virtual public void test()
{
PdfReader reader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, "user10.pdf");
Rectangle rectangle = new Rectangle(71, 792 - 84, 225, 792 - 75);
RenderFilter filter = new RegionTextRenderFilter(rectangle);
String txt = PdfTextExtractor.GetTextFromPage(reader, 1, new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter));
Assert.AreEqual("Pname Dname Email Address", txt);
}
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 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);
}
static void Main(string[] args)
{
//string strFile = @"D:\yoo\【着色算法】可根据不同着色技巧对图示进行重新染色.pdf";
string strFile = @"D:\yoo\张甜甜-Java开发.pdf";
PdfDocument doc = new PdfDocument();
PdfReader reader = new PdfReader(strFile);
for (int i = 1; i <= reader.NumberOfPages; i++)
{
RenderFilter fontFilter = new RegionTextRenderFilter(reader.GetPageSize(i));
ITextExtractionStrategy strategy = new TextWithFontExtractionStategy();
string s = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
}
}
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);
}
public static void ExtractIDs()
{
PdfReader reader = new PdfReader($@"{jobDir}\PDF Extraction\temp\{sourcePDF}");
FileStream fs = new FileStream($@"{jobDir}\PDF Extraction\temp\extractedIDs.txt", FileMode.Create);
StreamWriter sw = new StreamWriter(fs);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ITextExtractionStrategy strategy;
TextMarginFinder finder;
string previousVal = "";
string currentVal = "";
int count = 0;
string pages = "";
sw.WriteLine("Index\tID\tPageCounter\tPageNumber\tFileName");
for (int i = 1; i <= reader.NumberOfPages; i++)
{
try
{
// finder = parser.ProcessContent(i, new TextMarginFinder());
//Rectangle area = new Rectangle(finder.GetLlx(), finder.GetLly(), finder.GetWidth() / 2, finder.GetHeight() / 2);
Rectangle area = new Rectangle(414, 660, 522, 689);
RenderFilter filter = new RegionTextRenderFilter(area);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
currentVal = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
Rectangle area2 = new Rectangle(465, 565, 555, 635);
RenderFilter filter2 = new RegionTextRenderFilter(area2);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter2);
pages = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
if (previousVal != currentVal)
{
count = 0;
}
count++;
previousVal = currentVal;
sw.WriteLine($"{i}\t{currentVal}\t{pages.Split('\n')[0]}\t{count}\t{currentVal}-{count}");
}
catch (Exception)
{
sw.WriteLine($"{i}\tfailed");
}
}
sw.Flush();
sw.Close();
}
virtual public void Test()
{
PdfReader pdfReader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, "test.pdf");
String[] expectedText = new String[] {
"PostScript Compatibility",
"Because the PostScript language does not support the transparent imaging \n" +
"model, PDF 1.4 consumer applications must have some means for converting the \n" +
"appearance of a document that uses transparency to a purely opaque description \n" +
"for printing on PostScript output devices. Similar techniques can also be used to \n" +
"convert such documents to a form that can be correctly viewed by PDF 1.3 and \n" +
"earlier consumers. ",
"Otherwise, flatten the colors to some assumed device color space with pre-\n" +
"determined calibration. In the generated PostScript output, paint the flattened \n" +
"colors in a CIE-based color space having that calibration. "
};
Rectangle[] regions = new Rectangle[] {
new Rectangle(90, 605, 220, 581),
new Rectangle(80, 578, 450, 486), new Rectangle(103, 196, 460, 143)
};
RegionTextRenderFilter[] regionFilters = new RegionTextRenderFilter[regions.Length];
for (int i = 0; i < regions.Length; i++)
{
regionFilters[i] = new RegionTextRenderFilter(regions[i]);
}
MultiFilteredRenderListener listener = new MultiFilteredRenderListener();
LocationTextExtractionStrategy[] extractionStrategies = new LocationTextExtractionStrategy[regions.Length];
for (int i = 0; i < regions.Length; i++)
{
extractionStrategies[i] =
(LocationTextExtractionStrategy)
listener.AttachRenderListener(new LocationTextExtractionStrategy(), regionFilters[i]);
}
new PdfReaderContentParser(pdfReader).ProcessContent(1, listener);
for (int i = 0; i < regions.Length; i++)
{
String actualText = extractionStrategies[i].GetResultantText();
Assert.AreEqual(expectedText[i], actualText);
}
}
/// <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);
}
}
void TakeDataFromPdf(UnityWebRequest www)
{
MemoryStream mm = new MemoryStream(www.downloadHandler.data);
bytes = mm.ToArray();
PdfReader reader = new PdfReader(mm);
ITextExtractionStrategy strategy;
for (int q = 0; q < 6; q++)
{
for (int j = 0; j < 8; j++)
{
Rectangle rect = new Rectangle(45 + (j * Adeltax), 40 + (q * Adeltay), 138 + (j * Bdeltax), 130 + (q * Bdeltay));
RenderFilter filter = new RegionTextRenderFilter(rect);
string s;
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = "";
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
//step1_____________________________________
if (IsLaba(s))
{
float microBdeltaX = 0;
if (j == 0)
{
microBdeltaX = Bdeltax;
}
Bdeltax *= 2;
rect = new Rectangle(45 + (j * Adeltax), 40 + (q * Adeltay), 138 + (j * Bdeltax) + microBdeltaX, 130 + (q * Bdeltay));
filter = new RegionTextRenderFilter(rect);
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
j++;
Bdeltax /= 2;
}
nakedData.Add(s);
}
}
mm.Close();
}
public string ExtractByCoordinate()
{
ITextExtractionStrategy strategy;
Rectangle rectangle = new Rectangle(320, 785 - 250, 368, 799 - 250);
// Rectangle rectangle = new Rectangle(447, 934-250, 678, 951); -> Ok
RenderFilter filter = new RegionTextRenderFilter(rectangle);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
Console.WriteLine(PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy));
}
return(null);
}
public string ExtractData(float UIWith, float UIHeight, Point ll, Point ur,
int page = 1)
{
Console.WriteLine("Test");
float MultX = PageSize().Width / UIWith;
float MultY = PageSize().Height / UIHeight;
ITextExtractionStrategy strategy;
Rectangle rectangle = new Rectangle(ll.X * MultX, (UIHeight - ll.Y) * MultY, ur.X * MultX, (UIHeight - ur.Y) * MultY);
// Rectangle rectangle = new Rectangle(447, 934-250, 678, 951); // -> Ok
RenderFilter filter = new RegionTextRenderFilter(rectangle);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
// return "" + UIWith + " " + UIHeight + " " + ll.X + " " + ll.Y + " " + ur.X + " " + ur.Y;
return(PdfTextExtractor.GetTextFromPage(PdfReader, page, strategy));
}
public static string ReadID(string fileName)
{
try
{
PdfReader reader = new PdfReader(fileName);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ITextExtractionStrategy strategy;
//TextMarginFinder finder;
//finder = parser.ProcessContent(1, new TextMarginFinder());
Rectangle area = new Rectangle(414, 660, 522, 689);
RenderFilter filter = new RegionTextRenderFilter(area);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
return(PdfTextExtractor.GetTextFromPage(reader, 1, strategy));
}
catch (Exception)
{
return("unreadable");
}
}
public string GetTextInArea(string filename, int page, int x, int y, int width, int height)
{
string text = string.Empty;
using (PdfReader pdfReader = new PdfReader(filename))
{
RenderFilter filter = new RegionTextRenderFilter(new System.util.RectangleJ(x, y, width, height));
var strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
//var strategy = new SimpleTextExtractionStrategy();
text = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
text = Encoding.UTF8.GetString(ASCIIEncoding.Convert(
Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(text)));
}
return(text);
}
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);
}
}
public bool TakeSomeCellOfData(int x)
{
int y = 0;
x = EnterManager.instance.checkNumberOfLesson(x, ref y);
MemoryStream mm = new MemoryStream(bytes);
PdfReader reader = new PdfReader(mm);
ITextExtractionStrategy strategy;
RenderFilter filter;
string s;
Rectangle rect = new Rectangle(45 + (x * Adeltax), 40 + (y * Adeltay), 138 + (x * Bdeltax), 130 + (y * Bdeltay));
filter = new RegionTextRenderFilter(rect);
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
if (s.Contains("семинар") || s.Contains("лекции"))
{
return(true);
}
return(false);
}
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);
}
}
