def create_index_from_dir(stored_docs_dir,index_dir):
indexer = Indexer()
for filename in os.listdir(stored_docs_dir):
opened_file = open(os.path.join(stored_docs_dir,filename))
doc_raw = html_to_text(opened_file.read())
parsed_doc = to_doc_terms(doc_raw)
indexer.add_document(b16decode(filename),parsed_doc)
indexer.store_on_desk(index_dir)
评论列表
文章目录