python文本分析基础(1)

ounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(lineounter(line# 字符串类型连续字符序列，可以表示计算机所能识别的一切字符 # 字符串的界定符：单引号、双引号、三引号 # python中的文本分析实际上是对字符串的处理 # city='北京' # address='北京中国人民大学' # 三引号用于定义多行字符串 info='''地址：北京海淀区苏州街中国人民大学    收件人：han     手机号:12345678987 ''' info2="""地址：北京清华大学     收件人      手机号 """ print(info) print(info2) # 转移字符(特殊的字符串)# # \n换行符 # \t水平制表位，用于横向跳到下一个制表位 # \"双引号 # \'单引号 # \\一个反斜杠 print("北京") print("欢迎你") print('北京\n欢迎你')print('北京\n欢迎\n你') print('北京\t欢迎你') print('北京北京\t欢迎你') print('hellotooo') print('hello\ttooo')#hello是五个字符，一个制表位是8个字符，8-5=3 print('老师说：\'要用功\'') print('老师说：\"要用功读书\"')# # 原字符，是转义字符失效的符号r或R print(r'北京\n欢迎你') print(R'北京\n欢迎你')# 字符串的索引和切片# # 字符串又称为有序的的字符序列，对字符串中的某个字符的检索称为索引# # helloworld这个字符正向数是从0开始，反向数是从-1开始的# # 应用字符串切片string索引[]正向索引和负向索引# # 字符串的索引 s='helloruc' print(s[0],s[-8]) print('北京欢迎你'[-1]) print(s[:5])#5之前得 print(s[3:])#取3以后得 print(s[-3:-1])#不包含-1# # 字符串得常用操作# '''# 字符串常用操作符# x+y  将zifuchuang# x*n  复制n次字符串# x in s 如果x是s的子串，结果为True ,否则结果为False# ''' x = '2025年' y = '中国人民大学' print(x+y) print(x*10) print('20' in x) print('20' in y)# # 字符串编码和转换# # encode与decode# # str.encodestring = "好雨知时节" print("原字符串：",string) print("使用GB2312编码后：",string.encode('gb2312')) print("使用utf-8编码后：",string.encode('utf-8')) # 解码decode print("使用utf-8编码后：",string.encode('utf-8').decode('utf-8')) var11 ="我喜欢PYTHON"var12=var11.encode('utf-8',errors="ignore") var13=var12.decode() print(var13)# 字符串的分隔和合并str1='文科生学 python,真是 太难了，如何学'list1=str1.split()#如果不指定分割符号，默认以文本中的空格为分割符号list2=str1.split("，")print(list1)print(list2)print(len(list1))#针对一段文本进行切割全国乡村旅游重点村”是由文化和旅游部与国家发展改革委联合遴选并公布的乡村旅游名录。其核心目的是贯彻落实乡村振兴战略，在旅游规划、创意下乡、人才培训、宣传推广、金融支持、项目对接等方面予以支持，扶持一批文旅融合、生态环境优美、带动效益明显的村庄，从而引领全国乡村旅游的高质量发展。import restr13='全国乡村旅游重点村”是由文化和旅游部与国家发展改革委联合遴选并公布的乡村旅游名录。其核心目的是贯彻落实乡村振兴战略，在旅游规划、创意下乡、人才培训、宣传推广、金融支持、项目对接等方面予以支持，扶持一批文旅融合、生态环境优美、带动效益明显的村庄，从而引领全国乡村旅游的高质量发展。'import relist2=re.split("。|！|？",str13)  #针对一段文本，按照句号，问号或者其他符号进行切割