如何在保持 html 格式的同时从服务器上的文件中读取 html 格式的文本

Question

我正在尝试将标签的文本设置为从服务器上的文本文件中提取的字符串。此文件中的文本为 HTML 格式。有没有办法从这个文件中读取文本并将其显示在我的标签中，同时保持 HTML 格式？

例如，如果文件中有一行如<b>hello world!</b>，则标签将以粗体显示hello world!。

Answer 1

NSAttributedText 就是你要找的东西！

这里是实现

NSData *htmlData = [NSData dataWithContentsOfURL:url];
NSAttributedString *attrString = [[NSAttributedString alloc] initWithData:htmlData options:@{NSDocumentTypeDocumentAttribute: NSHTMLTextDocumentType, NSCharacterEncodingDocumentAttribute: @(NSUTF8StringEncoding)} documentAttributes:nil error:nil];

[yourLabel setAttributedText:attrString];

Answer 2

Google 有一个完美的解码 HTML 实体的库。

您可以使用扩展 google 实现的另一个 perfect 类将 html 转换为纯文本。

如果你想要一个 Swift 实现，你可以创建一个字符串扩展：

extension String  {
    static func stringByRemovingHTMLEntities(string: String) -> String {
        var result = string

        result = result.stringByReplacingOccurrencesOfString("<p>", withString: "\n\n", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("</p>", withString: "", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#8211;", withString: "-", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#8220;", withString: "\"", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#8221;", withString: "\"", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("<i>", withString: "", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("</i>", withString: "", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#38;", withString: "&", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#62;", withString: ">", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#x27;", withString: "'", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#x2F;", withString: "/", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&quot;", withString: "\"", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&#60;", withString: "<", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&lt;", withString: "<", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&gt;", withString: ">", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("&amp;", withString: "&", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("<pre><code>", withString: "", options: .CaseInsensitiveSearch, range: nil)
        result = result.stringByReplacingOccurrencesOfString("</code></pre>", withString: "", options: .CaseInsensitiveSearch, range: nil)

        var regex = NSRegularExpression(pattern: "<a[^>]+href=\"(.*?)\"[^>]*>.*?</a>",
            options: NSRegularExpressionOptions.CaseInsensitive, error: nil)
        result = regex!.stringByReplacingMatchesInString(result, options: nil, range: NSMakeRange(0, result.utf16Count), withTemplate: "$1")

        return result
    }

    func stringByDecodingHTMLEntities() -> String? {
        var r: NSRange
        let pattern = "<[^>]+>"
        var s = self.stringByDecodingHTMLEscapeCharacters()
        r = (s as NSString).rangeOfString(pattern, options: NSStringCompareOptions.RegularExpressionSearch)
        while (r.location != NSNotFound) {
            s = (s as NSString).stringByReplacingCharactersInRange(r, withString: " ")
            r = (s as NSString).rangeOfString(pattern, options: NSStringCompareOptions.RegularExpressionSearch)
        }
        return s.stringByReplacingOccurrencesOfString("  ", withString: " ")
    }

    func stringByDecodingHTMLEscapeCharacters() -> String {
        var s = self.stringByReplacingOccurrencesOfString("&quot;", withString: "\"")
        s = s.stringByReplacingOccurrencesOfString("&apos;", withString: "'")
        s = s.stringByReplacingOccurrencesOfString("&amp;", withString: "&")
        s = s.stringByReplacingOccurrencesOfString("&lt;", withString: "<")
        s = s.stringByReplacingOccurrencesOfString("&gt;", withString: ">")
        s = s.stringByReplacingOccurrencesOfString("&#39;", withString: "'")
        s = s.stringByReplacingOccurrencesOfString("&ldquot;", withString: "\"")
        s = s.stringByReplacingOccurrencesOfString("&rdquot;", withString: "\"")
        s = s.stringByReplacingOccurrencesOfString("&nbsp;", withString: " ")
        s = s.stringByReplacingOccurrencesOfString("&aacute;", withString: "á")
        s = s.stringByReplacingOccurrencesOfString("&eacute;", withString: "é")
        s = s.stringByReplacingOccurrencesOfString("&iacute;", withString: "í")
        s = s.stringByReplacingOccurrencesOfString("&oacute;", withString: "ó")
        s = s.stringByReplacingOccurrencesOfString("&uacute;", withString: "ú")
        s = s.stringByReplacingOccurrencesOfString("&ntilde;", withString: "ñ")
        s = s.stringByReplacingOccurrencesOfString("&#8217;", withString: "'")

        return s
    }
}