Question

是否可以只获取通过URL获取的HTML字符串的一部分？

以下示例代码：

  let myURLString = "https://myUrl.something"
        guard let myURL = NSURL(string: myURLString) else {
            print("Error: \(myURLString) doesn't seem to be a valid URL")
            return
        }
        do {
            let myHTMLString = try String(contentsOf: myURL as URL)
            let htmlString = String(myHTMLString)
            print("HTML: \(myHTMLString)")
        } catch let error as NSError {
            print("Error: \(error)")
        }

我想将标记<h3 class="post-title">中的内容添加到</h3>。

我知道我应该使用正则表达式，但我真的不知道如何以正确的方式设置它。我试过这样的事情：

  let myURLString = "https://www.fvgtech.it/category/podcast/"
        guard let myURL = NSURL(string: myURLString) else {
            print("Error: \(myURLString) doesn't seem to be a valid URL")
            return
        }
        do {
            let myHTMLString = try String(contentsOf: myURL as URL)
            let htmlString = String(myHTMLString)

            if let match = htmlString.range(of: "(<h3.+)", options: .regularExpression) {
                print("Found",htmlString.substring(with: match))
            }


            print("HTML: \(myHTMLString)")
        } catch let error as NSError {
            print("Error: \(error)")
        }

但它只打印<h3 class="post-title">而不是中间的打印。提前致谢！

Answer 1

我们需要在start String和end String之间搜索所有子字符串。参见String of Extension

 let myURLString = "https://www.fvgtech.it/category/podcast/"
    guard let myURL = NSURL(string: myURLString) else {
        print("Error: \(myURLString) doesn't seem to be a valid URL")
        return
    }
    do {
        let myHTMLString = try String(contentsOf: myURL as URL)
        let htmlString = String(myHTMLString)
        print(htmlString.allStringsBetween("<h3 class=\"post-title\">", andString: "</h3>"))

    } catch let error as NSError {
        print("Error: \(error)")
    }

字符串扩展

extension String{

  func allStringsBetween(start: String, end: String) -> [Any] {
            var strings = [Any]()
            var startRange: NSRange = (self as NSString).range(of: start)

            while true {
                if startRange.location != NSNotFound {
                    var targetRange = NSRange()
                    targetRange.location = startRange.location + startRange.length
                    targetRange.length = self.count - targetRange.location
                    let endRange: NSRange = (self as NSString).range(of: end, options: [], range: targetRange)
                    if endRange.location != NSNotFound {
                        targetRange.length = endRange.location - targetRange.location
                        strings.append((self as NSString).substring(with: targetRange))
                        var restOfString =  NSRange()
                        restOfString.location = endRange.location + endRange.length
                        restOfString.length = self.count - restOfString.location
                        startRange = (self as NSString).range(of: start, options: [], range: restOfString)
                    }
                    else {
                        break
                    }
                }
                else {
                    break
                }

            }
            return strings
        }

    }

在字符串Swift之间拆分HTML字符串

1 个答案: