print("Started getting text from \"{0}\"".format(input_file.path_txt))
start_time = time()
input_file.text = file_process.get_text(input_file)
end_time = time()
print("Getting text from \"{0}\" took {1:.3f}s".format(input_file.path_txt, end_time - start_time), end = "\n\n")
"""
Started getting keywords from input_file
"""
stopwords = set()
if (stopwords_file.path_txt == None):
pass
else:
print("Started parsing TXT with stopwords, wait for a while...")
start_time = time()
stopwords = split.get_list(stopwords_file.path_txt, enableComments = True)
stopwords = set(stopwords)
end_time = time()
print("Parsing TXT with stopwords took {0:.3f}s".format(end_time - start_time), end = "\n\n")
"""
Started getting keyword phrases from input_file
"""
print("Started getting keyword phrases")
start_time = time()
keywords = keywords.getKeyPhrases(input_file.text, stopwords, lemmatizer = lemmatize)
end_time = time()
input_file.keywords = keywords
if len(keywords) == 0:
print("No keywords were found for an input file \"{0}\"".format(input_file.path_txt))
exit(0)
retcode = subprocess.call(["python", "./pdf_import.py", pdf, pdf + ".txt"])
if (retcode != 0):
print("Error while parsing PDF file!")
exit(1)
end_time = time.time()
print("Parsing PDF took {0:.3f}".format(end_time - start_time), "seconds")
except OSError:
print("Error while trying to parse pdf file!")
exit(1)
#Getting words from a txt file
print("\nStarted parsing TXT, wait for a while...")
start_time = time.time()
text = split.get_list(input_file, enableComments = False)
end_time = time.time()
print("Parsing TXT took {0:.3f}".format(end_time - start_time), "seconds")
#Getting words for deleting
if (stopwords_file == ''):
stopwords = set()
pass
else:
#print("\nStarted parsing TXT with stopwords, wait for a while...")
start_time = time.time()
stopwords = split.get_list(stopwords_file, enableComments = True)
end_time = time.time()
print("\nParsing TXT with stopwords took {0:.3f}".format(end_time - start_time), "seconds")
stopwords = set(stopwords)
#Getting words from a txt file
print("\nStarted parsing TXT, wait for a while...")
start_time = time()
#text = split.get_list(input_file, enableComments = False)
text = split.get_text(input_file)
end_time = time()
print("Parsing TXT took {0:.3f}".format(end_time - start_time), "seconds")
#Getting words for deleting
if (stopwords_file == ''):
stopwords = set()
pass
else:
#print("\nStarted parsing TXT with stopwords, wait for a while...")
start_time = time()
stopwords = split.get_list(stopwords_file, enableComments = True)
end_time = time()
print("\nParsing TXT with stopwords took {0:.3f}".format(end_time - start_time), "seconds")
stopwords = set(stopwords)
print("\nStarted getting keyword phrases")
start_time = time()
keywords = keywords.getKeyPhrases(text, stopwords, lemmatizer = lemmatizer)
end_time = time()
print("Getting keyword phrases took {0:.3f}".format(end_time - start_time), "seconds")
if (output_file == ''):
print("\nKeywords (generated by RAKE):\n")
for key in keywords:
print(key[0])
else:
