static void Main(string[] args) { WebClient client = new WebClient(); client.Encoding = System.Text.Encoding.UTF8; var html = client.DownloadString("https://blog.csdn.net/czjnoe/article/details/106600070"); NSoup.Nodes.Document doc = NSoup.NSoupClient.Parse(html); //根据标签名获取节点 NSoup.Select.Elements metaElements = doc.GetElementsByTag("meta"); foreach (var item in metaElements) { } //根据id获取节点 NSoup.Nodes.Element headClassElements = doc.GetElementById("head"); //根据class获取节点 var headIdElements = doc.GetElementsByClass("fm").ToList(); foreach (var item in headIdElements) { } //根据属性名称获取节点 List <Element> attributeNameElements = doc.GetElementsByAttribute("class").ToList(); //根据属性值获取节点 List <Element> attributeValueElements = doc.GetElementsByAttributeValue("id", "su").ToList(); //根据jQuery选择器获取节点 var selectElments = doc.Select("#head").ToList(); }
/// <summary> /// 获得地址代码 /// </summary> private IDictionary <string, string> GetAddressCode() { string url = "http://www.mca.gov.cn/article/sj/xzqh/2020/2020/202003301019.html"; HttpClientHelper httpClient = new HttpClientHelper(); string html = httpClient.GetAsync(url).GetAwaiter().GetResult(); NSoup.Nodes.Document doc = NSoup.NSoupClient.Parse(html); IDictionary <string, string> hashtable = new Dictionary <string, string>(); var trs = doc.Select("tr[height=19]"); foreach (Element tr in trs) { var tb = tr.Select("td"); hashtable.Add(tb[1].Text(), tb[2].Text()); } return(hashtable); }
private static string ihVal(string key, Document doc) { return doc.Select("th:contains(" + key + ") + td").First.Text(); }