/// <summary>
/// 辅助函数：从HTML中获得用户信息
/// </summary>
/// <param name="currentUserHtml">包含微博用户信息的HTML文本</param>
private void GetUserInfoFromHtml(string currentUserHtml)
{
//配置相关的过滤器
HasAttributeFilter nickNameFilter = new HasAttributeFilter("class", "name");
HasAttributeFilter remarkNameFilter = new HasAttributeFilter("class", "CH");
HasAttributeFilter linkUrlFilter = new HasAttributeFilter("class", "pf_lin S_link1");
HasAttributeFilter selfIntroFilter = new HasAttributeFilter("class", "pf_intro bsp");
HasAttributeFilter tagsFilter = new HasAttributeFilter("class", "S_func1");
HasAttributeFilter profileFilter = new HasAttributeFilter("class", "tags");
Lexer lexer = new Lexer(currentUserHtml);
Parser parser = new Parser(lexer);
//获取微博名
NodeList nickNameNodeList = parser.ExtractAllNodesThatMatch(nickNameFilter);
if (nickNameNodeList.Size() == 1)
{
user.NickName = ((Span)nickNameNodeList[0]).ToPlainTextString();
}
else
{
Console.WriteLine("判断微博名的标准出错！");
}
//注意此处：如果要重复使用parser，一定要在本次使用“完”、下次使用前调用reset，否则会出错
parser.Reset();
//获取备注名称
NodeList remarkNameNodeList = parser.ExtractAllNodesThatMatch(remarkNameFilter);
if (remarkNameNodeList.Size() == 1 && remarkNameNodeList[0].GetType().Equals(typeof(Span)))
{
string str = ((Span)remarkNameNodeList[0]).ToPlainTextString();
//去掉头尾的括号
user.RemarkName = str.Substring(1, str.Length - 2);
}
else
{
Console.WriteLine("判断微博备注名称的标准出错！");
}
parser.Reset();
//获取微博链接地址
NodeList linkUrlNodeList = parser.ExtractAllNodesThatMatch(linkUrlFilter);
if (linkUrlNodeList.Size() == 1 && linkUrlNodeList[0].GetType().Equals(typeof(ATag)))
{
user.LinkURL = ((ATag)linkUrlNodeList[0]).StringText;
}
else
{
Console.WriteLine("判断微博链接地址的标准出错！");
}
parser.Reset();
//获取自我描述
NodeList selfIntroNodeList = parser.ExtractAllNodesThatMatch(selfIntroFilter);
if (selfIntroNodeList.Size() == 1 && selfIntroNodeList[0].Children[1].GetType().Equals(typeof(Span)))
{
user.SelfIntroduction = ((Span)selfIntroNodeList[0].Children[1]).GetAttribute("TITLE");
}
else
{
Console.WriteLine("判断自我描述的标准出错！");
}
parser.Reset();
//获取标签
NodeList tagsNodeList = parser.ExtractAllNodesThatMatch(tagsFilter);
string str2 = "";
for (int i = 0; i < tagsNodeList.Size(); i++)
{
if (tagsNodeList[i].GetType().Equals(typeof(Span)))
{
str2 += ((Span)tagsNodeList[i]).ToPlainTextString() + " ";
}
}
user.Tags = str2;
parser.Reset();
//获取属性信息
NodeList profileNodeList = parser.ExtractAllNodesThatMatch(profileFilter);
if (profileNodeList.Size() == 1)
{
//通过分析发现，有用的信息均处于<a>标记中，所以按<a>标记取。然后再分析是其中的文本还是<em>中的title
NodeClassFilter aTagFilter = new NodeClassFilter(typeof(ATag));
NodeList profileList = profileNodeList[0].Children.ExtractAllNodesThatMatch(aTagFilter, true);
for (int j = 0; j < profileList.Size(); j++)
{
ATag aTag = (ATag)profileList[j];
if (aTag.Attributes.Contains("TITLE"))
{
user.Profile += aTag.GetAttribute("TITLE") + " ";
}
else
{
//遇到含有node-type="infoSlide"的节点说明所有属性遍历结束
if (aTag.Attributes.Contains("NODE-TYPE") && aTag.GetAttribute("NODE-TYPE").Equals("infoSlide"))
{
break;
}
else
{
//包含<em>子节点的情况
if (aTag.Children[0].GetType().Equals(typeof(TagNode)))
{
TagNode tagNode = (TagNode)aTag.Children[0];
user.Profile += tagNode.GetAttribute("TITLE") + " ";
}
else
{
//直接把<a>标记包含的文本输出
user.Profile += aTag.StringText + " ";
}
}
}
}
}
else
{
Console.WriteLine("判断用户属性信息的标准出错！");
}
}
static void GetSubtitleHtmlFromFile()
{
List<List<NodeFilter>> filters = new List<List<NodeFilter>>();
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters.Add(new List<NodeFilter>());
filters[0].Add(new HasAttributeFilter("class", "xl29"));
filters[0].Add(new HasAttributeFilter("class", "xl31"));
filters[0].Add(new HasAttributeFilter("class", "xl32"));
filters[0].Add(new HasAttributeFilter("class", "xl33"));
filters[1].Add(new HasAttributeFilter("class", "xl25"));
filters[1].Add(new HasAttributeFilter("class", "xl26"));
filters[1].Add(new HasAttributeFilter("class", "xl27"));
filters[1].Add(new HasAttributeFilter("class", "xl28"));
filters[2].Add(new HasAttributeFilter("class", "xl27"));
filters[2].Add(new HasAttributeFilter("class", "xl28"));
filters[2].Add(new HasAttributeFilter("class", "xl29"));
filters[2].Add(new HasAttributeFilter("class", "xl30"));
filters[3].Add(new HasAttributeFilter("class", "xl27"));
filters[3].Add(new HasAttributeFilter("class", "xl28"));
filters[3].Add(new HasAttributeFilter("class", "xl29"));
filters[3].Add(new OrFilter(new HasAttributeFilter("class", "xl31"), new HasAttributeFilter("class", "xl30")));
filters[4].Add(new HasAttributeFilter("class", "xl27"));
filters[4].Add(new HasAttributeFilter("class", "xl28"));
filters[4].Add(new HasAttributeFilter("class", "xl29"));
filters[4].Add(new HasAttributeFilter("class", "xl30"));
filters[5].Add(new HasAttributeFilter("class", "xl33"));
filters[5].Add(new HasAttributeFilter("class", "xl32"));
filters[5].Add(new HasAttributeFilter("class", "xl30"));
filters[5].Add(new HasAttributeFilter("class", "xl28"));
filters[6].Add(new HasAttributeFilter("class", "xl29"));
filters[6].Add(new HasAttributeFilter("class", "xl30"));
filters[6].Add(new HasAttributeFilter("class", "xl31"));
filters[6].Add(new HasAttributeFilter("class", "xl32"));
filters[7].Add(new HasAttributeFilter("class", "xl28"));
filters[7].Add(new HasAttributeFilter("class", "xl24"));
filters[7].Add(new HasAttributeFilter("class", "xl30"));
filters[7].Add(new HasAttributeFilter("class", "xl31"));
DirectoryInfo directory = new DirectoryInfo(@"D:\Download\魔戒三部曲电影导演评论字幕\mht");
int count = 0;
foreach (FileInfo file in directory.GetFiles("*.htm"))
{
StreamReader reader = new StreamReader(file.FullName);
string htmlContent = reader.ReadToEnd();
reader.Close();
string fileName = file.Name.Substring(0, file.Name.IndexOf('.'));
Lexer lexer = new Lexer(htmlContent);
Parser parser = new Parser(lexer);
//红色的是演员解说
NodeList redNodeList = parser.ExtractAllNodesThatMatch(filters[count][0]);
GetSubtitleFromHtml(redNodeList, fileName + "_演员解说");
//黄色的是导演编剧解说
parser.Reset();
NodeList yelloNodeList = parser.ExtractAllNodesThatMatch(filters[count][1]);
GetSubtitleFromHtml(yelloNodeList, fileName + "_导演编剧解说");
//蓝色的是特技制作组
parser.Reset();
NodeList blueNodeList = parser.ExtractAllNodesThatMatch(filters[count][2]);
GetSubtitleFromHtml(blueNodeList, fileName + "_特技制作组解说");
//绿色的是幕后制作团队
parser.Reset();
NodeList greenNodeList = parser.ExtractAllNodesThatMatch(filters[count][3]);
GetSubtitleFromHtml(greenNodeList, fileName + "_幕后制作团队解说");
count++;
}
}