正则表达式实例1

正则表达式

r'\t'使用原始字符串来表示它们,模式元素(r'\t'，等价于 '\\t')匹配相应的特殊字符。
re.S  使 . 匹配包括换行在内的所有字符
(.*?) 匹配分组，(.*? )后面多个问号，代表非贪婪模式，也就是说只匹配符合条件的最少字符，分组返回的是列表

ss = re.findall(r"</strong>(.*?)<br/><br/>",strpp,re.S)

实例1：

itemleft = re.search(r'(Item\s+offered)',desc,re.I|re.S)fitleft = re.search(r'(Fits?\s+models?\s+&\s+years?)',desc,re.I) # 获得匹配第一个字符的索引

实例2：

#将描述的多空格换成空格,|换成空格 将-前后空格去掉desc = re.sub(r"\s+", " ", desc)   #\s匹配一个空白符desc = re.sub("\|", " ", desc)desc = re.sub("\s*-\s*", "-", desc, re.I)# print(desc)desc = re.sub("(folder)|(folding)", "folding", desc, re.I) #re.I忽略大小写desc = re.sub("(Manually)|(Manual)", "Manual", desc, re.I)desc = re.sub("(telescopic)|(Telescoping)", "Telescoping", desc, re.I)

se = re.search(r"(Manual folding)|(Power Folding: No)|(Manual [\s\w]*? folding)", desc, re.I) #w匹配任意字母数字字符或下划线字符

替换

df = df.replace({"desc":{"\|":"\\n"}},regex=True)df = df.replace({"fits":{"\|":"\\n"}},regex=True)

#数据库里的描述 & & 两种形式的数据都有，强制将&转换为&df = df.replace({"description":{"\B&\B":"&"}},regex=True)  # html转义字符

model = str(model).replace("&", "&") #因为model town & country的特殊性，需要特殊处理res = "-\d{4} "+ str(model)

实例3：

a = re.search(r'(door\b)|(cab\b)|(sedan\b)|(doors\b)',fitment) #\b 边界

s_fitment = s_fitment.replace("|","\n") #换行，方便后面正则表达式匹配

实例4：

desc = str(df.loc[i,"new_description_new"]) sql转义字符desc = desc.replace("\\","\\\\")desc = desc.replace("\'","\\\'")desc = desc.replace("\"","\\\"")desc = desc.replace("\n\n","\\n")desc = desc.replace("\r\n","\\n")desc = desc.replace("\n","\\n")desc = desc.replace("\t","\\t")