def getText():
dataList = []
for f in os.listdir('unsupervised\\documents'):
filePath = 'unsupervised\\documents\\' + f
#print filePath
fileName, fileExtension = os.path.splitext(filePath)
#print fileExtension
if fileExtension.lower() == '.docx':
print '' #'its a {0} {1}{2}'.format('word document', fileName, fileExtension)
doc = docxDocument(filePath)
for p in doc.paragraphs:
dataList.append(p.text) #print p.text
#print "-------------------------------"
elif fileExtension.lower() == '.pdf':
print '' #'its a {0} {1}{2}'.format('pdf document', fileName, fileExtension)
#TODO
elif ((fileExtension.lower() == '.html') or (fileExtension.lower() == '.htm')):
print '' #'its a {0} {1}{2}'.format('html file', fileName, fileExtension)
with codecs.open (filePath, errors='ignore') as myfile:
source = myfile.read()
article = Document(source).summary()
title = Document(source).title()
soup = BeautifulSoup(article, 'lxml')
final = replaceTwoOrMore((title.replace('\n', ' ').replace('\r', '') + '.' + soup.text.replace('\n', ' ').replace('\r', '')))
dataList.append(final)
#print '*** TITLE *** \n\"' + title + '\"\n'
#print '*** CONTENT *** \n\"' + soup.text + '[...]\"'
else:
print '' # 'undectected document type'
print '' #"-------------------------------"
return dataList
def main():
#print 'Hello there'
# Command line args are in sys.argv[1], sys.argv[2] ...
# sys.argv[0] is the script name itself and can be ignored
dataList = []
for f in os.listdir('documents'):
filePath = 'documents\\' + f
#print filePath
fileName, fileExtension = os.path.splitext(filePath)
#print fileExtension
if fileExtension.lower() == '.docx':
print '' #'its a {0} {1}{2}'.format('word document', fileName, fileExtension)
doc = docxDocument(filePath)
for p in doc.paragraphs:
dataList.append(p.text) #print p.text
#print "-------------------------------"
elif fileExtension.lower() == '.pdf':
print '' #'its a {0} {1}{2}'.format('pdf document', fileName, fileExtension)
# with open(filePath) as f:
# doc = slate.PDF(f)
# print doc[1]
# exit()
#TODO
elif ((fileExtension.lower() == '.html') or (fileExtension.lower() == '.htm')):
print '' #'its a {0} {1}{2}'.format('html file', fileName, fileExtension)
with codecs.open (filePath, errors='ignore') as myfile:
source = myfile.read()
article = Document(source).summary()
title = Document(source).title()
soup = BeautifulSoup(article, 'lxml')
final = replaceTwoOrMore((title.replace('\n', ' ').replace('\r', '') + '.' + soup.text.replace('\n', ' ').replace('\r', '')))
dataList.append(final)
#print '*** TITLE *** \n\"' + title + '\"\n'
#print '*** CONTENT *** \n\"' + soup.text + '[...]\"'
else:
print '' # 'undectected document type'
print '' #"-------------------------------"
#print dataList
#for i in dataList:
# print i
cachedStopWords = stopwords.words("english")
combined = ' '.join(dataList)
#print combined
bloblist = [tb(combined)]
for i, blob in enumerate(bloblist):
print("Top words in document {}".format(i + 1))
scores = {word: tfidf(word, blob, bloblist) for word in blob.words if word not in nltk.corpus.stopwords.words('english')}
#print scores
sorted_words = sorted(scores.items(), key=lambda x: x[1], reverse=True)
#print sorted_words
for word, score in sorted_words:
print("\tWord: {}, TF-IDF: {}".format(word, round(score, 5)))