IOS使用正则表达式去掉html中的标签元素,获得纯文本
content是根据网址获得的网页源码字符串NSRegularExpression*regularExpretion=[NSRegularExpressionregularExpressionWithPattern:@"<[^>]*>|\n"options:0error:nil];content=[regularExpretionstringByReplacingMatchesInString:contentoptions:NSMatchingReportProgressrange:NSMakeRange(0, content.length)withTemplate:@"-"];//替换所有html和换行匹配元素为"-"regularExpretion=[NSRegularExpressionregularExpressionWithPattern:@"-{1,}"options:0error:nil] ;content=[regularExpretionstringByReplacingMatchesInString:contentoptions:NSMatchingReportProgressrange:NSMakeRange(0, content.length)withTemplate:@"-"];//把多个"-"匹配为一个"-"//根据"-"分割到数组NSArray*arr=[NSArrayarray];content=[NSStringstringWithString:content];arr = [contentcomponentsSeparatedByString:@"-"];NSMutableArray*marr=[NSMutableArrayarrayWithArray:arr];[marrremoveObject:@""];returnmarr;//正则去除网络标签-(NSString *)getZZwithString:(NSString *)string{NSRegularExpression *regularExpretion=[NSRegularExpression regularExpressionWithPattern:@"<[^>]*>|\n"options:0error:nil];string=[regularExpretion stringByReplacingMatchesInString:string options:NSMatchingReportProgress range:NSMakeRange(0, string.length) withTemplate:@""];return string;}
