19 lines
573 B
Python
19 lines
573 B
Python
|
from jieba.analyse import textrank
|
||
|
|
|
||
|
|
with open(r"D:\小工具程序\pdf2md\output_directory\good_i.mmd", "r", encoding="utf8") as f:
|
||
|
|
lines = []
|
||
|
|
for i in f.readlines():
|
||
|
|
if i.strip():
|
||
|
|
lines.append(i.strip())
|
||
|
|
else:
|
||
|
|
lines.append(" ")
|
||
|
|
|
||
|
|
print("".join(lines))
|
||
|
|
|
||
|
|
sentences_list: list = lines
|
||
|
|
all_article = "".join(sentences_list) # 将所有的文本整合为一个大文本
|
||
|
|
keywords = textrank(all_article, topK=10, withWeight=True)
|
||
|
|
print('Text rank 结果展示：')
|
||
|
|
for word, weight in keywords:
|
||
|
|
print(word, ": ", str(weight))
|