static void Main(string[] args)
{
PdfReader reader = new PdfReader(@"D:\191.pdf");
IEnumerable <string> GetColumnText(float llx, float lly, float urx, float ury)
{
int get_PageNum = reader.NumberOfPages;
for (int pagecount = 1; pagecount <= get_PageNum; pagecount++)
{
var rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
var textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
var text = PdfTextExtractor.GetTextFromPage(reader, pagecount, textExtractionStrategy);
yield return(text);
}
}
foreach (string result in GetColumnText(0, 0, 500, 500000))
{
Console.Write("{0} ", result);
Console.ReadLine();
}
}
public List <string> getTextByCoOrdinate(PdfReader reader, int pageNumber, int cordinate1, int coordinate2, int coordinate3, int coordinate4)
{
List <string> data = new List <string>();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, coordinate2, coordinate3, coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageNumber, textExtractionStrategy);
string[] words = text.Split('\n');
foreach (var x in words)
{
if (!string.IsNullOrWhiteSpace(x))
{
data.Add(x.Trim());
}
}
foreach (var y in data)
{
Console.WriteLine(y);
}
return(data);
}
public static string GetRectangle(PdfReader reader, int pageNumber, float llx, float lly, float urx, float ury)
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
return(PdfTextExtractor.GetTextFromPage(reader, pageNumber, textExtractionStrategy));
}
private string[] ExtractCurrentColumnFromPage(Rectangle column, PdfReader reader, int page)
{
var renderFilter = new RegionTextRenderFilter(column);
var renderFilterArray = new RenderFilter[] { renderFilter };
var filteredTextRenderListener = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilterArray);
var textFromColumn = PdfTextExtractor.GetTextFromPage(reader, page, filteredTextRenderListener);
return(SplitColumnTextIntoRows(textFromColumn));
}
public string GetStringValueFromRegion(string file, iTextSharp.text.Rectangle rectangle)
{
var reader = new PdfReader(file);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rectangle);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
return(PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy));
}
public void ToggleDrawFilter(RenderFilter toggle)
{
if ((DrawFilter & toggle) > 0)
{
DrawFilter &= ~toggle;
}
else
{
DrawFilter |= toggle;
}
}
public static ITextExtractionStrategy MakeRectangle(float pixelDistanceFromLeft, float pixelDistanceFromBottom, float pixelDistanceWidth, float pixelDistanceHeight)
{
var rectangle = new System.util.RectangleJ(pixelDistanceFromLeft, pixelDistanceFromBottom, pixelDistanceWidth, pixelDistanceHeight);
var filters = new RenderFilter[1];
filters[0] = new RegionTextRenderFilter(rectangle);
ITextExtractionStrategy strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filters);
return(strategy);
}
private static string GetColumnText(PdfReader reader, int pageNum, float llx, float lly, float urx, float ury)
{
// reminder, parameters are in points, and 1 in = 2.54 cm = 72 points
var rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
var textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
var text = PdfTextExtractor.GetTextFromPage(reader, pageNum, textExtractionStrategy);
return(text);
}
private void ReadText()
{
//List<string> linestringlist = new List<string>();
//PdfReader reader = new PdfReader(pdfFileName);
iTextSharp.text.Rectangle rectA = new iTextSharp.text.Rectangle(coordinate1a, coordinate2a, coordinate3a, coordinate4a);
iTextSharp.text.Rectangle rectB = new iTextSharp.text.Rectangle(coordinate1b, coordinate2b, coordinate3b, coordinate4b);
RenderFilter[] renderFilter = new RenderFilter[2];
renderFilter[0] = new RegionTextRenderFilter(rectA);
renderFilter[1] = new RegionTextRenderFilter(rectB);
ITextExtractionStrategy textExtractionStrategyA = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter[0]);
ITextExtractionStrategy textExtractionStrategyB = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter[1]);
textA = PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategyA);
textB = PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategyB);
}
/// <summary>
/// Extracts text from PDF file. (only selectable text content from the pages, not OCR from images)
/// </summary>
/// <param name="filepath">input file path</param>
/// <param name="zone">Rectangle which specifies the zone where the text is extracted from a page. if it's null, then the full page is processed.</param>
/// <param name="pages">List of pages to extract data from. If null or first item is 0, all pages will be extracted.</param>
/// <returns>a list of strings. one string from each page</returns>
public static List <string> GetPdfTextFromPages(string filepath, RectangleF?zone = null, List <int> pages = null)
{
using (PdfReader reader = new PdfReader(filepath))
{
List <string> result = new List <string>();
if (pages == null || pages.First() == 0) //then read all pages
{
pages = Enumerable.Range(1, reader.NumberOfPages).ToList(); //create the list of all pagenumbers in the actual PDF
}
foreach (var i in pages)
{
if (i > reader.NumberOfPages)
{
continue;
}
if (zone.HasValue)
{ //zone based text extract
float x = Utilities.MillimetersToPoints(zone.Value.X);
float y = Utilities.MillimetersToPoints(zone.Value.Y);
float w = Utilities.MillimetersToPoints(zone.Value.Width);
float h = Utilities.MillimetersToPoints(zone.Value.Height);
var pagesize = reader.GetPageSizeWithRotation(i);
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(x, pagesize.Top - y, x + w, pagesize.Top - y - h); //tanslate coordinates to iText
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, i, textExtractionStrategy);
result.Add(text.Replace("\n", Environment.NewLine));
}
else
{ //full page text extract
string text = PdfTextExtractor.GetTextFromPage(reader, i);
result.Add(text.Replace("\n", Environment.NewLine));
}
}
reader.Close();
return(result);
}
}
public void ProcessSceneVisibility(RenderFilter filter, DrawGroup dispGroup)
{
bool alwaysVis = dispGroup != null ? dispGroup.AlwaysVisible : true;
for (int i = 0; i < SYSTEM_SIZE; i++)
{
if (cCulled[i])
{
continue;
}
if ((cSceneVis[i]._renderFilter & filter) == 0)
{
cCulled[i] = true;
continue;
}
if (!alwaysVis && cSceneVis[i]._drawGroup != null && !cSceneVis[i]._drawGroup.IsInDisplayGroup(dispGroup))
{
cCulled[i] = true;
}
}
}
public string getParagraphByCoOrdinate(string filepath, int pageno, int cordinate1, int coordinate2, int coordinate3, int coordinate4, bool filter)
{
PdfReader reader = new PdfReader(filepath);
if (filter == false)
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, 1000 - coordinate2, coordinate3, 1000 - coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageno, textExtractionStrategy);
return(text);
}
else
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, coordinate2, coordinate3, coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageno, textExtractionStrategy);
return(text);
}
}
//static public Dictionary<string, string> ExtractTexts(this PdfReader pr, int pageI, Dictionary<string, RenderFilter[]> fieldNames2filters)
//{
// Dictionary<string, string> fieldNames2texts = new Dictionary<string, string>();
// foreach (string fn in fieldNames2filters.Keys)
// fieldNames2texts[fn] = pr.ExtractText(pageI, fieldNames2filters[fn]);
// return fieldNames2texts;
//}
public static string ExtractText(this PdfReader pr, int pageI, float x, float y, float w, float h)
{
RenderFilter[] rf = new RenderFilter[] { new RegionTextRenderFilter(new System.util.RectangleJ(x, y, w, h)) };
return(ExtractText(pr, pageI, rf));
}
public static void ExtractText(string fileName, string outFileName)
{
/* pour extraire seulement les 3 1ères pages
* PdfReader pdfReader1 = new PdfReader("AN_PAI_12022018_1M.pdf");
* Document document = new Document();
*
* PdfCopy copy = new PdfCopy(document, new FileStream("splitpaie1-3.pdf", FileMode.Create));
* document.Open();
* for (int page = 1; page <= 3; page++)
* {
* document.NewPage();
* copy.AddPage(copy.GetImportedPage(pdfReader1, page));
* }
* document.Close();*/
StreamWriter outFile = new StreamWriter(outFileName, false, System.Text.Encoding.UTF8);
StreamWriter outFile2 = new StreamWriter("filtered " + outFileName, false, System.Text.Encoding.UTF8);
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
Rectangle psize = pdfReader.GetPageSize(page);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
//ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
string id1, id2, netRegex, netLocation, idLocation;
netRegex = id1 = id2 = "";
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
outFile.Write(currentPageText);
var match = Regex.Match(currentPageText, "Matricule : *([0-9]*) SS : ([0-9]*)");
if (match.Success)
{
id1 = match.Groups[1].Value;
id2 = match.Groups[2].Value;
outFile2.Write("Matricule : " + id1 + " SS : " + id2);
}
outFile2.Write(";");
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(400, 842 - 128, 480, 848 - 110);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
idLocation = PdfTextExtractor.GetTextFromPage(pdfReader, page, textExtractionStrategy);
outFile2.Write(";");
outFile2.Write(idLocation);
outFile2.Write(";");
if ("Matricule : " + id1 + " SS : " + id2 != idLocation.Trim())
{
int h = 0;
}
//match = Regex.Match(currentPageText, "Pér *([0-9]*) *([0-9]*) *([0-9]*)");
match = Regex.Match(currentPageText, "Net imposable(.*)Net imposable");
if (match.Success)
{
netRegex = match.Groups[1].Value;
outFile2.Write(netRegex);
}
rect = new iTextSharp.text.Rectangle(150, 240, 210, 250);
renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
netLocation = PdfTextExtractor.GetTextFromPage(pdfReader, page, textExtractionStrategy);
rect = new iTextSharp.text.Rectangle(400, 842 - 128, 480, 848 - 110);
renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategyEx(), renderFilter);
string matriculeLocation = PdfTextExtractor.GetTextFromPage(pdfReader, page, textExtractionStrategy);
outFile2.Write(";");
outFile2.Write(netLocation);
if (netRegex.Trim() != netLocation.Trim())
{
int x = 0;
//page 259, rappel période antérieure, pas de net imposable de période
}
if (netLocation == "")
{
int z = 0;
//page 56, normal, sur plusieurs pages
}
outFile2.WriteLine();
}
pdfReader.Close();
outFile.Close();
outFile2.Close();
}
private void Scrape(CancellationToken token, string path)
{
PdfReader reader = new PdfReader(path);
string sUri = "";
try
{
// Pagination
for (var i = 1; i <= reader.NumberOfPages; i++)
{
//get current page
var pageDict = reader.GetPageN(i);
//get all annotations from current page
var annotArray = (PdfArray)PdfReader.GetPdfObject(pageDict.Get(PdfName.ANNOTS));
//ensure array isn't empty
if (annotArray == null)
{
continue;
}
if (annotArray.Length <= 0)
{
continue;
}
// check every annotation on the page
foreach (var annot in annotArray.ArrayList)
{
//convert the iTextSharp-specific object to a generic PDF object
var annotDict = (PdfDictionary)PdfReader.GetPdfObject(annot);
//ensure the object isnt empty
if (annotDict == null)
{
continue;
}
//get the annotation subtype and ensure it is a link
var subtype = annotDict.Get(PdfName.SUBTYPE).ToString();
Log("Subtype: " + subtype);
if (subtype != "/Link")
{
continue;
}
//get the annotations ACTION
var linkDict = (PdfDictionary)annotDict.GetDirectObject(PdfName.A);
if (linkDict == null)
{
continue;
}
if (!linkDict.Get(PdfName.S).Equals(PdfName.GOTO))
{
//get the link from the annotation
sUri = linkDict.Get(PdfName.URI).ToString();
Log("URI: " + sUri);
if (String.IsNullOrEmpty(sUri))
{
continue;
}
}
//build the link address into a string
string linkTextBuilder;
//create a rectangle, define its paramteres, read the text under the rectangle (the anchor text for the link) and write it to the string
var LinkLocation = annotDict.GetAsArray(PdfName.RECT);
List <string> linestringlist = new List <string>();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(((PdfNumber)LinkLocation[0]).FloatValue, ((PdfNumber)LinkLocation[1]).FloatValue, ((PdfNumber)LinkLocation[2]).FloatValue, ((PdfNumber)LinkLocation[3]).FloatValue);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
linkTextBuilder = PdfTextExtractor.GetTextFromPage(reader, i, textExtractionStrategy).Trim();
Log(linkTextBuilder);
String sUriHTTPSPrefix = sUri.Substring(0, 5);
String sUriWWWPrefix = sUri.Substring(0, 3);
if (sUriHTTPSPrefix.Equals("https"))
{
Log("Prefix: " + sUriHTTPSPrefix);
}
else if (sUriWWWPrefix.Equals("www"))
{
Log("Prefix: " + sUriWWWPrefix);
}
if (sUri.Length.Equals(70) && sUriHTTPSPrefix.Equals("https"))
{
//instantiate the web request and response objects
WebRequest httpReq = WebRequest.Create(sUri);
WebResponse response = httpReq.GetResponse();
//check website response from request and save status to string
string webStatus = ((HttpWebResponse)response).StatusDescription.ToString();
Log("Webstatus: " + webStatus);
//check website response url from request and save url to string
string responseURL = ((HttpWebResponse)response).ResponseUri.ToString();
Log("Response URI: " + responseURL);
//split the response url string to just sku number after the "="
string webSite = responseURL.Split('=')[1];
Log("Response SKU: " + webSite);
//split the link harvested from the annotations in the pdf after the "="
string sku = sUri.Split('=')[1];
Log("PDF SKU: " + sku);
//truncate the split string to just the sku (removes any extra symbols, such as copywright, which were captured in the rectangle)
string finalSku = sku.Substring(0, 7);
Log("PDF SKU Final: " + finalSku);
//delete asteriks from sku
var deleteChars = new string[] { "*" };
foreach (var c in deleteChars)
{
linkTextBuilder = finalSku.Replace(c, string.Empty);
}
//truncate the split string to just the sku (removes any extra symbols, such as copywright, which were captured in the rectangle)
string linkText = linkTextBuilder.Substring(0, 7);
Log("Link SKU Final: " + linkText);
//default status of string match is "NO MATCH"
string match = "\tNO MATCH";
//make a blank IPEndPoint
IPEndPoint remoteEP = null;
//create a new httpwebrequest
HttpWebRequest req = (HttpWebRequest)HttpWebRequest.Create(sUri);
//bind IPEndPoint from the remote end point to a variable
req.ServicePoint.BindIPEndPointDelegate = delegate(ServicePoint servicePoint, IPEndPoint remoteEndPoint, int retryCount)
{
remoteEP = remoteEndPoint;
return(null);
};
//get the response from the request
req.GetResponse();
Log("HTTP response: " + req.GetResponse());
//set remoteEndPoint to string for display
string hostIP = remoteEP.Address.ToString();
Log("Host IP: " + hostIP);
//stop the request to make way for a new request on next iteration
req.Abort();
//if sku from PDF link, website response link, and pdf anchor text all match then change match
if (linkText.Equals(sku) && webSite.Equals(sku))
{
match = "MATCH";
}
//add data to datagridview
this.skuGrid.Rows.Add(i, sku, linkTextBuilder, webSite, match, webStatus, hostIP);
//close http request and response
response.Close();
if (token.IsCancellationRequested)
{
// Clean up here, then...
token.ThrowIfCancellationRequested();
Log("Cancellation token: " + token);
MessageBox.Show("Scrape stopped");
throbber.Hide();
skuGrid.Show();
}
}
else if (!sUri.Length.Equals(70) && sUriWWWPrefix.Equals("www") ||
!sUri.Length.Equals(70) && sUriHTTPSPrefix.Equals("https"))
{
//instantiate the web request and response objects
WebRequest httpReq = WebRequest.Create(sUri);
WebResponse response = httpReq.GetResponse();
//check website response from request and save status to string
string webStatus = ((HttpWebResponse)response).StatusDescription.ToString();
Log("Web Status: " + webStatus);
//check website response url from request and save url to string
string responseURL = ((HttpWebResponse)response).ResponseUri.ToString();
Log("Response URI: " + responseURL);
//split the response url string to just sku number after the "="
string webSite = responseURL;
Log("Response SKU: " + webSite);
//default status of string match is "NO MATCH"
string match = "\tNO MATCH";
//make a blank IPEndPoint
IPEndPoint remoteEP = null;
//create a new httpwebrequest
HttpWebRequest req = (HttpWebRequest)HttpWebRequest.Create(sUri);
//bind IPEndPoint from the remote end point to a variable
req.ServicePoint.BindIPEndPointDelegate = delegate(ServicePoint servicePoint, IPEndPoint remoteEndPoint, int retryCount)
{
remoteEP = remoteEndPoint;
return(null);
};
//get the response from the request
req.GetResponse();
Log("HTTP Response: " + req.GetResponse());
//set remoteEndPoint to string for display
string hostIP = remoteEP.Address.ToString();
Log("Host IP: " + hostIP);
//stop the request to make way for a new request on next iteration
req.Abort();
//delete asteriks from sku
var deleteChars = new string[] { "*" };
foreach (var c in deleteChars)
{
linkTextBuilder = linkTextBuilder.Replace(c, string.Empty);
}
//if sku from PDF link, website response link, and pdf anchor text all match then change match
if (linkTextBuilder.Equals(webSite))
{
match = "MATCH";
}
//add data to datagridview
this.skuGrid.Rows.Add(i, null, linkTextBuilder, webSite, match, webStatus, hostIP);
//close http request and response
response.Close();
if (token.IsCancellationRequested)
{
// Clean up here, then...
token.ThrowIfCancellationRequested();
Log("Cancellation token: " + token);
MessageBox.Show("Scrape stopped");
throbber.Hide();
skuGrid.Show();
}
}
}
}
MessageBox.Show("Scrape complete");
throbber.Hide();
skuGrid.Show();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
Log("EXCEPTION ERROR: " + ex + " " + ex.HelpLink);
throbber.Hide();
skuGrid.Show();
}
finally
{
taskIsRunning = false;
//update grid
skuGrid.Update();
//close PDF reader
reader.Close();
WriteLog(log);
}
}
