF-8') as b_file:
b_file.write(list_to_csv(columns)+'\n')
for row_data in whole_data:
row_list = []
for ecolumn in columns:
row_list.append(row_data.get(ecolumn))
b_file.write(list_to_csv(row_list)+'\n')
CSV output is not written to the source file but to a different file.
The output file is also always truncated and written, hence the 'w' mode.

I would recommend using csv.DictReader and csv.DictWriter classes which will read into and out of python dicts. This would make it easier to modify the dict values that you read in from the JSON file.