统计english article 的英文单词

2018-06-18 01:55:09来源:未知 阅读 ()

新老客户大回馈,云服务器低至5折

# -*- coding: utf-8 -*-

import string
def extend_word(text):
if text.find('\'') > 0:
old2new = dict()
words = text.split()
for word in words:
if word.find('\'') > 0:
parts = word.split('\'')
if parts[1] == 'm':
parts[1] = 'am'
elif parts[1] == 's':
parts[1] = 'is'
elif parts[1] == 're':
parts[1] = 'are'
elif parts[1] == 't':
parts[1] = 'not'
elif parts[1] == 've':
parts[1] = 'have'
elif parts[1] == 'll':
parts[1] = 'will'
elif parts[1] == 'd':
if words[words.index(word) +1] == 'better':
parts[1] = 'had'
else:
parts[1] = 'would'
if parts[0].endswith('n'):
parts[0] =parts[0][:-1]
old2new[word] = ' '.join(parts)
_text = text
for old_word in old2new.keys():
_text = _text.replace(old_word, old2new[old_word])
return _text


def show_in_order(record):
items = sorted(records.items(), key=lambda item:item[1], reverse=True)
for item in items:
print(item[0], item[1])

with open('1.txt', 'r') as file:
article = file.read()
no_pun_text = article
_punctuation = string.punctuation.replace('\'', '')
for pun in _punctuation:
no_pun_text = no_pun_text.replace(pun, '')
complete_text = extend_word(no_pun_text)
records = dict()
for word in complete_text.lower().split():
records[word] = records.get(word, 0) + 1
show_in_order(records)

标签:

版权申明:本站文章部分自网络,如有侵权,请联系:west999com@outlook.com
特别注意:本站所有转载文章言论不代表本站观点,本站所提供的摄影照片,插画,设计作品,如需使用,请与原作者联系,版权归原作者所有

上一篇:Dajngo-Xadmin 修改菜单摆放排序

下一篇:世界,你好!