Trying to get def countnonarticlewords to count the number of Non-Article Words in a mobydick text file. The words I am trying to not count are 'a','an' and'the'.Any hints on how I could modify def countnonarticlewords to output Example #1. Currently it is outputting Example #2
Example #1
******* mobydick.txt *******
Total Lines: 15604
Total Chars: 512293
Total Words: 115314
**Total Non-Article Words: 105479**
Example #2
Enter the test file name: mobydick.txt
*****mobydick.txt*****
Total Lines: 15604
Total Chars: 512293
Total Words: 115314
**Total Non-Article Words: 15604**
What I have so far:
def getTextFile():
filename=input("Enter the test file name: ")
textFile=open(filename, 'r')
return filename,textFile
def outputcountresults(filename, linecount, charcount, wordcount, nonarticlewordcount):
print("*****{}*****".format(filename))
print("Total Lines: {}".format(linecount))
print("Total Chars: {}".format(charcount))
print("Total Words: {}".format(wordcount))
print("Total Non-Article Words: {}".format(nonarticlewordcount))
def countcharacters(line):
charcount=0
for c in line:
if not c.isspace():
charcount= charcount +1
return charcount
def countnonarticlewords(line):
nonarticlewords= line.split()
nonarticlewords=0
for nonarticle in line:
#nonarticlewords= line.split()
if not 'a' or 'an' or 'the':
nonarticlewords= nonarticlewords +1
return len(nonarticle)
def countwords(line):
words= line.split()
return len(words)
def countdocstats(docFile):
linecount=0
totalcharacters=0
totalwords=0
totalnonarticlewords=0
for line in docFile:
linecount= linecount + 1
totalwords= totalwords + countwords(line)
totalcharacters=totalcharacters+countcharacters(line)
totalnonarticlewords= totalnonarticlewords + countnonarticlewords(line)
return linecount, totalcharacters, totalwords, totalnonarticlewords
def main():
filename, textFile=getTextFile()
linecount, totalcharacters, totalwords, totalnonarticlewords= countdocstats(textFile)
outputcountresults(filename,linecount,totalcharacters,totalwords,totalnonarticlewords)
main()
