python script file to create Excel file, summarizing the html reports...

python script file to create Excel file, summarizing the html reports generated by running the Postman collections using newman -htmlextra report generator.

Summarize_Newman_Html_Reports.py

+#!/usr/bin/env python3
+
+# importing the libraries
+import os
+import re
+import xlsxwriter
+from bs4 import BeautifulSoup
+import requests
+import datetime
+#
+# This script processes all the html files that are generated by using the Postman Newman (htmlextra)
+# program to run the postman collections for "OSDU Platform Validation project."
+# it expects the report files to follow the assumptions and rules mentioned in file 
+# OSDU Platform Validation CI_CD_Notes.md of "Platform Validation project"
+# At present it is assuming 11 collections being run each of the four platforms
+# AWS, AZURE, GCP, IBM
+# In future work will be done where it should be able handle n number of collections instead of fix 11
+# At present this restriction is because of the way the writing of the excel file is implemented,
+# specially the writing of the last summary part, after all the collections are processed.
+#=======================================================================================================
+# Method to process html report file and summarize the results in Excel file
+def processFile(fnm, platform, rowNo, colOffset, envFileNamesPopulated):
+    # print("fileName: " + fnm)
+    # print("Platform: " + platform)
+    # print("Row: ", rowNo)
+    # print("Total Rows: ", totRows)
+    # print("Column offset", colOffset)
+    # return()
+    #
+    html = open(fnm, 'r').read()   # local html
+    bs = BeautifulSoup(html, features="html.parser")
+    #
+    mydivs = bs.findAll("div", {"class": "col-sm-12 mb-3"})
+    txt = mydivs[0].get_text()
+    fileInfo = txt.split("\n")
+    # Get file and environment information
+    collectionName = ""
+    enviornmentName = ""
+    count = 0
+    pattern = re.compile("Collection:")
+    # Parse and extract all the necessary values
+    for elm in fileInfo:
+        if pattern.search(elm):
+            if (count == 0):
+                collectionstr = elm.split(":")
+                collectionName = collectionstr[1]
+                pattern = re.compile("Environment:")
+                count += 1
+            elif (count == 1):
+                environmentstr = elm.split(":")
+                enviornmentName = environmentstr[1]
+    #           
+    print(collectionName)
+    print(enviornmentName)
+    # Save/Collect environment file name
+    if (envFileNamesPopulated == False):
+        if (colOffset == 0):
+            env_file_names.append(enviornmentName)
+        elif (colOffset == 6):
+            env_file_names.append(enviornmentName)
+        elif (colOffset == 10):
+            env_file_names.append(enviornmentName)
+        elif(colOffset == 14):
+            env_file_names.append(enviornmentName)
+        else:
+            print("Something wrong while populating env file names")
+    #
+    #Get the summary of Total requests pass/fail, Total assertions pass/fail, Total tests skipped
+    mytab = bs.findAll("table", {"class": "table table-striped table-bordered"})
+    txt2 = mytab[0].get_text()
+    summaryInfo = txt2.split()
+    # Initialize the values
+    totalRequestsPassed = 0
+    totalRequestsFailed = 0
+    totalAssertionPassed = 0
+    totalAssertionFailed = 0
+    skippedTests = 0
+    count = 0
+    # Parse and extract all the necessary values
+    for info in summaryInfo:
+        if (count == 5):
+            totalRequestsPassed = info     
+        elif (count == 6):
+            totalRequestsFailed = info
+        elif (count == 16):
+            totalAssertionPassed = info
+        elif (count == 17):
+            totalAssertionFailed = info
+        elif (count == 20):
+            skippedTests = info       
+        count += 1
+    #
+    passRate = (100 * float(totalAssertionPassed ) / (float(totalAssertionPassed) + float(totalAssertionFailed)) )
+
+    # print("totalRequestsPassed: " + totalRequestsPassed)
+    # print("totalRequestsFailed: " + totalRequestsFailed)
+    # print("totalAssertionPassed: " + totalAssertionPassed)
+    # print("totalAssertionFailed: " + totalAssertionFailed)
+    # print("skippedTests: " + skippedTests)
+    # print(passRate)
+
+    records.append((collectionName, totalRequestsPassed, totalAssertionPassed, totalAssertionFailed, passRate ))
+
+    curRow = len(records) - 1
+    # print(records[curRow])
+    
+    for col_num, data in enumerate(records[curRow]):
+
+        l_colNum = col_num
+        if (col_num > 1) and (colOffset > 5):
+            l_colNum = col_num + colOffset-2
+        if (l_colNum == 0):
+            worksheet.write(rowNo, l_colNum, data, collection_cell_format)
+        elif (l_colNum == 1):
+            worksheet.write(rowNo, l_colNum, int(data), request_cell_format)
+        elif ( (l_colNum == 4) or (l_colNum == 8) or (l_colNum == 12) or (l_colNum == 16 ) ):
+            if (passRate >= 100.0):
+                worksheet.write(rowNo, l_colNum, data, greenPct_cell_format)
+            elif (passRate < 60.0):
+                worksheet.write(rowNo, l_colNum, data, redPct_cell_format)
+            else:
+                worksheet.write(rowNo, l_colNum, data, pct_cell_format)
+        else:
+            worksheet.write(rowNo, l_colNum, int(data), cell_format)
+    #Extract run Date Info
+    if (len(collection_run_date) == 0): 
+        mydivs3 = bs.findAll("div", {"class": "col-md-9 col-lg-12 main"})
+        txt3 = mydivs3[0].get_text()
+        dateInfo = txt3.split("\n")
+        collection_run_date.append(dateInfo[2])
+    #
+        
+#=======================================================================================================
+# Start of Main
+print("Starting to summarize all the html reports")
+
+records = []
+env_file_names = []
+env_file_names_populated = False
+collection_run_date = []
+# Define the headers for the excel file
+records.append(("","","","AWS","","","","AZURE","","","","GCP","","","","IBM",""))
+records.append(("Collection Name", "#of Requests", "Pass", "Fail", "PassRate","","Pass", "Fail", "PassRate","","Pass", "Fail", "PassRate","","Pass", "Fail", "PassRate"))
+
+#Create and initialize the excel file
+workbook = xlsxwriter.Workbook('NewmanHtmlReportsSummary.xlsx')
+worksheet = workbook.add_worksheet()
+worksheet.set_column(0, 0, 40)
+worksheet.set_column(1, 1, 12)
+cell_format = workbook.add_format({'align': 'center', 'bold': True})
+summ_cell_format = workbook.add_format({'align': 'left', 'bold': True})
+summ_right_cell_format = workbook.add_format({'align': 'right', 'bold': True})
+
+request_cell_format = workbook.add_format({'align': 'center', 'bg_color': '#D8E4BC'})
+
+collection_cell_format = workbook.add_format({'align': 'center', 'bold': True})
+collection_cell_format.set_font_color('blue')
+#
+total_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': 'orange', 'font_color': 'blue'})
+#
+pct_cell_format = workbook.add_format({'align': 'center', 'bold': True})
+pct_cell_format.set_num_format('0.00')
+#
+greenPct_cell_format = workbook.add_format({'align': 'center', 'bold': True})
+greenPct_cell_format.set_font_color('green')
+greenPct_cell_format.set_num_format('0.00')
+#
+redPct_cell_format = workbook.add_format({'align': 'center', 'bold': True})
+redPct_cell_format.set_font_color('red')
+redPct_cell_format.set_num_format('0.00')
+#
+head_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#78B0DE'})
+head_cell_format.set_font_size(14)
+
+head2_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'black'})
+head2_cell_format.set_font_size(12)
+
+head2_green_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'green'})
+head2_green_cell_format.set_font_size(12)
+head2_red_cell_format = workbook.add_format({'align': 'center', 'bold': True, 'bg_color': '#BBD7EF', 'font_color': 'red'})
+head2_red_cell_format.set_font_size(12)
+
+#Write the header records to excel file
+rowNum = 0
+col_offset = 0
+for row_num in records:
+    for col_num, data in enumerate(records[rowNum]):
+        if (rowNum == 0):
+            worksheet.write(rowNum, col_num, data, head_cell_format)
+        else:
+            # print("rowNum: ", rowNum, "  col_num: ", col_num)
+            if (rowNum == 1):
+                if ( (col_num == 2) or (col_num == 6) or (col_num == 10) or (col_num == 14) ):
+                    worksheet.write(rowNum, col_num, data, head2_green_cell_format)
+                elif ((col_num == 3) or (col_num == 7) or (col_num == 11) or (col_num == 15)):
+                    worksheet.write(rowNum, col_num, data, head2_red_cell_format)
+                else:
+                    worksheet.write(rowNum, col_num, data, head2_cell_format)
+            
+    rowNum += 1
+#process all the reports to summarize the results
+curPlatform = ""
+localRowNo = rowNum
+collName = []
+for file in os.listdir("."):
+    if (file.endswith(".html")):    # process only html files
+        fileParts = file.split(".")
+        if (fileParts[0] == "index"):
+            print("Skip - " + file)     # skip processing of index.html file
+            continue
+        else:
+            # print(file)
+            if (fileParts[0] != curPlatform):
+                #
+                localRowNo = rowNum
+                curPlatform = fileParts[0]
+                #
+                if (fileParts[0] == "aws"):               
+                    col_offset = 0
+                elif (fileParts[0] == "azure"):
+                    col_offset = 6
+                elif (fileParts[0] == "gcp"):
+                    col_offset = 10
+                elif (fileParts[0] == "ibm"):
+                    col_offset = 14
+                else:
+                    print("Invalid platform: " + fileParts[0])
+                    continue
+                env_file_names_populated = False
+            else:
+                env_file_names_populated = True
+
+            if (fileParts[0] == "aws"):
+                collName.append(fileParts[1])
+
+            processFile(file, fileParts[0], localRowNo, col_offset, env_file_names_populated)     # process html report file
+            localRowNo += 1
+            print("")
+#
+print("Total number of collections: ", len(collName) )
+print("Total number of reports summarized: ", (len(records)-2) )
+print("Total number of platforms", ((len(records) - 2)/len(collName)) )
+fill_cell_format = workbook.add_format({'bg_color': '#FFE1E5'})
+total_row_num = len(collName) + 2
+colList = [5,9,13]
+for i in range(2, total_row_num):
+    for j in  range(len(colList)):
+        worksheet.write(i, colList[j], "", fill_cell_format)
+#
+total_cols = 17
+for j in range(total_cols):
+    if (j == 0):
+        worksheet.write(13, j, "Total", total_cell_format)
+    elif ( (j == 5) or (j == 9) or (j == 13) ):
+        worksheet.write(total_row_num, j, "", total_cell_format)
+        # continue
+    elif (j == 1):
+        worksheet.write_formula('B14', '{=SUM(B3:B13)}', total_cell_format)
+    elif (j == 2):
+        worksheet.write_formula('C14', '{=SUM(C3:C13)}', total_cell_format)
+    elif (j == 3):
+        worksheet.write_formula('D14', '{=SUM(D3:D13)}', total_cell_format)
+    elif (j == 4):
+        worksheet.write_formula('E14', '{=SUM(E3:E13)}', total_cell_format)
+    elif (j == 6):
+        worksheet.write_formula('G14', '{=SUM(G3:G13)}', total_cell_format)
+    elif (j == 7):
+        worksheet.write_formula('H14', '{=SUM(H3:H13)}', total_cell_format)
+    elif (j == 8):
+        worksheet.write_formula('I14', '{=SUM(I3:I13)}', total_cell_format)
+    elif (j == 10):
+        worksheet.write_formula('K14', '{=SUM(K3:K13)}', total_cell_format)
+    elif (j == 11):
+        worksheet.write_formula('L14', '{=SUM(L3:L13)}', total_cell_format)
+    elif (j == 12):
+        worksheet.write_formula('M14', '{=SUM(M3:M13)}', total_cell_format)
+    elif (j == 14):
+        worksheet.write_formula('O14', '{=SUM(O3:O13)}', total_cell_format)
+    elif (j == 15):
+        worksheet.write_formula('P14', '{=SUM(P3:P13)}', total_cell_format)
+    elif (j == 16):
+        worksheet.write_formula('Q14', '{=SUM(Q3:Q13)}', total_cell_format)
+#
+date_time_obj = datetime.datetime.strptime(collection_run_date[0], '%A, %d %B %Y %H:%M:%S')
+str1 = "Collection run date:  " + date_time_obj.strftime('%m/%d/%Y, %H:%M:%S')
+worksheet.write(15, 0, str1, summ_cell_format)
+# str1 = "Summary report run date:\t " + (datetime.datetime.now().strftime('%A, %d %B %Y %H:%M:%S'))
+str1 = "Summary report date:  " + (datetime.datetime.now().strftime('%m/%d/%Y, %H:%M:%S'))
+worksheet.write(16, 0, str1, summ_cell_format)
+#
+worksheet.write(18, 0, "Environment Files:", summ_cell_format)
+numOfEnvs = len(env_file_names)
+for i in range(numOfEnvs):
+    worksheet.write((19+i), 0, env_file_names[i], cell_format)
+#
+workbook.close()
+print(env_file_names)
+print(collection_run_date)
+print("Summary Report Date: ", datetime.datetime.now())
+print("Done")
+exit()
+#
+
+