invert HasNoHeadline; better NextPage parser;

This commit is contained in:
2014-02-17 22:10:20 +01:00
parent d754eda216
commit 3bbf4fdcb7
5 changed files with 58 additions and 12 deletions
+3
View File
@@ -94,6 +94,9 @@ namespace ReadSharp
// treat paragraphs as crlf
outText.Write("\r\n");
break;
case "br":
outText.Write("\r\n");
break;
}
if (node.HasChildNodes)
+2 -2
View File
@@ -17,7 +17,7 @@ namespace ReadSharp
/// <value>
/// <c>true</c> if [has no headline]; otherwise, <c>false</c>.
/// </value>
public bool HasNoHeadline { get; set; }
public bool HasHeadline { get; set; }
/// <summary>
/// Are deep links with hashes not transformed to absolute URIs (default: false).
@@ -52,7 +52,7 @@ namespace ReadSharp
return new ReadOptions()
{
HasHeaderTags = false,
HasNoHeadline = false,
HasHeadline = false,
UseDeepLinks = false,
PrettyPrint = false,
MultipageDownload = false
+9 -2
View File
@@ -214,7 +214,7 @@ namespace ReadSharp
DomSerializationParams = new DomSerializationParams()
{
BodyOnly = !options.HasHeaderTags,
NoHeadline = options.HasNoHeadline,
NoHeadline = !options.HasHeadline,
PrettyPrint = options.PrettyPrint,
DontIncludeContentTypeMetaElement = true,
DontIncludeMobileSpecificMetaElements = true,
@@ -352,6 +352,14 @@ namespace ReadSharp
Encoding = encoding
};
// in same special cases their are multiple pages, which are only comments or do not contain new content.
// if this is the case we will break here and return the first page only.
if (previousResponse != null && previousResponse.TranscodingResult.ExtractedContent == transcodingResult.ExtractedContent)
{
previousResponse.TranscodingResult.NextPageUrl = null;
return previousResponse;
}
// multiple pages are available
try
{
@@ -359,7 +367,6 @@ namespace ReadSharp
{
return await Request(new Uri(transcodingResult.NextPageUrl), new ReadOptions()
{
HasNoHeadline = true,
PrettyPrint = options.PrettyPrint,
UseDeepLinks = options.UseDeepLinks,
MultipageDownload = true