def process_resume(email_data):
path = download_attachment(email_data["attachment_url"])
text = convert_pdf_to_txt(path)
text = text.rstrip()
fp = file("temp.txt", "wb")
fp.write(text)
fp.close()
resume_text_list = getresumecontent("temp.txt")
resume_text = ';'.join(resume_text_list)
clean_text = Stopwords.removeStopWords(
unicode(resume_text, encoding="utf-8"))
keywords = extract_keywords(resume_text)
workex = workexfinder("temp.txt")
lines = workex.split(";;")
entity_names = []
string = "".join(lines)
tokens = nltk.word_tokenize(string)
tagged = nltk.pos_tag(tokens)
entities = nltk.chunk.ne_chunk(tagged)
for entity in entities:
entity_names.extend(extract_entity_names(entity))
retval = {}
retval["keywords"] = keywords
retval["workex"] = entity_names
return retval
