ios 解析html内容

在 iOS 中通常加载 HTML 字符串有两种方式

通过 UILabel 加载富文本的方法加载 HTML 字符串
通过 WebView 加载 HTML 字符串

第一个解析html 去除标签取数据

//str为我们取出的html数据
NSString * str = [reponse[@"data"] objectForKey:@"gn_content"];
//将str转换成标准的html数据
str = [self htmlEntityDecode:str];
NSString *htmlString = [NSString stringWithFormat:@" \n"
                                    " \n"
                                    " \n"
                                    " \n"
                                    ""
                                    "%@"
                                    ""
                                    "",str];
            [webViewV loadHTMLString:htmlString baseURL:nil];
            //webViewV为我们创建的一个webView

//将 < 等类似的字符转化为HTML中的“<”等
- (NSString *)htmlEntityDecode:(NSString *)string
{
    string = [string stringByReplacingOccurrencesOfString:@""" withString:@"\""];
    string = [string stringByReplacingOccurrencesOfString:@"'" withString:@"'"];
    string = [string stringByReplacingOccurrencesOfString:@"<" withString:@"<"];
    string = [string stringByReplacingOccurrencesOfString:@">" withString:@">"];
    string = [string stringByReplacingOccurrencesOfString:@"&" withString:@"&"]; // Do this last so that, e.g. @"&lt;" goes to @"<" not @"<"

    return string;
}

第二篇借鉴

- (void)viewDidLoad {
    [super viewDidLoad];

1.UILabel 加载 HTML 字符串
NSString * str1 = @"<div>Google（中文名：谷歌），是一家美国的跨国科技企业。</div><div>Google由当时在斯坦福大学攻读理工博士的拉里·佩奇和谢尔盖·布卢姆共同创建，因此两人也被称为“Google Guys”。</div><div>1998年9月4日，Google以私营公司的形式创立，设计并管理一个互联网搜索引擎“Google搜索”。</div>";
NSString * str2 = @"<p><br></p>";
NSString * str3 = @"<p>qqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqqq</p>";
//1.将字符串转化为标准HTML字符串
    str1 = [self htmlEntityDecode:str1];
//2.将HTML字符串转换为attributeString
    NSAttributedString * attributeStr = [self attributedStringWithHTMLString:str1];

//3.使用label加载html字符串
    self.label.attributedText = attributeStr;

2.UIWebView 加载HTML字符串
    UIWebView * webView = [[UIWebView alloc]initWithFrame:CGRectMake(20, 300, self.view.frame.size.width - 40, 400)];
    [webView loadHTMLString:str1 baseURL:nil];
    [self.view addSubview:webView];
    self.webView = webView;
}

//将 < 等类似的字符转化为HTML中的“<”等 
- (NSString *)htmlEntityDecode:(NSString *)string
{
    string = [string stringByReplacingOccurrencesOfString:@""" withString:@"\""];
    string = [string stringByReplacingOccurrencesOfString:@"'" withString:@"'"];
    string = [string stringByReplacingOccurrencesOfString:@"<" withString:@"<"];
    string = [string stringByReplacingOccurrencesOfString:@">" withString:@">"];
    string = [string stringByReplacingOccurrencesOfString:@"&" withString:@"&"]; // Do this last so that, e.g. @"&lt;" goes to @"<" not @"<"

    return string;
}

//将HTML字符串转化为NSAttributedString富文本字符串
- (NSAttributedString *)attributedStringWithHTMLString:(NSString *)htmlString
{
    NSDictionary *options = @{ NSDocumentTypeDocumentAttribute : NSHTMLTextDocumentType,
                               NSCharacterEncodingDocumentAttribute :@(NSUTF8StringEncoding) };

    NSData *data = [htmlString dataUsingEncoding:NSUTF8StringEncoding];

    return [[NSAttributedString alloc] initWithData:data options:options documentAttributes:nil error:nil];
}

//去掉 HTML 字符串中的标签
- (NSString *)filterHTML:(NSString *)html
{
    NSScanner * scanner = [NSScanner scannerWithString:html];
    NSString * text = nil;
    while([scanner isAtEnd]==NO)
    {
        //找到标签的起始位置
        [scanner scanUpToString:@"<" intoString:nil];
        //找到标签的结束位置
        [scanner scanUpToString:@">" intoString:&text];
        //替换字符
        html = [html stringByReplacingOccurrencesOfString:[NSString stringWithFormat:@"%@>",text] withString:@""];
    }
    //    NSString * regEx = @"<([^>]*)>";
    //    html = [html stringByReplacingOccurrencesOfString:regEx withString:@""];
    return html;
}

注意

此处的字符串不是标准的标签的HTML字符串，所以我们首先要调用- (NSString )htmlEntityDecode:(NSString )string 方法将字符串转换成标准的HTML字符串，这样才可以进行HTML字符串的加载
实例的第二个字符串中的内容为空，当用 Label 加载的时候只是两行空白数据，此时可以调用- (NSString )filterHTML:(NSString )html 方法，去掉标签，将HTML字符串转换为常用的字符串样式