/// <summary>
/// Initializes a new instance of NReadabilityTranscoder. Allows setting all options.
/// </summary>
/// <param name="dontStripUnlikelys">Determines whether elements that are unlikely to be a part of main content will be removed.</param>
/// <param name="dontNormalizeSpacesInTextContent">Determines whether spaces in InnerText properties of elements will be normalized automatically (eg. whether double spaces will be replaced with single spaces).</param>
/// <param name="dontWeightClasses">Determines whether 'weight-class' algorithm will be used when cleaning content.</param>
/// <param name="readingStyle">Styling for the extracted article.</param>
/// <param name="readingMargin">Margin for the extracted article.</param>
/// <param name="readingSize">Font size for the extracted article.</param>
private NReadabilityTranscoder(
bool dontStripUnlikelys,
bool dontNormalizeSpacesInTextContent,
bool dontWeightClasses,
ReadingStyle readingStyle,
ReadingMargin readingMargin,
ReadingSize readingSize)
{
_dontStripUnlikelys = dontStripUnlikelys;
_dontNormalizeSpacesInTextContent = dontNormalizeSpacesInTextContent;
_dontWeightClasses = dontWeightClasses;
_readingStyle = readingStyle;
_readingMargin = readingMargin;
_readingSize = readingSize;
_sgmlDomBuilder = new SgmlDomBuilder();
_sgmlDomSerializer = new SgmlDomSerializer();
_elementsScores = new Dictionary<XElement, float>();
}
/// <summary>
/// Initializes a new instance of NReadabilityTranscoder. Allows setting reading options.
/// </summary>
/// <param name="readingStyle">Styling for the extracted article.</param>
/// <param name="readingMargin">Margin for the extracted article.</param>
/// <param name="readingSize">Font size for the extracted article.</param>
public NReadabilityTranscoder(ReadingStyle readingStyle, ReadingMargin readingMargin, ReadingSize readingSize)
: this(false, false, false, readingStyle, readingMargin, readingSize)
{
}
private string GetReadingStyleClass(ReadingStyle readingStyle)
{
return GetUserStyleClass("style", readingStyle.ToString());
}
/// <summary>
/// Initializes a new instance of NReadabilityTranscoder. Allows setting all options.
/// </summary>
/// <param name="dontStripUnlikelys">Determines whether elements that are unlikely to be a part of main content will be removed.</param>
/// <param name="dontNormalizeSpacesInTextContent">Determines whether spaces in InnerText properties of elements will be normalized automatically (eg. whether double spaces will be replaced with single spaces).</param>
/// <param name="dontWeightClasses">Determines whether 'weight-class' algorithm will be used when cleaning content.</param>
/// <param name="readingStyle">Styling for the extracted article.</param>
/// <param name="readingMargin">Margin for the extracted article.</param>
/// <param name="readingSize">Font size for the extracted article.</param>
/// <param name="articleElementHints">Hints for sites with difficult to find article bodies, in form of a dictionary of a regex matching the url of the content and the selector for the element containing the article</param>
public NReadabilityTranscoder(
bool dontStripUnlikelys,
bool dontNormalizeSpacesInTextContent,
bool dontWeightClasses,
ReadingStyle readingStyle,
ReadingMargin readingMargin,
ReadingSize readingSize,
IDictionary<Regex, string> articleElementHints)
: this(dontStripUnlikelys, dontNormalizeSpacesInTextContent, dontWeightClasses, readingStyle, readingMargin, readingSize)
{
if (articleElementHints != null)
{
foreach (var kvp in articleElementHints)
{
_articleContentElementHints[kvp.Key] = kvp.Value;
}
}
}
