我想從pdf中提取文本並重新發布它。 我的代碼如下:如何使用mupdf從pdf中提取文本?
BOOL CTextEditorDoc::loadTxt()
{
if(m_strPDFPath.IsEmpty())
return FALSE;
#ifdef _DEBUG
DWORD dwTick = GetTickCount();
CString strLog;
#endif
CString strFile;
fz_context *ctx;
fz_document* doc;
fz_matrix ctm;
fz_page *page;
fz_device *dev;
fz_text_page *text;
fz_text_sheet *sheet;
int i,line,rotation,pagecount;
if(!gb2312toutf8(m_strPDFPath,strFile))
return FALSE;
ctx = fz_new_context(NULL, NULL, FZ_STORE_UNLIMITED);
fz_try(ctx){
doc = fz_open_document(ctx, strFile.GetBuffer(0));
}fz_catch(ctx){
fz_free_context(ctx);
return FALSE;
}
line = 0;
rotation = 0;
pagecount = 0;
pagecount = fz_count_pages(doc);
fz_rotate(&ctm, rotation);
fz_pre_scale(&ctm,1.0f,1.0f);
sheet = fz_new_text_sheet(ctx);
for(i=0;i<pagecount;i++){
page = fz_load_page(doc,i);
text = fz_new_text_page(ctx);
dev = fz_new_text_device(ctx, sheet, text);
#ifdef _DEBUG
dwTick = GetTickCount();
#endif
fz_run_page(doc, page, dev, &ctm, NULL);
#ifdef _DEBUG
strLog.Format("run page:%d ms\n",GetTickCount() - dwTick);
OutputDebugString(strLog);
dwTick = GetTickCount();
#endif
//m_linesInfoVector.push_back(line);
print_text_page(ctx,m_strContent,text,line);
#ifdef _DEBUG
strLog.Format("print text:%d ms\n",GetTickCount() - dwTick);
OutputDebugString(strLog);
dwTick = GetTickCount();
#endif
fz_free_device(dev);
fz_free_text_page(ctx,text);
fz_free_page(doc, page);
}
fz_free_text_sheet(ctx,sheet);
fz_close_document(doc);
fz_free_context(ctx);
return TRUE;
}
這段代碼可以提取PDF的所有文字,但它可能是太慢了。如何改進? 大部分時間用於功能fz_run_page
。也許只是從pdf中提取文本,我不需要執行fz_run_page
?
@@ Robin Watts,您認爲mupdf是世界上最好的pdf庫嗎? – tfzxyinhao
@Robin Watts,有沒有關於加速閱讀PDF文本的任何事情? – EekTheCat