Created
March 24, 2014 05:38
-
-
Save reee/9734697 to your computer and use it in GitHub Desktop.
Split a Doc into words and compare with a keywords list
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# coding:utf-8 | |
import os | |
import jieba | |
# Define where we put the files | |
source_dictionary = "/opt/ht/source" | |
keywords_file = "/opt/ht/keywords-new.txt" | |
result_file = "/opt/ht/result.txt" | |
# Convert the Keywords into a list | |
keywords_list = [] | |
f = file(keywords_file) | |
while True: | |
line = f.readline() | |
if len(line) == 0: | |
break | |
keywords_list.append(line) | |
# Deal With the source file | |
file_list = os.listdir(source_dictionary) | |
r_file = open(result_file, "w") | |
for files in file_list: | |
s_article = open(files).read() | |
s_sentence = s_article.split(u"。".encode("utf-8")) | |
for sentences in s_sentence: | |
words_list = list(jieba.cut(sentences,cut_all=False)) | |
result = list(set(words_list) & set(keywords_list)) | |
for words in result: | |
r_file.write("%s;" % words) | |
r_file.write("\n") | |
r_file.write("A New File Start") | |
r_file.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment