/// <summary>
/// 添加爬虫实体类
/// </summary>
/// <typeparam name="T">爬虫实体类的类型, 必须继承自 ISpiderEntity</typeparam>
/// <param name="targetUrlsExtractor">目标链接的解析、筛选器</param>
/// <param name="dataHandler">对解析的结果进一步加工操作</param>
public void AddEntityType <T>(ITargetRequestExtractor targetUrlsExtractor, IDataHandler dataHandler) where T : new()
{
CheckIfRunning();
var processor = new EntityProcessor <T>(UseEntityModelExtractor ? null : new ModelExtractor(), targetUrlsExtractor, dataHandler);
AddPageProcessors(processor);
}
/// <summary>
/// 构造方法
/// </summary>
/// <param name="extractor">爬虫实体的解析器</param>
/// <param name="targetRequestExtractor">目标链接的解析、筛选器</param>
/// <param name="dataHandlers">对解析的结果进一步加工操作</param>
public EntityProcessor(IModelExtractor extractor = null, ITargetRequestExtractor targetRequestExtractor = null, params IDataHandler[] dataHandlers)
: base(new ModelDefinition <T>(), extractor ?? new ModelExtractor <T>(), targetRequestExtractor, dataHandlers)
{
}
/// <summary>
/// 构造方法
/// </summary>
/// <param name="model">数据模型</param>
/// <param name="extractor">模型解析器</param>
/// <param name="targetRequestExtractor">目标链接的解析器</param>
/// <param name="dataHandlers">数据处理器</param>
public ModelProcessor(IModel model, IModelExtractor extractor = null, ITargetRequestExtractor targetRequestExtractor = null,
params IDataHandler[] dataHandlers)
{
Model = model ?? throw new ArgumentNullException(nameof(model));
Extractor = extractor ?? new ModelExtractor();
if (targetRequestExtractor != null)
{
TargetUrlsExtractor = targetRequestExtractor;
}
RegionAndPatternTargetRequestExtractor regionAndPatternTargetUrlsExtractor;
if (TargetUrlsExtractor == null)
{
regionAndPatternTargetUrlsExtractor = new RegionAndPatternTargetRequestExtractor();
TargetUrlsExtractor = regionAndPatternTargetUrlsExtractor;
}
else
{
regionAndPatternTargetUrlsExtractor = TargetUrlsExtractor as RegionAndPatternTargetRequestExtractor;
}
if (regionAndPatternTargetUrlsExtractor == null)
{
return;
}
if (Model.TargetRequestSelectors != null && Model.TargetRequestSelectors.Any())
{
foreach (var targetUrlsSelector in Model.TargetRequestSelectors)
{
var patterns = targetUrlsSelector.Patterns?.Select(x => x?.Trim()).Distinct().ToArray();
var xpaths = targetUrlsSelector.XPaths?.Select(x => x?.Trim()).Distinct().ToList();
if (xpaths == null && patterns == null)
{
throw new SpiderException("Region xpath and patterns should not be null both");
}
if (xpaths != null && xpaths.Count > 0)
{
foreach (var xpath in xpaths)
{
regionAndPatternTargetUrlsExtractor.AddTargetUrlExtractor(xpath, patterns);
}
}
else
{
if (patterns != null && patterns.Length > 0)
{
regionAndPatternTargetUrlsExtractor.AddTargetUrlExtractor(null, patterns);
}
}
if (targetUrlsSelector.ExcludePatterns != null)
{
foreach (var p in targetUrlsSelector.ExcludePatterns)
{
regionAndPatternTargetUrlsExtractor.ExcludeTargetUrlPatterns.Add(new Regex(p));
}
}
}
}
if (dataHandlers != null)
{
foreach (var datahandler in dataHandlers)
{
if (datahandler != null)
{
_dataHandlers.Add(datahandler);
}
}
}
}
/// <summary>
/// Construct a <see cref="TargetRequestHandler"/> instance.
/// </summary>
/// <summary xml:lang="zh-CN">
/// 构造方法
/// </summary>
/// <param name="targetRequestExtractor">目标链接解析器 <see cref="ITargetRequestExtractor"/></param>
/// <param name="extractByProcessor">Processor是否还需要执行目标链接解析工作(Should <see cref="IPageProcessor"/> continue to execute <see cref="ITargetRequestExtractor"/>)</param>
public TargetRequestHandler(ITargetRequestExtractor targetRequestExtractor, bool extractByProcessor = false)
{
_targetUrlsExtractor = targetRequestExtractor ?? throw new ArgumentNullException(nameof(targetRequestExtractor));
_extractByProcessor = extractByProcessor;
}
/// <summary>
/// 添加爬虫实体类
/// </summary>
/// <typeparam name="T">爬虫实体类的类型, 必须继承自 ISpiderEntity</typeparam>
/// <param name="targetUrlsExtractor">目标链接的解析、筛选器</param>
public void AddEntityType <T>(ITargetRequestExtractor targetUrlsExtractor) where T : new()
{
AddEntityType <T>(targetUrlsExtractor, null);
}
