[Python Study Notes]字符串处理技巧(持续更新)

‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘
>>文件: 字符串处理.py
>>作者: liu yang
>>邮箱: liuyang0001@outlook.com
>>博客: www.cnblogs.com/liu66blog

‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘‘

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import sys, os

# 1.字符串的连接和合并
# 相加 //两个字符串可以很方便的通过‘+‘连接起来
str1=‘123‘
str2=‘456‘
str3=str1+str2
print(str3)
# -----------输出----------------------
# 123456
# ------------------------------------

# 合并//用join方法
url=[‘www‘,‘cnblog‘,‘com/liu66blog‘]
print(‘.‘.join(url))
# -----------输出----------------------
# www.cnblog.com/liu66blog
# ------------------------------------


# 2.字符串的切片和相乘
# 相乘//比如写代码的时候要分隔符，用python很容易实现
Separator=‘*‘*30
print(Separator)
# -----------输出----------------------
# ******************************
# ------------------------------------

# 切片操作
url=‘www.cnblogs.com/liu66blog‘
# 取下标0-15个字符
print(url[0:16])
# 取下标16-最后一个
print(url[16:])
# 取倒数第四个到最后
print(url[-4:])
# 复制字符串
print(url[::])
# -----------输出----------------------
# www.cnblogs.com/
# liu66blog
# blog
# www.cnblogs.com/liu66blog
# ------------------------------------


# 3.字符串的分割
# 普通的分割，用split
# split只能做非常简单的分割，而且不支持多个分隔
url=‘www.cnblogs.com/liu66blog‘
url_list=url.split(‘.‘)
print(url_list)
# -----------输出----------------------
# [‘www‘, ‘cnblogs‘, ‘com/liu66blog‘]
# ------------------------------------

# 复杂的分割
# r表示不转义,分隔符可以是;或者,或者/,或者空格后面跟0个多个额外的空格，然后按照这个模式去分割
url=‘www.cnblogs.com/liu66blog‘
import re
url_list=re.split(r‘[.;/]\s*‘,url)
print(url_list)
# -----------输出----------------------
# [‘www‘, ‘cnblogs‘, ‘com‘, ‘liu66blog‘]
# ------------------------------------


# 4.字符串的开头和结尾的处理
#  比方我们要查一个名字是以什么开头或者什么结尾
url=‘www.cnblogs.com/liu66blog‘
result=url.endswith(‘blog‘)
print(result)
result=url.startswith(‘ww.‘)
print(result)
# -----------输出----------------------
# True
# False
# ------------------------------------


# 5.字符串的查找和匹配
# 一般查找
# 我们可以很方便的在长的字符串里面查找子字符串，会返回子字符串所在位置的索引, 若找不到返回-1
url=‘www.cnblogs.com/liu66blog‘
result=url.find(‘liu66‘)
print(result)
result=url.find(‘liuyang‘)
print(result)
# -----------输出----------------------
# 16
# -1
# ------------------------------------

# 复杂查找
data_str=‘2018/2/22‘
result=re.match(r‘\d+/\d+/\d+‘,data_str)
if result:
    print(‘ok,存在‘)
# -----------输出----------------------
# ok,存在
# ------------------------------------


# 6.字符串的替换
# 普通的替换//用replace就可以
url=‘www.cnblogs.com/liu66blog‘
url_new=url.replace(‘www.‘,‘‘)
print(url_new)
# -----------输出----------------------
# cnblogs.com/liu66blog
# ------------------------------------

# 复杂的替换 利用re.sub函数
url=‘www.cnblogs.com/liu66blog‘
url_new=re.sub(r‘\d\d‘,‘00‘,url)
print(url_new)
# -----------输出----------------------
# cnblogs.com/liu00blog
# ------------------------------------


# 7.字符串中去掉一些字符
# 去除空格//对文本处理的时候比如从文件中读取一行，然后需要去除每一行的两侧的空格，table或者是换行符
url=‘  www.cnblogs.com/liu66blog  ‘
url_new=url.strip()
print(url_new)

# 复杂的文本清理,可以利用str.translate，
# 先构建一个转换表，table是一个翻译表，表示把‘w‘转成大写的‘W‘,
# 然后在old_str里面去掉‘liu66‘,然后剩下的字符串再经过table 翻译
# Python3.4已经没有string.maketrans()了，取而代之的是内建函数:
# bytearray.maketrans()、bytes.maketrans()、str.maketrans()
url=‘www.cnblogs.com/liu66blog‘

# 创建翻译表
instr=‘w‘
outstr=‘W‘
table=str.maketrans(instr,outstr)

url_new=url.translate(table)
print(url_new)
# -----------输出----------------------
# WWW.cnblogs.com/liu66blog
# ------------------------------------

# 8.找最长的单词
txt=‘Python is a programming language that lets you work more quickly and integrate your systems more effectively. ‘     ‘You can learn to use Python and see almost immediate gains in productivity and lower maintenance costs. ‘     ‘Learn more about Python..‘
# 使用空格分隔
txt_list=txt.split(‘ ‘)
# 使用sorted()函数按照单词长度排序
txt_list_new=sorted(txt_list,key=lambda x:len(x),reverse=True)
# 定义一个空列表,存储最长的
longest_word=[]
# 判断后面的单词长度
for i,word in enumerate(txt_list_new):
    if len(txt_list_new[i])<len(txt_list_new[0]):
        break
    else:
        longest_word.append(txt_list_new[i])
print(longest_word)
# -----------输出----------------------
# [‘effectively.‘, ‘productivity‘]
# ------------------------------------


# 9.找出指定长度的单词
len_4_word=filter(lambda x:5>len(x)>=4,txt_list)
# 注意python3 filter返回不再是列表 需要自己转换!!
len_4_word_list=list(len_4_word)
# 转换成去重元祖
len_4_word_tuple=tuple(set(len_4_word_list))
print(len_4_word_list)
print(len_4_word_tuple)
# -----------输出----------------------
# [‘that‘, ‘lets‘, ‘work‘, ‘more‘, ‘your‘, ‘more‘, ‘more‘]
# (‘your‘, ‘more‘, ‘lets‘, ‘that‘, ‘work‘)
# ------------------------------------


# 10.使用最频繁的单词
from collections import Counter
# most_common(x) x代表列举的个数
print(Counter(txt_list).most_common(6))
# -----------输出----------------------
# [(‘more‘, 3), (‘and‘, 3), (‘Python‘, 2), (‘is‘, 1), (‘a‘, 1), (‘programming‘, 1)]
# ------------------------------------


# 11.列出所有大写的单词
title_words_list=[]
for i in txt_list:
    if i.istitle():
        title_words_list.append(i)
# 得到去重字典
title_words_dict=set(title_words_list)
print(title_words_list)
print(title_words_dict)
# -----------输出----------------------
# [‘Python‘, ‘You‘, ‘Python‘, ‘Learn‘, ‘Python..‘]
# {‘Python..‘, ‘Learn‘, ‘Python‘, ‘You‘}
# ------------------------------------


# 12.未完待续...