We Keep Coding

OpenXml how to split a word document into pages

I want to split a Word document into separate pages and save them to files like Page_1.docx; Page_2.docx ......
At first I tried to do this:
using (var sourceWordDoc = WordprocessingDocument.Open(
wordFilePath
, false))
{
var sourceElements = sourceWordDoc.MainDocumentPart.Document.Body.Elements();
var pageElements = new List<DocumentFormat.OpenXml.OpenXmlElement>();
var pageIndex = 1;
foreach (var sourceElement in sourceElements)
{
var run = sourceElement.GetFirstChild<Run>();
if (run != null)
{
var lastRenderedPageBreak = run.GetFirstChild<LastRenderedPageBreak>();
var pageBreak = run.GetFirstChild<Break>();
if (lastRenderedPageBreak != null || pageBreak != null)
{
//Create and save page
using (var destinationWordDoc = WordprocessingDocument.Create(
$"Page_{pageIndex}.docx",
DocumentFormat.OpenXml.WordprocessingDocumentType.Document))
{
var destinationPart = destinationWordDoc.AddMainDocumentPart();
destinationPart.Document = new Document();
var destinationBody = destinationPart.Document.AppendChild(new Body());
foreach (var pageElement in pageElements)
{
destinationBody.Append(pageElement.CloneNode(true));
}
destinationPart.Document.Save();
}
pageElements.Clear();
pageIndex++;
}
}
pageElements.Add(sourceElement);
}
}
But in this variand, Header is not copied.
Then I wrote the following code to copy the Header (for test):
using (var sourceWordDoc = WordprocessingDocument.Open(
wordFilePath
, false))
{
var sourceHeaderPart = sourceWordDoc.MainDocumentPart.HeaderParts.FirstOrDefault();
var sourceDocument = sourceWordDoc.MainDocumentPart.Document;
using (var destinationWordDoc = WordprocessingDocument.Create(
somePath
, WordprocessingDocumentType.Document))
{
var destinationMainDocumentPart = destinationWordDoc.AddMainDocumentPart();
destinationMainDocumentPart.Document = new DocumentFormat.OpenXml.Wordprocessing.Document();
var destinationBody = destinationMainDocumentPart.Document.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Body());
var rId = string.Empty;
if (sourceHeaderPart != null)
{
var destinationHeaderPart = destinationMainDocumentPart.AddNewPart<HeaderPart>();
rId = destinationMainDocumentPart.GetIdOfPart(destinationHeaderPart);
destinationHeaderPart.FeedData(sourceHeaderPart.GetStream());
}
var sourceElements = sourceDocument.Body.Elements();
foreach (var sourceElement in sourceElements)
{
if (sourceElement.GetType() == typeof(DocumentFormat.OpenXml.Wordprocessing.SectionProperties))
{
var sourceSectionsElements = sourceElement.Elements();
foreach (var sourceSectionsElement in sourceSectionsElements)
{
if (sourceSectionsElement.GetType() == typeof(DocumentFormat.OpenXml.Wordprocessing.HeaderReference))
{
var sourceHeaderReference = (DocumentFormat.OpenXml.Wordprocessing.HeaderReference)sourceSectionsElement;
sourceHeaderReference.Id = rId;
break;
}
}
}
destinationBody.Append(sourceElement.CloneNode(true));
}
}
}
But now I have a new problem, images from the header are not transferred.
Are there any options to break the document into separate pages and at the same time preserve the entire content of the page?

Odoo rpc query with join in C#

I have this type of code to make a selection from Odoo Rpc:
XmlRpcClient client = new XmlRpcClient();
client.Url = LocalApplication.Url;
client.Path = "common";
// LOGIN BG
XmlRpcRequest requestLogin = new XmlRpcRequest("authenticate");
requestLogin.AddParams(LocalApplication.Db, LocalApplication.User, LocalApplication.Pass, XmlRpcParameter.EmptyStruct());
XmlRpcResponse responseLogin = client.Execute(requestLogin);
// READ
client.Path = "object";
// var x = client.Execute("select * from res_partner");
XmlRpcRequest requestSearch = new XmlRpcRequest("execute_kw");
requestSearch.AddParams(LocalApplication.Db, responseLogin.GetInt(),
LocalApplication.Pass, "res.partner", "search_read",
XmlRpcParameter.AsArray(
XmlRpcParameter.AsArray(
XmlRpcParameter.AsArray("is_agent", "=", "True".ToLower()))),
XmlRpcParameter.AsStruct(
XmlRpcParameter.AsMember("fields",
XmlRpcParameter.AsArray("name", "id", "phone", "email"))));
// SAVE
XmlRpcResponse responseSearch = client.Execute(requestSearch);
var agents = (responseSearch.GetObject() as List<object>);
Taswiq.Bussiness.Person p = new Person(LocalApplication.ConnectionString);
if (agents != null)
{
foreach (var a in agents)
{
Dictionary<string, object> agent = a as Dictionary<string, object>;
p.Name = agent["name"].ToString() == "False" ? "ND" : agent["name"].ToString();
p.Marca = Convert.ToInt32(agent["id"]);
p.Type = 1;
p.Phone = agent["phone"].ToString() == "False" ? "ND" : agent["phone"].ToString();
p.Email = agent["email"].ToString() == "False" ? "ND" : agent["email"].ToString();
MessageStruct result = p.Save();
if (result.HasErrors)
{
return result.Message;
}
}
return "Success";
}
All works fine, but now I need to make some join from this 2 tables like this:
Select *
from product_template as d
inner join product_product as r on r.product_tmpl_id = d.id;
I can't find anything but Python code.
Can anyone help me with that?

I think I found a solution. I do not know if is the best way but in my case it solved the problem.
I have made same list with every table that I need to go with join:
public List<object> lstStock = new List<object>();
public void PopulateStockList()
{
XmlRpcClient stock = new XmlRpcClient();
stock.Url = LocalApplication.Url;
stock.Path = "common";
//LOGIN BG
XmlRpcRequest requestLogin = new XmlRpcRequest("authenticate");
requestLogin.AddParams(LocalApplication.Db, LocalApplication.User,
LocalApplication.Pass,
XmlRpcParameter.EmptyStruct());
XmlRpcResponse responseLogin = stock.Execute(requestLogin);
//READ
stock.Path = "object";
XmlRpcRequest requestSearch = new XmlRpcRequest("execute_kw");
requestSearch.AddParams(LocalApplication.Db, responseLogin.GetInt(),
LocalApplication.Pass, "stock.quant", "search_read",
XmlRpcParameter.AsArray(
XmlRpcParameter.AsArray(
XmlRpcParameter.AsArray("id", ">", 0)
)
),
XmlRpcParameter.AsStruct(
XmlRpcParameter.AsMember("fields",
XmlRpcParameter.AsArray("product_id", "quantity", "in_date",
"owner_id"))
)
);
XmlRpcResponse responseSearch = stock.Execute(requestSearch);
lstStock = (responseSearch.GetObject() as List<object>);
}
Same way for every table that i need to join with.
And in the end, inside the foreach i made that join that i need to populate my sql table
public string DownloadRpcStock()
{
try
{
PopulateProdTemplate();
PopulateStockList();
PopulateProductList();
Stock s = new Stock(LocalApplication.ConnectionString);
foreach (var st in lstStock)
{
Dictionary<string, object> stc = st as Dictionary<string, object>;
var productId = stc["product_id"] as List<object>;
if (productId != null)
s.IdProduct = Convert.ToInt32(productId[0]); //Din lista care vine pe product_id imi iau valoarea dorita
s.IdStorage = 1;
s.StockQuantity = Convert.ToDouble(stc["quantity"]);
s.Rest = Convert.ToDouble(stc["quantity"]);
var prod = lstProduct.FirstOrDefault(
k => Convert.ToInt32((k as Dictionary<string, object>)["id"]) == Convert.ToInt32((stc["product_id"] as List<object>)[0])) as Dictionary<string, object>;
var prodTemplate =
lstProdTemplate.FirstOrDefault(
k => Convert.ToInt32((k as Dictionary<string, object>)["id"]) ==
Convert.ToInt32((prod["product_tmpl_id"] as List<object>)[0])) as Dictionary<string, object>;
if (prodTemplate != null)
s.Price = Convert.ToDouble(prodTemplate["list_price"]);
s.Batch = "NoBatch"; // Provizoriu
s.Date = Convert.ToDateTime(stc["in_date"]);
s.ExpireDate = Convert.ToDateTime(stc["in_date"]); // Provizoriu
s.IdCustomerSuplier = Convert.ToInt32(stc["owner_id"]);
s.Id = 0; //if (Id == 0) act = insert
MessageStruct result = s.Save();
if (result.HasErrors)
{
return result.Message;
}
}
return "Success";
}
catch (Exception ex)
{
return ex.Message;
}
}
I found many such questions on the internet without a solution.
I hope my solution will help someone else in the future.

How do I refactor the code which contains foreach loop

I need to refactor the below code so that the deleted_at logic will be outside of the foreach (var app in data) loop. I tried to create the list guids and then add guids to it but its not working because model.resources is inside the loop and it is still deleting all the apps.
I need deleted_at logic outside because I'm trying to delete all apps which are in the database but are not in new data that I'm receiving from API.
If you have a better approach on my code I would love to see that, Thank you.
public async Task GetBuilds()
{
var data = new List<GetBuildTempClass>();
var guids = new List<GetBuildTempClass>();
using (var scope = _scopeFactory.CreateScope())
{
var _DBcontext = scope.ServiceProvider.GetRequiredService<PCFStatusContexts>();
foreach (var app in data)
{
var request = new HttpRequestMessage(HttpMethod.Get,
"apps/" + app.AppGuid + "/builds?per_page=200&order_by=updated_at");
var response = await _client_SB.SendAsync(request);
var json = await response.Content.ReadAsStringAsync();
BuildsClass.BuildsRootObject model =
JsonConvert.DeserializeObject<BuildsClass.BuildsRootObject>(json);
foreach (var item in model.resources)
{
var x = _DBcontext.Builds.FirstOrDefault(o =>
o.Guid == Guid.Parse(item.guid));
if (x == null)
{
_DBcontext.Builds.Add(new Builds
{
Guid = Guid.Parse(item.guid),
State = item.state,
CreatedAt = item.created_at,
UpdatedAt = item.updated_at,
Error = item.error,
CreatedByGuid = Guid.Parse(item.created_by.guid),
CreatedByName = item.created_by.name,
CreatedByEmail = item.created_by.email,
AppGuid = app.AppGuid,
AppName = app.AppName,
Foundation = 2,
Timestamp = DateTime.Now
});
}
else if (x.UpdatedAt != item.updated_at)
{
x.State = item.state;
x.UpdatedAt = item.updated_at;
x.Timestamp = DateTime.Now;
}
var sqlresult = new GetBuildTempClass
{
AppGuid = Guid.Parse(item.guid)
};
guids.Add(sqlresult);
}
//var guids = model.resources.Select(r => Guid.Parse(r.guid));
var builds = _DBcontext.Builds.Where(o =>
guids.Contains(o.Guid) == false &&
o.Foundation == 2 && o.DeletedAt == null);
foreach (var build_item in builds)
{
build_item.DeletedAt = DateTime.Now;
}
}
await _DBcontext.SaveChangesAsync();
}
}

I got it working I added var guids = new List < Guid > (); list to store data,
added guids.Add(Guid.Parse(item.guid)); to populate the list and finally wrote var builds = _DBcontext.Builds.Where(o = >guids.Contains(o.Guid) == false && o.Foundation == 2 && o.DeletedAt == null); outside the loop.
If anyone has a better suggestion please add a new answer.
public async Task GetBuilds() {
var data = new List < GetBuildTempClass > ();
var guids = new List < Guid > ();
using(var scope = _scopeFactory.CreateScope()) {
var _DBcontext = scope.ServiceProvider.GetRequiredService < PCFStatusContexts > ();
foreach(var app in data) {
var request = new HttpRequestMessage(HttpMethod.Get, "apps/" + app.AppGuid + "/builds?per_page=200&order_by=updated_at");
var response = await _client_SB.SendAsync(request);
var json = await response.Content.ReadAsStringAsync();
BuildsClass.BuildsRootObject model = JsonConvert.DeserializeObject < BuildsClass.BuildsRootObject > (json);
foreach(var item in model.resources) {
var x = _DBcontext.Builds.FirstOrDefault(o = >o.Guid == Guid.Parse(item.guid));
if (x == null) {
_DBcontext.Builds.Add(new Builds {
Guid = Guid.Parse(item.guid),
State = item.state,
CreatedAt = item.created_at,
UpdatedAt = item.updated_at,
Error = item.error,
CreatedByGuid = Guid.Parse(item.created_by.guid),
CreatedByName = item.created_by.name,
CreatedByEmail = item.created_by.email,
AppGuid = app.AppGuid,
AppName = app.AppName,
Foundation = 2,
Timestamp = DateTime.Now
});
}
else if (x.UpdatedAt != item.updated_at) {
x.State = item.state;
x.UpdatedAt = item.updated_at;
x.Timestamp = DateTime.Now;
}
guids.Add(Guid.Parse(item.guid));
}
}
var builds = _DBcontext.Builds.Where(o = >guids.Contains(o.Guid) == false && o.Foundation == 2 && o.DeletedAt == null);
foreach(var build_item in builds) {
build_item.DeletedAt = DateTime.Now;
}
await _DBcontext.SaveChangesAsync();
}
}

Get string data Xpath

I need help to get data from the site. I use geckofx in my application. I want it to retrieve text data from the xpath location after loading the page
XPathResult xpathResult = geckoWebBrowser1.Document.EvaluateXPath("/html/body/table[3]/tbody/tr[1]/td[2]/a[1]");
IEnumerable<GeckoNode> foundNodes = xpathResult.GetNodes();
How to download data as text?

It looks like you are struggling to retrieve the text from the GeckoFX objects.
Here are a few calls and operations that should get you started:
//get by XPath
XPathResult xpathResult = _browser.Document.EvaluateXPath("//*[#id]/div/p[2]");
var foundNodes = xpathResult.GetNodes();
foreach (var node in foundNodes)
{
var x = node.TextContent; // get text text contained by this node (including children)
GeckoHtmlElement element = node as GeckoHtmlElement; //cast to access.. inner/outerHtml
string inner = element.InnerHtml;
string outer = element.OuterHtml;
//iterate child nodes
foreach (var child in node.ChildNodes)
{
}
}
//get by id
GeckoHtmlElement htmlElementById = _browser.Document.GetHtmlElementById("mw-content-text");
//get by tag
GeckoElementCollection byTag = _browser.Document.GetElementsByTagName("input");
foreach (var ele in byTag)
{
var y = ele.GetAttribute("value");
}
//get by class
var byClass = _browser.Document.GetElementsByClassName("input");
foreach (var node in byClass)
{
//...
}
//cast to a different object
var username = ((GeckoInputElement)_browser.Document.GetHtmlElementById("yourUsername")).Value;
//create new object from DomObject
var button = new GeckoButtonElement(_browser.Document.GetElementById("myBtn").DomObject);

public string extract(string xpath, string type)
{
string result = string.Empty;
GeckoHtmlElement elm = null;
GeckoWebBrowser wb = geckoWebBrowser1;//(GeckoWebBrowser)GetCurrentWB();
if (wb != null)
{
elm = GetElement(wb, xpath);
if (elm != null)
//UpdateUrlAbsolute(wb.Document, elm);
if (elm != null)
{
switch (type)
{
case "html":
result = elm.OuterHtml;
break;
case "text":
if (elm.GetType().Name == "GeckoTextAreaElement")
{
result = ((GeckoTextAreaElement)elm).Value;
}
else
{
result = elm.TextContent.Trim();
}
break;
case "value":
result = ((GeckoInputElement)elm).Value;
break;
default:
result = extractData(elm, type);
break;
}
}
}
return result;
}
private string extractData(GeckoHtmlElement ele, string attribute)
{
var result = string.Empty;
if (ele != null)
{
var tmp = ele.GetAttribute(attribute);
/*if (tmp == null)
{
tmp = extractData(ele.Parent, attribute);
}*/
if (tmp != null)
result = tmp.Trim();
}
return result;
}
private object GetCurrentWB()
{
if (tabControl1.SelectedTab != null)
{
if(tabControl1.SelectedTab.Controls.Count > 0)
//if (tabControl1.SelectedTab.Controls.Count > 0)
{
Control ctr = tabControl1.SelectedTab.Controls[0];
if (ctr != null)
{
return ctr as object;
}
}
}
return null;
}
private GeckoHtmlElement GetElement(GeckoWebBrowser wb, string xpath)
{
GeckoHtmlElement elm = null;
if (xpath.StartsWith("/"))
{
if (xpath.Contains("#class") || xpath.Contains("#data-type"))
{
var html = GetHtmlFromGeckoDocument(wb.Document);
HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
doc.LoadHtml(html);
var node = doc.DocumentNode.SelectSingleNode(xpath);
if (node != null)
{
var currentXpath = "/" + node.XPath;
elm = (GeckoHtmlElement)wb.Document.EvaluateXPath(currentXpath).GetNodes().FirstOrDefault();
}
}
else
{
elm = (GeckoHtmlElement)wb.Document.EvaluateXPath(xpath).GetNodes().FirstOrDefault();
}
}
else
{
elm = (GeckoHtmlElement)wb.Document.GetElementById(xpath);
}
return elm;
}
private string GetHtmlFromGeckoDocument(GeckoDocument doc)
{
var result = string.Empty;
GeckoHtmlElement element = null;
var geckoDomElement = doc.DocumentElement;
if (geckoDomElement is GeckoHtmlElement)
{
element = (GeckoHtmlElement)geckoDomElement;
result = element.InnerHtml;
}
return result;
}
private void button5_Click(object sender, EventArgs e)
{
var text = extract("/html/body/table[3]/tbody/tr[1]/td[2]/a[2]", "text");
MessageBox.Show(text);
}
I also insert the code from which I used a little longer code but it also works. maybe someone will need it. The creator of the code is Đinh Công Thắng, Web Automation App,
Regards

Instagram API: How to insert all user media in c# asp.net mvc?

I am trying the get all user media from the instagram api and store into database but how can do that i don't know. i am write the code but using this code just add one media in the database. any one have the idea then please let me know how can do that. here below list the my code.
This is my C# method :
public string makePostFromInstagram()
{
var serializer1 = new System.Web.Script.Serialization.JavaScriptSerializer();
var nodes1 = serializer1.Deserialize<dynamic>(GetData(strInstagramUserId));
foreach (var date in nodes1)
{
if (date.Key == "data")
{
string theKey = date.Key;
var thisNode = date.Value;
int userCount = 0;
foreach (var post in thisNode)
{
if (thisNode[userCount]["username"] == strInstagramUserId)
{
id = thisNode[userCount]["id"].ToString();
}
userCount++;
}
}
}
var serializer = new System.Web.Script.Serialization.JavaScriptSerializer();
Dictionary<string, object> csObj = serializer.Deserialize<Dictionary<string, object>>(GetRecentPost(id, accessToken));
int length = ((ArrayList)csObj["data"]).Count;
var nodes = serializer.Deserialize<dynamic>(GetRecentPost(id, accessToken));
foreach (var date in nodes)
{
if (date.Key == "data")
{
string theKey = date.Key;
var thisNode = date.Value;
foreach (var post in thisNode)
{
UsersOnInstagram objUserInsta = new UsersOnInstagram();
string result = null;
//here i am add just one image so i want to here add multiple image insert
if (post["type"] == "image")
result = UsersOnInstagram.addInstagramPost(strPtId, HttpUtility.UrlEncode(post["caption"]["text"]), post["images"]["standard_resolution"]["url"], UnixTimeStampToDateTime(Convert.ToDouble(post["created_time"])), null, post["type"]);
else if (post["type"] == "video")
result = objUserInsta.addInstagramPost(HttpUtility.UrlEncode(post["caption"]["text"]), strPtId, post["images"]["standard_resolution"]["url"], UnixTimeStampToDateTime(Convert.ToDouble(post["created_time"])), post["videos"]["standard_resolution"]["url"], post["type"]);
}
}
}
Response.End();
}
this is my api method :
public static string GetRecentPost(string instagramaccessid, string instagramaccesstoken)
{
Double MAX_TIMESTAMP = DateTimeToUnixTimestamp(DateTime.Today.AddDays(-1));
Double MIN_TIMESTAMP = DateTimeToUnixTimestamp(DateTime.Today.AddDays(-2));
string url = "https://api.instagram.com/v1/users/" + instagramaccessid + "/media/recent?access_token=" + instagramaccesstoken + "&min_timestamp=" + MIN_TIMESTAMP + "&maz_timestamp=" + MAX_TIMESTAMP;
var webClient = new System.Net.WebClient();
string d = webClient.DownloadString(url);
return d;
}
any one know how can do that please let me know.