.gitignore

@@ -0,0 +1,28 @@
+*.tar.gz
+*.swp
+*.log
+*.textlog
+*.retry
+*.sublime-*
+.vscode
+.idea/
+*.mp4
+**/venv/*
+**/virtualenv/*
+.hypothesis
+.ipynb_checkpoints
+**/build/*
+**/dist/*
+*.spec
+
+# python cache files
+__pycache__/
+.pytest_cache
+
+# Crash log files
+crash.log
+.vault_pass.txt
+.DS_Store
+.htaccess
+htpasswd
+account.json

1.Table Extraction/Extract Tables from PDFs.py

@@ -1,3 +1,4 @@
+#! /usr/bin/env python3
 import camelot
 
 tables = camelot.read_pdf('foo.pdf', pages='1', flavor='lattice')

2.Automate The News/1.news-extract-data.py

@@ -1,14 +1,23 @@
+#!/usr/bin/which python3
+# 1.news-extract-data.py
+# extract information from a site using Xpath's chrome webdriver
+# this will open a browser session on the URL and allow extraction
+
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
 import pandas as pd
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+PATH = os.path.expanduser('~/Downloads/chromedriver')  # introduce path here
+OUT = 'headline.csv'
+WEB = 'https://www.thesun.co.uk/sport/football/'
 
-web = 'https://www.thesun.co.uk/sport/football/'
-path = '/Users/frankandrade/Downloads/chromedriver'  # introduce path here
-
+print('{}--> {}'.format(PROG, WEB), end='', flush=True)
 # Creating the driver
-driver_service = Service(executable_path=path)
+driver_service = Service(executable_path=PATH)
 driver = webdriver.Chrome(service=driver_service)
-driver.get(web)
+driver.get(WEB)
 
 # Finding Elements
 containers = driver.find_elements(by='xpath', value='//div[@class="teaser__copy-container"]')
@@ -23,10 +32,12 @@
     titles.append(title)
     subtitles.append(subtitle)
     links.append(link)
+    print(".", end='', flush=True)
 
 # Exporting data to a CSV file
 my_dict = {'title': titles, 'subtitle': subtitles, 'link': links}
 df_headlines = pd.DataFrame(my_dict)
-df_headlines.to_csv('headline.csv')
-
+df_headlines.to_csv(OUT)
+print("{} {} entries".format(OUT, len(titles)))
 driver.quit()
+exit(0)

2.Automate The News/2.news-headless.py

@@ -1,18 +1,29 @@
+#!/usr/bin/which python3
+# 2.news-headless.py
+# extract information from a site using Xpath's chrome webdriver
+# this will NOT open a browser but extract the pages from the URL anyway
+
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.chrome.service import Service
 import pandas as pd
+import os
+import sys
 
-web = 'https://www.thesun.co.uk/sport/football/'
-path = '/Users/frankandrade/Downloads/chromedriver'  # introduce path here
+WEB = 'https://www.thesun.co.uk/sport/football/'
+PROG = os.path.basename(sys.argv[0])
+DRIVER_PATH = os.path.expanduser('~/Downloads/chromedriver')  # introduce path here
+OUT_FILE = 'headline.csv'
 
+print('{}--> driver.get('.format(PROG), end='', flush=True)
 # add headless mode
 options = Options()
 options.headless = True
-driver_service = Service(executable_path=path)
+driver_service = Service(executable_path=DRIVER_PATH)
 driver = webdriver.Chrome(service=driver_service, options=options)
-driver.get(web)
+driver.get(WEB)
 
+print('{} )'.format(WEB), end='', flush=True)
 containers = driver.find_elements(by='xpath', value='//div[@class="teaser__copy-container"]')
 
 titles = []
@@ -25,9 +36,12 @@
     titles.append(title)
     subtitles.append(subtitle)
     links.append(link)
+    print(".", end='', flush=True)
 
 my_dict = {'title': titles, 'subtitle': subtitles, 'link': links}
 df_headlines = pd.DataFrame(my_dict)
-df_headlines.to_csv('headline-headless.csv')
+df_headlines.to_csv(OUT_FILE)
+print(" {} [{} entries]".format(OUT_FILE, len(titles)))
 
 driver.quit()
+exit(0)

2.Automate The News/3.news-automation.py

@@ -1,3 +1,9 @@
+#!/usr/bin/which python3
+# 3.news-automation.py
+# extract information from a site using Xpath's chrome webdriver
+# this will NOT open a browser but extract the pages from the URL anyway
+# name output file with date, so it can be run via cron regularly
+
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.chrome.service import Service
@@ -6,41 +12,47 @@
 import os
 import sys
 
-# Preparing script before we convert it to executable
-application_path = os.path.dirname(sys.executable)
-
-# get date in format MMDDYYYY
-now = datetime.now()
-month_day_year = now.strftime("%m%d%Y")
+WEB = 'https://www.thesun.co.uk/sport/football/'
+PROG = os.path.basename(sys.argv[0])
+DRIVER_PATH = os.path.expanduser('~/Downloads/chromedriver')
 
-web = 'https://www.thesun.co.uk/sport/football/'
-path = '/Users/frankandrade/Downloads/chromedriver'  # introduce path here
+OUT_FILE = 'football_headlines_{}.csv'.format(datetime.now().strftime("%Y%m%d"))
+"""
+# os.path.join ensures name is not OS dependent (e.g. directory seperator MacOS="/", Win="\")
+# but I don't want the file stored where python is stored so commented out
+"""
+# OUT_FILE = os.path.join(os.path.dirname(sys.executable), OUT_FILE)
 
+print('{}--> driver.web('.format(PROG), end='', flush=True)
 # Headless mode
 options = Options()
 options.headless = True
-driver_service = Service(executable_path=path)
+driver_service = Service(executable_path=DRIVER_PATH)
 driver = webdriver.Chrome(service=driver_service, options=options)
-driver.get(web)
+driver.get(WEB)
 
+print('{}) '.format(WEB), end='', flush=True)
 containers = driver.find_elements(by='xpath', value='//div[@class="teaser__copy-container"]')
 
 titles = []
 subtitles = []
 links = []
+link_count = 0
 for container in containers:
     title = container.find_element(by='xpath', value='./a/h2').text
     subtitle = container.find_element(by='xpath', value='./a/p').text
     link = container.find_element(by='xpath', value='./a').get_attribute('href')
     titles.append(title)
     subtitles.append(subtitle)
     links.append(link)
+    link_count += 1
+    if (link_count % 5) == 0:  # print "+" when count mod 5 = 0
+        print(".", end='', flush=True)
 
 # Exporting data to the same folder where the executable will be located
 my_dict = {'title': titles, 'subtitle': subtitles, 'link': links}
 df_headlines = pd.DataFrame(my_dict)
-file_name = f'football_headlines_{month_day_year}.csv'
-final_path = os.path.join(application_path, file_name)
-df_headlines.to_csv(final_path)
+df_headlines.to_csv(OUT_FILE)
+print(" {} [{} entries]".format(OUT_FILE, len(titles)))
 
 driver.quit()

3.Excel Report/1.make-pivot-table.py

@@ -1,14 +1,30 @@
-import pandas as pd
+#!/usr/bin/which python3
+# 1.make-pivot-table.py
+# read the supermarket sales spreadsheet
+# select 3 columns by Gender, Product, Total Sales
+# create a pivot table using Gender for y-axis showing Product and Total Sales
+# output to excel
 
+import pandas as pd
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+IN_FILE = os.path.expanduser('supermarket_sales.xlsx')
+OUT_FILE = os.path.expanduser('pivot_table.xlsx')
 # Read Excel File
-df = pd.read_excel('supermarket_sales.xlsx')
+df = pd.read_excel(IN_FILE)
+print('{}--> {}'.format(PROG, IN_FILE))  # , end='', flush=True)
 
 # Select columns: 'Gender', 'Product line', 'Total'
 df = df[['Gender', 'Product line', 'Total']]
+print('selecting columns')
+print(df)
 
 # Make pivot table
 pivot_table = df.pivot_table(index='Gender', columns='Product line',
                              values='Total', aggfunc='sum').round(0)
 
-# Export pivot table to Excel file
-pivot_table.to_excel('pivot_table.xlsx', 'Report', startrow=4)
+# Export table to Excel file w/ sheet='Report' starting at row 4
+pivot_table.to_excel(OUT_FILE, 'Report', startrow=4)
+print(pivot_table)
+print(' -->{}'.format(OUT_FILE))

3.Excel Report/2.add-charts.py

@@ -1,40 +1,80 @@
+#!/usr/bin/which python3
+# 2.add-charts.py
+# loads the Excel pivot_table.xlsx 'Report' workbook created in 1.make-pivot-table.py
+# select the 'Report' sheet to generate the graph
+# select 3 columns by Gender, Product, Total Sales
+# create a pivot table using Gender for y-axis showing Product and Total Sales
+# output to excel
+
 from openpyxl import load_workbook
 from openpyxl.chart import BarChart, Reference
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+IN_FILE = os.path.expanduser('pivot_table.xlsx')
+OUT_FILE = os.path.expanduser('barchart.xlsx')
 
 # Read workbook and select sheet
-wb = load_workbook('pivot_table.xlsx')
-sheet = wb['Report']
+if not os.path.exists(IN_FILE):
+    print("{} -- file '{}' not found".format(PROG, IN_FILE))
+    exit(1)
+
+# if the pivot_table.xlsx file has been modified by IntelliJ's ExcelReader,
+# this will throw a 'KeyError' exception, so trap it and handle that
+# NOTE: opening the file with Apple's Numbers or Excel does not cause this error
+try:
+    wb = load_workbook(IN_FILE)
+except KeyError:
+    print("{} -- error opening '{}'... regenerate the file".format(PROG, IN_FILE))
+    exit(1)
+
+try:
+    sheet = wb['Report']  # not defined if Sheet not found...throws KeyError
+    print("{}--> '{}({})'".format(PROG, IN_FILE, sheet), end='', flush=True)
+except KeyError:
+    print("{} -- error opening '{}' -- workbook or sheet not found".format(PROG, IN_FILE))
+    exit(1)
 
 # Active rows and columns
 min_column = wb.active.min_column
 max_column = wb.active.max_column
 min_row = wb.active.min_row
 max_row = wb.active.max_row
+# print('  [active cells=({},{}):({},{})] '.format(min_row,min_column,max_row,max_column))
 
 # Instantiate a barchart
 barchart = BarChart()
 
 # Locate data and categories
+# data reference omits the column with the category headers
 data = Reference(sheet,
                  min_col=min_column+1,
                  max_col=max_column,
                  min_row=min_row,
-                 max_row=max_row)  # including headers
-
+                 max_row=max_row
+                 )
+# categories being displayed are in Column A (e.g.1)
+# don't include the headers in min_row
 categories = Reference(sheet,
                        min_col=min_column,
                        max_col=min_column,
                        min_row=min_row+1,
-                       max_row=max_row)  # not including headers
+                       max_row=max_row
+                       )
 
+# Make chart
 # Adding data and categories
 barchart.add_data(data, titles_from_data=True)
 barchart.set_categories(categories)
 
-# Make chart
-sheet.add_chart(barchart, "B12")
 barchart.title = 'Sales by Product line'
+# chart style for Excel 16.6 on MacOS
+# plain   1=BW  2=multi-color 3=blue  4=red  5=green  6=purple  7=cyan  8=orange
+# outline 9=BW 10=multi-color 11=blue 12=red 13=green 14=purple 15=cyan 16=orange
+# no error occurs of style > 16
 barchart.style = 5  # choose the chart style
+sheet.add_chart(barchart, "B12")
 
 # Save workbook
-wb.save('barchart.xlsx')
+wb.save(OUT_FILE)
+print(" --> '{}'".format(OUT_FILE))

3.Excel Report/3.apply-formulas.py

@@ -1,22 +1,50 @@
+#!/usr/bin/which python3
+# 3.apply-formulas.py
+# loads the Excel pivot_table.xlsx 'Report' workbook created in 1.make-pivot-table.py
+# select the 'Report' sheet to generate the graph
+# select 3 columns by Gender, Product, Total Sales
+# create a pivot table using Gender for y-axis showing Product and Total Sales
+# output to excel
 from openpyxl import load_workbook
 from openpyxl.utils import get_column_letter
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+IN_FILE = os.path.expanduser('barchart.xlsx')
+OUT_FILE = os.path.expanduser('report.xlsx')
+
+if not os.path.exists(IN_FILE):
+    print("{} -- file '{}' not found".format(PROG, IN_FILE))
+    exit(1)
+
+# if the barchart.xlsx file has been modified by IntelliJ's ExcelReader,
+# this will throw a 'KeyError' exception
+try:
+    wb = load_workbook(IN_FILE)
+except KeyError:
+    print("{} -- error opening '{}'... regenerate the file".format(PROG, IN_FILE))
+    exit(1)
 
-wb = load_workbook('barchart.xlsx')
 sheet = wb['Report']
+print("{}--> '{}({})'".format(PROG, IN_FILE, sheet), end='', flush=True)
 
 min_column = wb.active.min_column
 max_column = wb.active.max_column
 min_row = wb.active.min_row
 max_row = wb.active.max_row
 
+# this is what this code does if you did it manually
 # Write an Excel formula with Python
 # sheet['B8'] = '=SUM(B6:B7)'
 # sheet['B8'].style = 'Currency'
 
 # Write multiple formulas with a for loop
-for i in range(min_column+1, max_column+1):  # (B, G+1)
-    letter = get_column_letter(i)
+# the range method produces an iterable from start to stop-1,
+# so to ensure covering the last column, specify max_column+1
+for i in range(min_column+1, max_column+1):  # (B, G+1) skipping category
+    letter = get_column_letter(i)            # conv column # to letter
     sheet[f'{letter}{max_row + 1}'] = f'=SUM({letter}{min_row + 1}:{letter}{max_row})'
-    sheet[f'{letter}{max_row + 1}'].style = 'Currency'
+    sheet[f'{letter}{max_row + 1}'].style = 'Currency' # formats as "####.## $"
 
-wb.save('report.xlsx')
+wb.save(OUT_FILE)
+print(" --> '{}'".format(OUT_FILE))

3.Excel Report/4.format-cells.py

@@ -1,13 +1,32 @@
+#!/usr/bin/which python3
+# 4.format-cells.py
+# loads the Excel report.xlsx 'Report' workbook created in 2.add-charts.py
+# select the 'Report' sheet
+# annotate cells A1 and A2 with titles
+# output to excel
 from openpyxl import load_workbook
 from openpyxl.styles import Font
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+IN_FILE = os.path.expanduser('report.xlsx')
+OUT_FILE = os.path.expanduser('report_january.xlsx')
 
-wb = load_workbook('report.xlsx')
+if not os.path.exists(IN_FILE):
+    print("{} -- file '{}' not found".format(PROG, IN_FILE))
+    exit(1)
+
+# if the barchart.xlsx file has been modified by IntelliJ's ExcelReader,
+# this will throw a 'KeyError' exception
+wb = load_workbook(IN_FILE)
 sheet = wb['Report']
+print("{}--> '{}({})'".format(PROG, IN_FILE, sheet), end='', flush=True)
 
 # Add format
 sheet['A1'] = 'Sales Report'
 sheet['A2'] = 'January'
 sheet['A1'].font = Font('Arial', bold=True, size=20)
 sheet['A2'].font = Font('Arial', bold=True, size=10)
 
-wb.save('report_january.xlsx')
+wb.save(OUT_FILE)
+print(" --> '{}'".format(OUT_FILE))

3.Excel Report/5.pivot-to-report.py

@@ -1,14 +1,44 @@
+#!/usr/bin/which python3
+# 5.pivot-to-report.py
+# loads the Excel pivot_table.xlsx 'Report' workbook created in 1.make-pivot-table.py
+# select the 'Report' sheet
+# create bar chart
+# create total summary of categories
+# annotate cells A1 and A2 with titles
+# output to excel
 from openpyxl import load_workbook
 from openpyxl.chart import BarChart, Reference
 from openpyxl.utils import get_column_letter
 from openpyxl.styles import Font
+import os
+import sys
+PROG = os.path.basename(sys.argv[0])
+MONTH = 'february'
+IN_FILE = os.path.expanduser('pivot_table.xlsx')
+OUT_FILE = os.path.expanduser(f'report_{MONTH}.xlsx')
+
+# Read workbook and select sheet
+if not os.path.exists(IN_FILE):
+    print("{} -- file '{}' not found".format(PROG, IN_FILE))
+    exit(1)
 
 # Putting together #2, #3, and #4 (input: pivot_table.xlsx + month , output: Report with barchart, formulas and format)
-month = 'february'
 
-# Read workbook and select sheet
-wb = load_workbook('pivot_table.xlsx')
-sheet = wb['Report']
+# if the pivot_table.xlsx file has been modified by IntelliJ's ExcelReader,
+# this will throw a 'KeyError' exception, so trap it and handle that
+# NOTE: opening the file with Apple's Numbers or Excel does not cause this error
+try:
+    wb = load_workbook(IN_FILE)
+except KeyError:
+    print("{} -- error opening '{}'... regenerate the file".format(PROG, IN_FILE))
+    exit(1)
+
+try:
+    sheet = wb['Report']  # not defined if Sheet not found...throws KeyError
+    print("{}--> '{}({})'".format(PROG, IN_FILE, sheet), end='', flush=True)
+except KeyError:
+    print("{} -- error opening '{}' -- workbook or sheet not found".format(PROG, IN_FILE))
+    exit(1)
 
 # Active rows and columns
 min_column = wb.active.min_column
@@ -20,8 +50,18 @@
 barchart = BarChart()
 
 # Locate data and categories
-data = Reference(sheet, min_col=min_column+1, max_col=max_column, min_row=min_row, max_row=max_row)  # including headers
-categories = Reference(sheet, min_col=min_column, max_col=min_column, min_row=min_row+1, max_row=max_row)  # not including headers
+data = Reference(sheet,
+                 min_col=min_column+1,
+                 max_col=max_column,
+                 min_row=min_row,
+                 max_row=max_row
+                 )  # including headers
+categories = Reference(sheet,
+                       min_col=min_column,
+                       max_col=min_column,
+                       min_row=min_row+1,
+                       max_row=max_row
+                       )  # not including headers
 
 # Adding data and categories
 barchart.add_data(data, titles_from_data=True)
@@ -30,18 +70,25 @@
 # Make chart
 sheet.add_chart(barchart, "B12")
 barchart.title = 'Sales by Product line'
+# chart style for Excel 16.6 on MacOS
+# plain   1=BW  2=multi-color 3=blue  4=red  5=green  6=purple  7=cyan  8=orange
+# outline 9=BW 10=multi-color 11=blue 12=red 13=green 14=purple 15=cyan 16=orange
+# no error occurs of style > 16
 barchart.style = 5  # choose the chart style
 
 # Write multiple formulas with a for loop
 for i in range(min_column+1, max_column+1):  # (B, G+1)
     letter = get_column_letter(i)
     sheet[f'{letter}{max_row + 1}'] = f'=SUM({letter}{min_row + 1}:{letter}{max_row})'
+    # Python's 'Currency' style appears as "##### $" which shows as Custom in Excel
+    # this is a bug in the openpyxl library
     sheet[f'{letter}{max_row + 1}'].style = 'Currency'
 
 # Add format
 sheet['A1'] = 'Sales Report'
-sheet['A2'] = month
+sheet['A2'] = MONTH
 sheet['A1'].font = Font('Arial', bold=True, size=20)
 sheet['A2'].font = Font('Arial', bold=True, size=10)
 
-wb.save(f'report_{month}.xlsx')
+wb.save(OUT_FILE)
+print(" --> '{}'".format(OUT_FILE))

3.Excel Report/6.py-to-exe.py

@@ -1,62 +1,220 @@
+#!/usr/bin/which python3
+"""
+6.py-to-exe.py
+loads the Excel the sales marketing data and creates a pivot_table.xlsx 'Report' workbook
+select the 'Report' sheet
+create bar chart
+create total summary of categories
+annotate cells A1 and A2 with titles
+output to excel from openpyxl import load_workbook
+"""
+
+import argparse
+import os
+import sys
+from datetime import date
+
+import pandas as pd
 from openpyxl import load_workbook
 from openpyxl.chart import BarChart, Reference
 from openpyxl.utils import get_column_letter
 from openpyxl.styles import Font
-import os
-import sys
 
-# Preparing script before we convert it to executable
-application_path = os.path.dirname(sys.executable)
-
-# Putting together #2, #3, and #4 (input: pivot_table.xlsx + month , output: Report with barchart, formulas and format)
-month = input('Introduce month: ')
-
-# Read workbook and select sheet
-input_path = os.path.join(application_path, 'pivot_table.xlsx')
-wb = load_workbook(input_path)
-sheet = wb['Report']
-
-# Active rows and columns
-min_column = wb.active.min_column
-max_column = wb.active.max_column
-min_row = wb.active.min_row
-max_row = wb.active.max_row
-
-# Instantiate a barchart
-barchart = BarChart()
-
-# Locate data and categories
-data = Reference(sheet,
-                 min_col=min_column+1,
-                 max_col=max_column,
-                 min_row=min_row,
-                 max_row=max_row)  # including headers
-categories = Reference(sheet,
-                       min_col=min_column,
-                       max_col=min_column,
-                       min_row=min_row+1,
-                       max_row=max_row)  # not including headers
-
-# Adding data and categories
-barchart.add_data(data, titles_from_data=True)
-barchart.set_categories(categories)
-
-# Make chart
-sheet.add_chart(barchart, "B12")
-barchart.title = 'Sales by Product line'
-barchart.style = 5  # choose the chart style
-
-# Write multiple formulas with a for loop
-for i in range(min_column+1, max_column+1):  # (B, G+1)
-    letter = get_column_letter(i)
-    sheet[f'{letter}{max_row + 1}'] = f'=SUM({letter}{min_row + 1}:{letter}{max_row})'
-    sheet[f'{letter}{max_row + 1}'].style = 'Currency'
-
-# Add format
-sheet['A1'] = 'Sales Report'
-sheet['A2'] = month
-sheet['A1'].font = Font('Arial', bold=True, size=20)
-sheet['A2'].font = Font('Arial', bold=True, size=10)
-
-output_path = os.path.join(application_path, f'report_{month}.xlsx')
-wb.save(output_path)
+
+def parse_arguments(default_input_file='supermarket_sales.xlsx',
+                    default_output_file='report.xlsx',
+                    default_month='MONTHLY'
+                    ):
+    """parse the argument list, build help and usage messages
+
+    Args:
+        default_input_file (str): filename containing a default input Excel spreadsheet
+        default_output_file (str): filename containing a default output Excel spreadsheet for
+        the consolidation report
+        default_month (str): containing the current month as a string (not validated)
+
+    Returns:
+        namespace (ns): namespace with the arguments passed and their values
+
+    """
+    parser = argparse.ArgumentParser(
+        description='generate Consolidation report from Excel spreadsheet of marketing data')
+    # if omitted, the default value is returned, so arg.input is always defined
+    parser.add_argument('-i', '--input',
+                        action='store',
+                        default=default_input_file,
+                        help=f'Input file of Excel Marketing data [default: {default_input_file}]',
+                        required=False,
+                        # nargs="?",   # command line arg w/o flag
+                        )
+    # if omitted, the default value is returned, so arg.output is always defined
+    parser.add_argument('-o', '--output',
+                        action="store",
+                        default=default_output_file,
+                        help=f'Consolidation Report output file [default: {default_output_file}]',
+                        required=False
+                        )
+    # if omitted, the current month is used, so arg.month will always be defined
+    parser.add_argument('-m', '--month',
+                        action="store",
+                        default=default_month,
+                        help=f'Month to tag in output report [default: {default_month}]',
+                        required=False
+                        )
+    parser.add_argument('-v', '--verbose',
+                        action="store_true",
+                        help='show progress as report is being built',
+                        required=False
+                        )
+    args = parser.parse_args()
+
+    # args.input = os.path.expanduser(args.input)
+    # args.output = os.path.expanduser(args.output)
+
+    return args  # namespace containing the argument passed on the command line
+
+
+def main():
+    """main program to input marketing data and output a consolidation report as Excel spreadsheet
+
+    Args:
+        inputs Excel spreadsheet (must be xlsx file)
+        assumes Excel table format with 1st line containing
+    - Invoice
+    - Branch
+    - City
+    - Customer Type
+    - Gender
+    - Product Line
+    - Unit Price
+    - Quantity
+    - Tax 5%
+    - Total
+    - Date (mm/dd/yy)
+    - Time (HH:MM)
+    - Payment
+    - cogs
+    - gross Margin
+    - gross Income
+    - Rating
+        outputs Excel spreadsheet consolidation report
+
+    Returns: 0
+
+"""
+    prog = os.path.basename(sys.argv[0])
+    this_month = date.today().strftime('%B')  # full month
+    args = parse_arguments(
+                            default_input_file='supermarket_sales.xlsx',
+                            default_output_file=f'report_{this_month}.xlsx',
+                            default_month=this_month
+                           )
+
+    input_expanded = os.path.expanduser(args.input)
+    # output_file = os.path.expanduser(os.path.exists(args.output))
+    if not os.path.exists(input_expanded):
+        print(f'{prog} -- file {input_expanded} not found')
+        sys.exit(1)
+
+    df = pd.read_excel(input_expanded)  # open excel file as panda dataframe
+
+    if args.verbose:
+        print(f'{prog}--> read_excel {input_expanded}...', end='', flush=True)
+
+    # Select columns: 'Gender', 'Product line', 'Total'
+    df = df[['Gender', 'Product line', 'Total']]
+    if args.verbose:
+        # print(df)
+        print('selecting columns...', end='', flush=True)
+
+    pivot_table = df.pivot_table(index='Gender', columns='Product line',
+                                 values='Total', aggfunc='sum').round(2)
+
+    # Export pivot table to Excel file w/ sheet starting at row 4
+    # Preparing script before we convert it to executable
+    # application_path = os.path.dirname(sys.executable)
+    # output_file = os.path.join(os.path.dirname(sys.executable), args.output)
+    pivot_table.to_excel(args.output, 'Report', startrow=4)
+    if args.verbose:
+        # print(pivot_table)
+        print(f'excel.pivot{args.output}...')
+
+    # if the pivot_table.xlsx file has been modified by IntelliJ's ExcelReader,
+    # this will throw a 'KeyError' exception, so trap it and handle that
+    # NOTE: opening the file with Apple's Numbers or Excel does not cause this error
+    # since this is an intermediate step and can't be read, remove the exception trapping
+    # try:
+    wb = load_workbook(args.output)
+    # except KeyError:
+    #     print(f"{PROG} -- error opening '{output_file}'... regenerate the file")
+    #     sys.exit(1)
+    #
+    # TODO: how to reference the sheet from report_sheet as a dict w/o hard coding reference?
+    try:
+        sheet = wb['Report']  # not defined if Sheet not found...throws KeyError
+        if args.verbose:
+            print(f"{prog}--> '{args.output}(Report)'...", end='', flush=True)
+    except KeyError:
+        print(f"{prog} -- error opening '{args.output}' -- workbook or sheet not found")
+        sys.exit(1)
+
+    if args.verbose:
+        print('...loaded...', end='', flush=True)
+
+    # Active rows and columns
+    min_column = wb.active.min_column
+    max_column = wb.active.max_column
+    min_row = wb.active.min_row
+    max_row = wb.active.max_row
+
+    # Instantiate a barchart
+    barchart = BarChart()
+
+    # Locate data and categories
+    data = Reference(sheet,
+                     min_col=min_column+1, max_col=max_column,  # data starts after header column
+                     min_row=min_row,      max_row=max_row)
+    categories = Reference(sheet,
+                           min_col=min_column, max_col=min_column,  # omit header column
+                           min_row=min_row+1,  max_row=max_row)
+
+    # Adding data and categories
+    barchart.add_data(data, titles_from_data=True)
+    barchart.set_categories(categories)
+
+    # Make chart in cell B12
+    sheet.add_chart(barchart, "B12")
+    barchart.title = 'Sales by Product line'
+    # chart style for Excel 16.6 on MacOS 12.4
+    # plain    1=BW  2=multi-color  3=blue  4=red  5=green  6=purple  7=cyan  8=orange
+    # outlined 9=BW 10=multi-color 11=blue 12=red 13=green 14=purple 15=cyan 16=orange
+    # no error occurs of style > 16
+    barchart.style = 5  # choose the chart style (plain green)
+    if args.verbose:
+        print('barchart...', end='', flush=True)
+    # Write multiple formulas with a for loop
+    # note that openpyxl has a bug incorrectly setting style='Currency' (##### $ instead of $#####)
+    for i in range(min_column+1, max_column+1):  # (B, G+1)
+        letter = get_column_letter(i)
+        sheet[f'{letter}{max_row + 1}'] = f'=SUM({letter}{min_row + 1}:{letter}{max_row})'
+        sheet[f'{letter}{max_row + 1}'].style = 'Currency'
+    if args.verbose:
+        print('summary...', end='', flush=True)
+
+    # Add Title and format
+    sheet['A1'] = 'Sales Report'
+    sheet['A2'] = args.month
+    sheet['A1'].font = Font('Arial', bold=True, size=20)
+    sheet['A2'].font = Font('Arial', bold=True, size=10)
+    if args.verbose:
+        print('titles...', end='', flush=True)
+
+    wb.save(args.output)
+    if args.verbose:
+        print(f" '{args.output}'")
+
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main())

4.WhatsApp/0.whatsapp-pywhatkit.py

@@ -1,15 +1,101 @@
+#!/usr/bin/which python3
+"""
+0.whatsapp-pywhatkit.py
+send message to single WhatsApp user or a GroupID
+
+"""
+import sys
+from datetime import datetime,timedelta
+import argparse
 import pywhatkit
 
-# Send message to a contact
-phone_number = input("Enter phone number: ")
 
-pywhatkit.sendwhatmsg(phone_number, "Test", 7, 21)
-pywhatkit.sendwhatmsg(phone_number, "Test", 7, 25, 15, True, 2)
+def parse_arguments():
+    """parse the argument list, build help and usage messages
+
+    parses command line for
+        -p --phone  (str): WhatsApp phone number to call  TODO: validate as phone #
+
+        -g --group  (str): WhatsApp Group ID to call
+
+    Returns:
+        namespace (ns): namespace with the arguments passed and their values
+
+    """
+    parser = argparse.ArgumentParser(
+        description='contact a WhatsApp user via their phone number or Group ID')
+    # if omitted, the script will prompt for the phone or group id
+    parser.add_argument('-p', '--phone',
+                        action='store',
+                        help='WhatsApp phone number',
+                        required=False,
+                        # nargs="?",   # command line arg w/o flag
+                        )
+    # if neither is passed, the phone is prompted
+    parser.add_argument('-g', '--group',
+                        action="store",
+                        help='WhatsApp Group ID',
+                        required=False
+                        )
+    args = parser.parse_args()
+    return args  # namespace containing the argument passed on the command line
+
+
+def main():
+    """parse WhatsApp phone number or group ID and contact that number
+    """
+    args = parse_arguments()
+    if args.phone:
+        phone_number = args.phone
+    else:
+        phone_number = input("Enter phone number: ")
+
+    # this could just as easily been now + timedelta(seconds=10)
+    # but we need to pass the hours minutes and seconds
+    now = datetime.now()
+    call_hh = now.hour
+    call_mm = now.minute
 
-# Send message to a group
-group_id = input("Enter group id: ")
+    # Send message to a contact 10 from when program was run
+    # sendwhatmsg_instantly(phone_no: str,
+    #                       message: str,
+    #                       wait_time: int = 15,
+    #                       tab_close: bool = False,
+    #                       close_time: int = 3) -> None
+    # sendwhatmsg( phone_no: str,
+    #           message: str,
+    #           time_hour: int,
+    #           time_min: int,
+    #           wait_time: int = 15,
+    #           tab_close: bool = False,
+    #           close_time: int = 3)
+    pywhatkit.sendwhatmsg_instantly('+1' + phone_number, "Instant Test")
+    # pywhatkit.sendwhatmsg('+1' + phone_number, "Test", call_hh, call_mm+2)
+    pywhatkit.sendwhatmsg('+1' + phone_number,
+                          "Test...wait 7...close....close=2",
+                          call_hh, call_mm+1,
+                          7, True, 2
+                          )
 
-pywhatkit.sendwhatmsg_to_group(group_id, "Test Group", 7, 31)
+    if args.group:
+        group_id = args.group
+    else:
+        group_id = input("Enter group id: ")
 
+    # Send message to a group
+    # sendwhatmsg_to_group( group_id: str,
+    #                       message: str,
+    #                       time_hour: int,
+    #                       time_min: int,
+    #                       wait_time: int = 15,
+    #                       tab_close: bool = False,
+    #                       close_time: int = 3) -> None
+    pywhatkit.sendwhatmsg_to_group(group_id,
+                                   "Test Group",
+                                   call_hh, call_mm+3
+                                   )
+    return 0
 
 
+if __name__ == '__main__':
+    sys.exit(main())

requirements.txt

@@ -0,0 +1,30 @@
+## requirements.txt
+## used by https://github.com/ifrankandrade/automation
+## and fork https://github.com/mvilain/python-automation
+## use this with a python virtual environment
+## (e.g. python3 -m virtualenvironment virtualenv; source virtualenv/bin/activate; python3 -m pip install -r requirements)
+#####    DO NOT ALLOW PYCHARM or INTELLIJ to install these modules
+#####    it will install them into the system directory...use the commands above
+pathlib
+
+## https://camelot-py.readthedocs.io/en/master/user/install-deps.html
+ghostscript
+tk
+## https://stackoverflow.com/questions/60666006/python-camelot-module-does-not-work-offline
+opencv-python
+camelot-py
+
+jupyterlab
+pandas
+openpyxl
+
+selenium
+pyinstaller
+
+pywhatkit
+## the following are part of the standard Library install
+## they don't need to be listed here but are used by this repo
+#email
+#ssl
+#time
+#wheel