To read page content from a document.
C# C++ Go Java JavaScript Obj-C PHP Python Ruby VB
1 PDFDoc doc = new PDFDoc (filename);
2 ElementReader reader = new ElementReader ();
3
4 // Read page content on every page in the document
5 for ( PageIterator itr = doc. GetPageIterator (); itr. HasNext (); itr. Next ())
6 {
7 // Read the page
8 reader. Begin (itr. Current ());
9 ProcessElements (reader);
10 reader. End ();
11 }
12
13 void ProcessElements ( ElementReader reader )
14 {
15 Element element;
16
17 // Traverse the page display list
18 while ((element = reader. Next ()) != null )
19 {
20 switch (element. GetType ())
21 {
22 case Element . ElementType . e_path :
23 {
24 if (element. IsClippingPath ())
25 {}
26 // ...
27 break ;
28 }
29 case Element . ElementType . e_text :
30 {
31 Matrix2D text_mtx = element. GetTextMatrix ();
32 // ...
33 break ;
34 }
35 case Element . ElementType . e_form :
36 {
37 reader. FormBegin ();
38 ProcessElements (reader);
39 reader. End ();
40 break ;
41 }
42 }
43 }
44 }
1 PDFDoc doc ( filename );
2 ElementReader reader;
3
4 // Read page content on every page in the document
5 PageIterator itr;
6 for (itr = doc. GetPageIterator (); itr. HasNext (); itr. Next ())
7 {
8 // Read the page
9 reader. Begin (itr. Current ());
10 ProcessElements (reader);
11 reader. End ();
12 }
13
14 void ProcessElements ( ElementReader reader )
15 {
16 Element element;
17
18 // Traverse the page display list
19 while ((element = reader. Next ()) != null)
20 {
21 switch (element. GetType ())
22 {
23 case Element :: e_path:
24 {
25 if (element. IsClippingPath ())
26 {}
27 // ...
28 break ;
29 }
30 case Element :: e_text:
31 {
32 Matrix2D text_mtx = element. GetTextMatrix ();
33 // ...
34 break ;
35 }
36 case Element :: e_form:
37 {
38 reader. FormBegin ();
39 ProcessElements (reader);
40 reader. End ();
41 break ;
42 }
43 }
44 }
45 }
1 doc := NewPDFDoc (filename)
2 reader := NewElementReader ()
3
4 // Read page content on every page in the document
5 itr := doc. GetPageIterator ()
6 for itr. HasNext (){
7 page := itr. Current ()
8 reader. Begin (page)
9 ProcessElements (reader)
10 reader. End ()
11 itr. Next ()
12 }
13
14 func ProcessElements ( reader ElementReader ){
15 element := reader. Next ()
16
17 // Traverse the page display list
18 for element. GetMp_elem (). Swigcptr () != 0 {
19 etype := element. GetType ()
20 if etype == ElementE_path{
21 if (element. IsClippingPath ())
22 {}
23 // ...
24 } else if etype == ElementE_text {
25 text_mtx := element. GetTextMatrix ()
26 // ...
27 } else if etype == ElementE_form {
28 reader. FormBegin ()
29 ProcessElements (reader)
30 reader. End ()
31 }
32 element = reader. Next ()
33 }
34 }
1 PDFDoc doc = new PDFDoc (filename);
2 ElementReader reader = new ElementReader ();
3
4 // Read page content on every page in the document
5 for ( PageIterator itr = doc. getPageIterator (); itr. hasNext (); itr. next ())
6 {
7 // Read the page
8 reader. begin (itr. current ());
9 ProcessElements (reader);
10 reader. end ();
11 }
12
13 void ProcessElements ( ElementReader reader)
14 {
15 Element element;
16
17 // Traverse the page display list
18 while ((element = reader. next ()) != null )
19 {
20 switch (element. getType ())
21 {
22 case Element.e_path :
23 {
24 if (element. isClippingPath ())
25 {}
26 // ...
27 break ;
28 }
29 case Element.e_text :
30 {
31 Matrix2D text_mtx = element. getTextMatrix ();
32 // ...
33 break ;
34 }
35 case Element.ElementType.e_form :
36 {
37 reader. formBegin ();
38 ProcessElements (reader);
39 reader. end ();
40 break ;
41 }
42 }
43 }
44 }
1 async function main () {
2 const doc = await PDFNet.PDFDoc. createFromURL (filename);
3 const reader = await PDFNet.ElementReader. create ();
4
5 // Read page content on every page in the document
6 const itr = await doc. getPageIterator ();
7 for (itr; await itr. hasNext (); itr. next ())
8 {
9 // Read the page
10 const page = await itr. current ();
11 reader. beginOnPage (page);
12 await ProcessElements (reader);
13 reader. end ();
14 }
15
16 async function ProcessElements ( reader )
17 {
18 // Traverse the page display list
19 for ( let element = await reader. next (); element !== null ; element = await reader. next ()) {
20 const elementType = await element. getType ();
21 switch (elementType)
22 {
23 case PDFNet.Element.Type.e_path:
24 {
25 if (element. isClippingPath ())
26 {}
27 // ...
28 break ;
29 }
30 case PDFNet.Element.Type.e_text:
31 {
32 const text_mtx = element. getTextMatrix ();
33 // ...
34 break ;
35 }
36 case PDFNet.Element.Type.e_form:
37 {
38 reader. formBegin ();
39 ProcessElements (reader);
40 reader. end ();
41 break ;
42 }
43 }
44 }
45 }
46 }
47 PDFNet. runWithCleanup (main);
1 PTPDFDoc * doc = [[PTPDFDoc alloc ] initWithFilepath : filename];
2 PTElementReader * reader = [[PTElementReader alloc ] init ];
3
4 for (PageIterator * itr = [doc GetPageIterator : 1 ]; [itr HasNext ]; [itr Next ])
5 {
6 // Read the page
7 [reader Begin : [itr Current ]];
8 ProcessElements (reader);
9 [reader End ];
10 }
11
12 void ProcessElements (PTElementReader * reader )
13 {
14 // Traverse the page display list
15 PTElement * element;
16 while ((element = [reader Next ]))
17 {
18 switch ([element GetType ])
19 {
20 case e_ptpath:
21 {
22 if ([element IsClippingPath ])
23 {}
24 // ...
25 break ;
26 }
27 case e_pttext_obj:
28 {
29 PTMatrix2D * text_mtx = [element GetTextMatrix ];
30 // ...
31 break ;
32 }
33 case e_ptform:
34 {
35 [reader FormBegin ];
36 ProcessElements (reader);
37 [reader End ];
38 break ;
39 }
40 }
41 }
42 }
1 $doc = new PDFDoc ($filename);
2 $reader = new ElementReader ();
3
4 for ($itr = $doc -> GetPageIterator (); $itr -> HasNext (); $itr -> Next ())
5 {
6 // Read the page
7 $reader -> Begin ($itr -> Current ());
8 ProcessElements ($reader);
9 $reader -> End ();
10 }
11
12 function ProcessElements ($reader)
13 {
14 // Traverse the page display list
15 while (($element = $reader -> Next ()) != null )
16 {
17 switch ($element -> GetType ())
18 {
19 case Element :: e_path :
20 {
21 if ($element -> IsClippingPath ())
22 {}
23 // ...
24 break ;
25 }
26 case Element :: e_text :
27 {
28 $text_mtx = $element -> GetTextMatrix ();
29 // ...
30 break ;
31 }
32 case Element :: e_form :
33 {
34 $reader -> FormBegin ();
35 ProcessElements ($reader);
36 $reader -> End ();
37 }
38 }
39 }
40 }
1 doc = PDFDoc(filename)
2 reader = ElementReader()
3
4 itr = doc.GetPageIterator()
5 while itr.HasNext():
6 # Read the page
7 reader.Begin(itr.Current())
8 ProcessElements(reader)
9 reader.End()
10 itr.Next()
11
12 def ProcessElements ( reader ):
13 # Traverse the page display list
14 element = reader.Next()
15 while element != None :
16 type = element.GetType()
17 if type == Element.e_path:
18 if element.IsClippingPath():
19 pass
20 # ...
21 elif type == Element.e_text:
22 text_mtx = element.GetTextMatrix()
23 # ...
24 elif type == Element.e_form:
25 reader.FormBegin()
26 ProcessElements(reader)
27 reader.End()
28 element = reader.Next()
1 doc = PDFDoc . new (filename)
2 reader = ElementReader . new ()
3
4 itr = doc. GetPageIterator ()
5 while itr. HasNext () do
6 # Read the page
7 reader. Begin (itr. Current ())
8 ProcessElements (reader)
9 reader. End ()
10 itr. Next ()
11 end
12
13 def ProcessElements ( reader )
14 # Traverse the page display list
15 element = reader. Next ()
16 while ! element. nil? do
17 type = element. GetType ()
18 case type
19 when Element :: E_path
20 if (element. IsClippingPath ())
21 end
22 # ...
23 when Element :: E_text
24 text_mtx = element. GetTextMatrix ()
25 # ...
26 when Element :: E_form:
27 reader. FormBegin ()
28 ProcessElements (reader)
29 reader. End ()
30 end
31 end
32 end
1 Dim doc As PDFDoc = New PDFDoc (filename)
2 Dim reader As ElementReader = New ElementReader
3
4 Dim itr As PageIterator = doc. GetPageIterator ()
5 While itr. HasNext ()
6 ' Read the page
7 reader. Begin (itr. Current ())
8 ProcessElements (reader)
9 reader. End ()
10 End While
11
12 Sub ProcessElements ( ByVal reader As ElementReader )
13 ' Traverse the page display list
14 Dim element As Element = reader. Next ()
15 While Not IsNothing (element)
16 If element. GetType () = element.Type.e_path Then
17 If element. IsClippingPath () then
18 End If
19 ' ...
20 ElseIf element. GetType () = element.Type.e_text Then
21 Dim text_mtx As Matrix2D = element. GetTextMatrix ()
22 ' ...
23 ElseIf element. GetType () = element.Type.e_form Then
24 reader. FormBegin ()
25 ProcessElements (reader)
26 reader. End ()
27 End If
28 element = reader. Next ()
29 End While
30 End Sub
Read Elements Across All PDF Pages
About reading page content Page content is represented as a sequence of graphical Elements such as paths, text, images, and forms. The only effect of the ordering of Elements in the display list is the order in which Elements are painted. Elements that occur later in the display list can obscure earlier elements.
A display list can be traversed using an ElementReader object. To start traversing the display list, call reader.Begin(). Then, reader.Next() will return subsequent Elements until null is returned (marking the end of the display list). While ElementReader only works with one page at a time, the same ElementReader object may be reused to process multiple pages.
A PDF page display list may contain child display lists of Form XObjects, Type3 font glyphs, and tiling patterns. A form XObject is a self-contained description of any sequence of graphics objects (such as path objects, text objects, and sampled images), defined as a PDF content stream. It may be painted multiple times — either on several pages or at several locations on the same page — and will produce the same results each time (subject only to the graphics state at the time the Form XObject is painted). In order to open a child display list for a Form XObject, call the reader.FormBegin() method. To return processing to the parent display list call reader.End(). Processing of the Form XObject display (traversing the child display list) is illustrated below.
Note that, in the above sample code, a child display list is opened when an element with type Element.ElementType.e_form is encountered by the reader.FormBegin() method. The child display list becomes the current display list until it is closed using reader.End(). At this point the processing is returned to the parent display list and the next Element returned will be the Element following the Form XObject. Also note that, because Form XObjects may be nested, a sub-display list could have its own child display lists. The sample above shows traversing these nested Form XObjects recursively.
Similarly, a pattern display list can be opened using reader.PatternBegin(), and a Type3 glyph display list can be opened using the reader.Type3FontBegin() method.
