def get_info(path): #function to get number of pages of input pdf
with open(path, 'rb') as f:
pdf = PdfFileReader(f)
print(pdf)
number_of_pages = pdf.getNumPages()
text = convert_pdf_to_txt(path, pages=range(0,number_of_pages))
LANGUAGE = "english"
SENTENCES_COUNT = 10
#url = "https://en.wikipedia.org/wiki/Automatic_summarization"
#parser = HtmlParser.from_url(url, Tokenizer(LANGUAGE))
# or for plain strings
parser = PlaintextParser.from_string(text, Tokenizer(LANGUAGE)) #PlaintextParser.from_file for files
stemmer = Stemmer(LANGUAGE)
summarizer = Summarizer(stemmer)
summarizer.stop_words = get_stop_words(LANGUAGE)
print("SUMMARY")
for sentence in summarizer(parser.document, SENTENCES_COUNT):
print(sentence)
#print(keywords.keywords(text)) #original keywords
keywordlist1=keywords.keywords(text,split=True) #list of keywords
keywordstring=" ".join(keywordlist1) #string of keywords
tokens= nltk.word_tokenize(keywordstring)
print("\n","KEYWORDS")
print("\n",{stem(t) for t in tokens},"\n") # gives set of unique kywords
def get_info(path):
with open(path, 'r') as f:
text = f.read()
LANGUAGE = "english"
SENTENCES_COUNT = 10
#url = "https://en.wikipedia.org/wiki/Automatic_summarization"
#parser = HtmlParser.from_url(url, Tokenizer(LANGUAGE))
# or for plain strings
parser = PlaintextParser.from_string(
text, Tokenizer(LANGUAGE)) #PlaintextParser.from_file for files
stemmer = Stemmer(LANGUAGE)
summarizer = Summarizer(stemmer)
summarizer.stop_words = get_stop_words(LANGUAGE)
print("SUMMARY")
for sentence in summarizer(parser.document, SENTENCES_COUNT):
print(sentence)
#print(keywords.keywords(text)) #original keywords
keywordlist1 = keywords.keywords(text, split=True) #list of keywords
keywordstring = " ".join(keywordlist1) #string of keywords
tokens = nltk.word_tokenize(keywordstring)
print("\n", "KEYWORDS")
print("\n", {stem(t)
for t in tokens}, "\n") # gives set of unique kywords
def create_lsa_summary():
for filename in os.listdir(TREES_SOURCE_PATH):
if filename.endswith('.xml'):
name = re.search('topic_(.*)\.xml', filename)
input_path = create_input(name.group(1))
with open(SUM_PATH + name.group(1) + '_LSA_Group5.txt',
'w',
encoding='utf8') as summary:
summary.write("====================== General Summary of " +
name.group(1) + " ======================\n")
parser = PlaintextParser.from_file(input_path,
Tokenizer("english"))
summarizer = LsaSummarizer()
s = summarizer(parser.document, 4)
for sentence in s:
summary.write(str(sentence) + '\n')
def create_textrank_summary(max_chars):
for filename in os.listdir(TREES_SOURCE_PATH):
chars = 0
if filename.endswith('.xml'):
name = re.search('topic_(.*)\.xml', filename)
input_path = create_input(name.group(1))
path = SUM_PATH + name.group(1)
with open(path + '_TextRank_Group5.txt', 'w',
encoding='utf8') as summary:
summary.write("====================== General Summary of " +
name.group(1) + " ======================\n")
parser = PlaintextParser.from_file(input_path,
Tokenizer("english"))
summarizer = TextRankSummarizer()
s = summarizer(parser.document, 3)
for sentence in s:
if (chars + len(str(sentence)) <= max_chars):
summary.write(str(sentence) + '\n')
chars += len(str(sentence))
expand_textrank(name.group(1), path, max_chars, chars)