C Requires Chilkat v11.7.0+

PDF to Markdown Options: Page Breaks, Images, Tables, Emphasis, Heading Levels

See more PDF Text Extraction Examples

Demonstrates the options of the "markdown" operation: pageBreaks (comment, rule or none), images (placeholder or none), tables (ruled or none), emphasis, and maxHeadingLevel. C

#include <C_CkPdf.h>
#include <C_CkJsonObject.h>
#include <C_CkStringBuilder.h>

void ChilkatSample(void)
    {
    BOOL success;
    HCkPdf pdf;
    HCkJsonObject json;
    HCkStringBuilder sbMarkdown;
    HCkJsonObject jsonOut;

    success = FALSE;

    //  This example requires the Chilkat API to have been previously unlocked.
    //  See Global Unlock Sample for sample code.

    //  The two-page PDF used in this example is available at markdown_options.pdf

    pdf = CkPdf_Create();
    success = CkPdf_LoadFile(pdf,"qa_data/pdf/markdown_options.pdf");
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        return;
    }

    json = CkJsonObject_Create();
    sbMarkdown = CkStringBuilder_Create();
    jsonOut = CkJsonObject_Create();

    //  First with the default options.
    success = CkPdf_ExtractTextSb(pdf,"markdown",json,sbMarkdown,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkStringBuilder_Dispose(sbMarkdown);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("---- default options ----\n");
    printf("%s\n",CkStringBuilder_getAsString(sbMarkdown));

    //  Now change the options:

    //  pageBreaks: "comment" (the default) separates pages with <!-- page N -->,
    //  "rule" separates them with a horizontal rule (---), and "none" runs the pages together.
    CkJsonObject_UpdateString(json,"pageBreaks","rule");

    //  images: "placeholder" (the default) marks where each image sits with ![image](page-1-image-1);
    //  "none" leaves images out.
    CkJsonObject_UpdateString(json,"images","none");

    //  tables: "ruled" (the default) converts tables that have drawn cell borders into Markdown tables;
    //  "none" returns their cells as plain text.
    CkJsonObject_UpdateString(json,"tables","none");

    //  emphasis: false leaves out the ** and * markers for bold and italic.
    CkJsonObject_UpdateBool(json,"emphasis",FALSE);

    //  maxHeadingLevel: inferred headings deeper than this level are folded into this level.
    //  The PDF has three heading levels; with maxHeadingLevel 2 the third level becomes ##.
    CkJsonObject_UpdateInt(json,"maxHeadingLevel",2);

    CkStringBuilder_Clear(sbMarkdown);
    success = CkPdf_ExtractTextSb(pdf,"markdown",json,sbMarkdown,jsonOut);
    if (success == FALSE) {
        printf("%s\n",CkPdf_lastErrorText(pdf));
        CkPdf_Dispose(pdf);
        CkJsonObject_Dispose(json);
        CkStringBuilder_Dispose(sbMarkdown);
        CkJsonObject_Dispose(jsonOut);
        return;
    }

    printf("---- custom options ----\n");
    printf("%s\n",CkStringBuilder_getAsString(sbMarkdown));

    //  Sample output:

    //  ---- default options ----
    //  <!-- page 1 -->
    //  
    //  # Community Garden Handbook
    //  
    //  ## Plots
    //  
    //  ### Plot Sizes
    //  
    //  Plots come in two sizes. A **full plot** is twenty feet by ten feet; a **half plot** is ten feet square. New gardeners are *strongly encouraged* to start with a half plot.
    //  
    //  ![image](page-1-image-1)
    //  
    //  ### Plot Fees
    //  
    //  | Plot | Size | Annual Fee |
    //  | --- | --- | --- |
    //  | Full | 20 x 10 ft | $60 |
    //  | Half | 10 x 10 ft | $35 |
    //  
    //  <!-- page 2 -->
    //  
    //  ## Watering
    //  
    //  ### Schedule
    //  
    //  The shared tanks are filled on Monday and Thursday mornings. Please water by hand from the tanks rather than running a hose from the street tap, which is metered.
    //  
    //  ### Dry Spells
    //  
    //  During a declared drought the committee may limit watering to **two days a week**. Notices are posted on the shed door and sent by e-mail.
    //  
    //  ---- custom options ----
    //  # Community Garden Handbook
    //  
    //  ## Plots
    //  
    //  ## Plot Sizes
    //  
    //  Plots come in two sizes. A full plot is twenty feet by ten feet; a half plot is ten feet square. New gardeners are strongly encouraged to start with a half plot.
    //  
    //  ## Plot Fees
    //  
    //  Plot Size Annual Fee
    //  
    //  Full 20 x 10 ft $60
    //  
    //  Half 10 x 10 ft $35
    //  
    //  ---
    //  
    //  ## Watering
    //  
    //  ## Schedule
    //  
    //  The shared tanks are filled on Monday and Thursday mornings. Please water by hand from the tanks rather than running a hose from the street tap, which is metered.
    //  
    //  ## Dry Spells
    //  
    //  During a declared drought the committee may limit watering to two days a week. Notices are posted on the shed door and sent by e-mail.


    CkPdf_Dispose(pdf);
    CkJsonObject_Dispose(json);
    CkStringBuilder_Dispose(sbMarkdown);
    CkJsonObject_Dispose(jsonOut);

    }