foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//script").Where(x => x.InnerHtml.Contains("DealerId:")))
{
}
I am trying to get value of dealer id with the help of above code but it is not returning anything, but if you trying to find DealerId from page source of above website then it is there. please help me to achieve this or if anything wrong with above code then please correct me.
you can parse JS code with something like (https://github.com/sebastienros/jint) and extract the field you need from JS object
you can simple find this text (not elegant, but works):
UPD1: regex version
static void Main(string[] args)
{
var url = "https://www.171chryslerdodgejeepram.com/";
var web = new HtmlWeb();
var doc = web.Load(url);
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//script").Where(x => x.InnerHtml.Contains("dealerId:")))
{
var s = node.InnerText;
Regex r = new Regex(#"dealerId:\s+'(\d+)'");
Match m = r.Match(s);
Console.WriteLine(m.Groups[1].Value);
}
Console.ReadKey();
}
var url = "https://www.171chryslerdodgejeepram.com/";
var web = new HtmlWeb();
var doc = web.Load(url);
foreach (HtmlNode node in doc.DocumentNode.SelectNodes("//script").Where(x => x.InnerHtml.ToLower().Contains("dealerid")))
{
AdwordsAccount info = new AdwordsAccount();
var s = node.InnerText;
//Regex r = new Regex("dealerid(.*?)\",");
Regex r = new Regex(#"dealerId:\s+'(\d+)'");
Match m = r.Match(s.ToLower());
info.account = m.Groups[1].Value;
urlinfo.adwordsaccount.Add(info);
}
#cereberus this is my code
I'm trying to program an API for discord and I need to retrieve two pieces of information out of the HTML code of the web page https://myanimelist.net/character/214 (and other similar pages with URLs of the form https://myanimelist.net/character/N for integers N), specifically the URL of the Character Picture (in this case https://cdn.myanimelist.net/images/characters/14/54554.jpg) and the name of the character (in this case Youji Kudou). Afterwards I need to save those two pieces of information to JSON.
I am using HTMLAgilityPack for this, yet I can't quite see through it. The following is my first attempt:
public static void Main()
{
var html = "https://myanimelist.net/character/214";
HtmlWeb web = new HtmlWeb();
var htmlDoc = web.Load(html);
var htmlNodes = htmlDoc.DocumentNode.SelectNodes("//body");
foreach (var node in htmlNodes.Descendants("tr/td/div/a/img"))
{
Console.WriteLine(node.InnerHtml);
}
}
Unfortunately, this produces no output. If I followed the path correctly (which is probably the first mistake) it should be "tr/td/div/a/img". I get no errors, it runs, yet I get no output.
My second attempt is:
public static void Main()
{
var html = "https://myanimelist.net/character/214";
HtmlWeb web = new HtmlWeb();
var htmlDoc = web.Load(html);
var htmlNodes = htmlDoc.DocumentNode.SelectNodes("//body");
HtmlAgilityPack.HtmlDocument doc = new HtmlAgilityPack.HtmlDocument();
var script = htmlDoc.DocumentNode.Descendants()
.Where(n => n.Name == "tr/td/a/img")
.First().InnerText;
// Return the data of spect and stringify it into a proper JSON object
var engine = new Jurassic.ScriptEngine();
var result = engine.Evaluate("(function() { " + script + " return src; })()");
var json = JSONObject.Stringify(engine, result);
Console.WriteLine(json);
Console.ReadKey();
}
But this also doesn't work.
How can I extract the required information?
EDIT:
So, I've come quite further now, and I've found a solution to finding the link. It was rather simple. But now I'm stuck with finding the name of the character. The website is structured the same on every other link there is (changing the last number) so, I want to find many different ones via for loop. Here's how I tried to do it:
for (int i = 1; i <= 1000; i++)
{
HtmlWeb web = new HtmlWeb();
var html = "https://myanimelist.net/character/" + i;
var htmlDoc = web.Load(html);
foreach (var item in htmlDoc.DocumentNode.SelectNodes("//*[#]"))
{
string n;
n = item.GetAttributeValue("src", "");
foreach (var item2 in htmlDoc.DocumentNode.SelectNodes("//*[#src and #alt='" + n + "']"))
{
Console.WriteLine(item2.GetAttributeValue("src", ""));
}
}
}
in the first foreach I would try to search for the name, which is concluded always at the same position (e.g http://prntscr.com/o1uo3c and http://prntscr.com/o1uo91 and to be specific: http://prntscr.com/o1xzbk) but I haven't found out how yet. Since the structure in the HTML doesn't have any body type I can follow up with. The second foreach loop is to search for the URL which works by now and the n should give me the name, so I can figure it out for each different character.
I was able to extract the character name and image from https://myanimelist.net/character/214 using the following method:
public static CharacterData ExtractCharacterNameAndImage(string url)
{
//Use the following if you are OK with hardcoding the structure of <div> elements.
//var tableXpath = "/html/body/div[1]/div[3]/div[3]/div[2]/table";
//Use the following if you are OK with hardcoding the fact that the relevant table comes first.
var tableXpath = "/html/body//table";
var nameXpath = "tr/td[2]/div[4]";
var imageXpath = "tr/td[1]/div[1]/a/img";
var htmlDoc = new HtmlWeb().Load(url);
var table = htmlDoc.DocumentNode.SelectNodes(tableXpath).First();
var name = table.SelectNodes(nameXpath).Select(n => n.GetDirectInnerText().Trim()).SingleOrDefault();
var imageUrl = table.SelectNodes(imageXpath).Select(n => n.GetAttributeValue("src", "")).SingleOrDefault();
return new CharacterData { Name = name, ImageUrl = imageUrl, Url = url };
}
Where CharacterData is defined as follows:
public class CharacterData
{
public string Name { get; set; }
public string ImageUrl { get; set; }
public string Url { get; set; }
}
Afterwards, the character data can be serialized to JSON using any of the tools from How to write a JSON file in C#?, e.g. json.net:
var url = "https://myanimelist.net/character/214";
var data = ExtractCharacterNameAndImage(url);
var json = JsonConvert.SerializeObject(data, Formatting.Indented);
Console.WriteLine(json);
Which outputs
{
"Name": "Youji Kudou",
"ImageUrl": "https://cdn.myanimelist.net/images/characters/14/54554.jpg",
"Url": "https://myanimelist.net/character/214"
}
If you would prefer the Name to include the Japanese in parenthesis, replace GetDirectInnerText() with just InnerText, which results in:
{
"Name": "Youji Kudou (工藤耀爾)",
"ImageUrl": "https://cdn.myanimelist.net/images/characters/14/54554.jpg",
"Url": "https://myanimelist.net/character/214"
}
Alternatively, if you prefer you could pull the character name from the document title:
var title = string.Concat(htmlDoc.DocumentNode.SelectNodes("/html/head/title").Select(n => n.InnerText.Trim()));
var index = title.IndexOf("- MyAnimeList.net");
if (index >= 0)
title = title.Substring(0, index).Trim();
How did I determine the correct XPath strings?
Firstly, using Firefox 66, I opened the debugger and loaded https://myanimelist.net/character/214 in the window with the debugging tools visible.
Next, following the instructions from How to find xpath of an element in firefox inspector, I selected the Youji Kudou (工藤耀爾) node and copied its XPath, which turned out to be:
/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[2]/div[4]
I then tried to select this node using SelectNodes()... and got a null result. But why? To determine this I created a debugging routine that would break the path into successively longer portions and determine where the failure occurs:
static void TestSelect(HtmlDocument htmlDoc, string xpath)
{
Console.WriteLine("\nInput path: " + xpath);
var splitPath = xpath.Split('/');
for (int i = 2; i <= splitPath.Length; i++)
{
if (splitPath[i-1] == "")
continue;
var thisPath = string.Join("/", splitPath, 0, i);
Console.Write("Testing \"{0}\": ", thisPath);
var result = htmlDoc.DocumentNode.SelectNodes(thisPath);
Console.WriteLine("result count = {0}", result == null ? "null" : result.Count.ToString());
}
}
This output the following:
Input path: /html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[2]/div[4]
Testing "/html": result count = 1
Testing "/html/body": result count = 1
Testing "/html/body/div[1]": result count = 1
Testing "/html/body/div[1]/div[3]": result count = 1
Testing "/html/body/div[1]/div[3]/div[3]": result count = 1
Testing "/html/body/div[1]/div[3]/div[3]/div[2]": result count = 1
Testing "/html/body/div[1]/div[3]/div[3]/div[2]/table": result count = 1
Testing "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody": result count = null
Testing "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr": result count = null
Testing "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[2]": result count = null
Testing "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[2]/div[4]": result count = null
As you can see, something goes wrong selecting the <tbody> path element. Manual inspection of the InnerHtml returned by selecting /html/body/div[1]/div[3]/div[3]/div[2]/table revealed that, for some reason, the server is not including the <tbody> tag when returning HTML to the HtmlWeb object -- possibly due to some difference in request header(s) provided by Firefox vs HtmlWeb. Once I omitted the tbody path element I was able to query for the character name successfully using:
/html/body/div[1]/div[3]/div[3]/div[2]/table/tr/td[2]/div[4]
A similar process provided the following working path for the image:
/html/body/div[1]/div[3]/div[3]/div[2]/table/tr/td[1]/div[1]/a/img
Since the two queries are finding contents in the same <table>, in my final code I selected the table only once in a separate step, and removed some of the hardcoding as to the specific nesting of <div> elements.
Demo fiddle here.
Alright, to finnish it up, I've rounded the Code, gratefully assisted by dbc, and implemented nearly completly into the project. Just if someone in later days maybe has a identical question, here they go. This outputs out of a defined number all the character names, links and images and writes it into a JSON file and could be adapted for other websites.
using System;
using System.Linq;
using Newtonsoft.Json;
using HtmlAgilityPack;
using System.IO;
namespace SearchingHTML
{
public class CharacterData
{
public string Name { get; set; }
public string ImageUrl { get; set; }
public string Url { get; set; }
}
public class Program
{
public static CharacterData ExtractCharacterNameAndImage(string url)
{
var tableXpath = "/html/body//table";
var nameXpath = "tr/td[2]/div[4]";
var imageXpath = "tr/td[1]/div[1]/a/img";
var htmlDoc = new HtmlWeb().Load(url);
var table = htmlDoc.DocumentNode.SelectNodes(tableXpath).First();
var name = table.SelectNodes(nameXpath).Select(n => n.GetDirectInnerText().Trim()).SingleOrDefault();
var imageUrl = table.SelectNodes(imageXpath).Select(n => n.GetAttributeValue("src", "")).SingleOrDefault();
return new CharacterData { Name = name, ImageUrl = imageUrl, Url = url };
}
public static void Main()
{
int max = 10000;
string fileName = #"C:\Users\path of your file.json";
Console.WriteLine("Environment version: " + Environment.Version);
Console.WriteLine("Json.NET version: " + typeof(JsonSerializer).Assembly.FullName);
Console.WriteLine("HtmlAgilityPack version: " + typeof(HtmlDocument).Assembly.FullName);
Console.WriteLine();
for (int i = 6; i <= max; i++)
{
try
{
var url = "https://myanimelist.net/character/" + i;
var htmlDoc = new HtmlWeb().Load(url);
var data = ExtractCharacterNameAndImage(url);
var json = JsonConvert.SerializeObject(data, Formatting.Indented);
Console.WriteLine(json);
TextWriter tsw = new StreamWriter(fileName, true);
tsw.WriteLine(json);
tsw.Close();
} catch (Exception ex) { }
}
}
}
}
/*******************************************************************************************************************************
****************************************************IF TESTING IS REQUIERED****************************************************
*******************************************************************************************************************************
*
* static void TestSelect(HtmlDocument htmlDoc, string xpath)
Console.WriteLine("\nInput path: " + xpath);
var splitPath = xpath.Split('/');
for (int i = 2; i <= splitPath.Length; i++)
{
if (splitPath[i - 1] == "")
continue;
var thisPath = string.Join("/", splitPath, 0, i);
Console.Write("Testing \"{0}\": ", thisPath);
var result = htmlDoc.DocumentNode.SelectNodes(thisPath);
Console.WriteLine("result count = {0}", result == null ? "null" : result.Count.ToString());
}
}
*******************************************************************************************************************************
*********************************************FOR TESTING ENTER THIS INTO MAIN CLASS********************************************
*******************************************************************************************************************************
*
* var url2 = "https://myanimelist.net/character/256";
var data2 = ExtractCharacterNameAndImage(url2);
var json2 = JsonConvert.SerializeObject(data2, Formatting.Indented);
Console.WriteLine(json2);
var nameXpathFromFirefox = "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[2]/div[4]";
var imageXpathFromFirefox = "/html/body/div[1]/div[3]/div[3]/div[2]/table/tbody/tr/td[1]/div[1]/a/img";
TestSelect(htmlDoc, nameXpathFromFirefox);
TestSelect(htmlDoc, imageXpathFromFirefox);
var nameXpathFromFirefoxFixed = "/html/body/div[1]/div[3]/div[3]/div[2]/table/tr/td[2]/div[4]";
var imageXpathFromFirefoxFixed = "/html/body/div[1]/div[3]/div[3]/div[2]/table/tr/td[1]/div[1]/a/img";
TestSelect(htmlDoc, nameXpathFromFirefoxFixed);
TestSelect(htmlDoc, imageXpathFromFirefoxFixed);
*******************************************************************************************************************************
*******************************************************************************************************************************
*******************************************************************************************************************************
*/
I am attempting to create a crawler that returns only links from a website and i have it to a point that it returns the HTML script.
I am now wanting to use an if statement to check that the string is returned and if it is returned, it searches for all "< a >" tags and shows me the href link.
but I don't know what object to check or what value I should be checking for.
Here is what I have so far:
namespace crawler
{
class Program
{
static void Main(string[] args)
{
System.Net.WebClient wc = new System.Net.WebClient();
string WebData wc.DownloadString("https://www.abc.net.au/news/science/");
Console.WriteLine(WebData);
// if
}
}
}
You can have a look at HTML Agility Pack:
Then you can find all links from a web page like:
var hrefs = new List<string>();
var hw = new HtmlWeb();
HtmlDocument document = hw.Load(/* your url here */);
foreach(HtmlNode link in document.DocumentNode.SelectNodes("//a[#href]"))
{
HtmlAttribute attribute = link.Attributes["href"];
if (!string.IsNullOrWhiteSpace(attribute.Value))
hrefs.Add(attribute.Value);
}
Firstly you can make a function to return the whole website HTML code as you have done. Here is the one I have!
public string GetPageContents()
{
string link = "https://www.abc.net.au/news/science/"
string pageContent = "";
WebClient web = new WebClient();
Stream stream;
stream = web.OpenRead(link);
using (StreamReader reader = new StreamReader(stream))
{
pageContent = reader.ReadToEnd();
}
stream.Close();
return pageContents;
}
Then you could make a function that would return a substring or a List of substring (meaning that if you wanted all < a > tags you would probably get more than one).
List<string> divTags = GetBetweenTags(pageContents, "<div>", "</div>")
This would give you a list where you could, for example, make another search for < a > tags inside each of those < div > tags.
public List<string> GetBetweenTags(string pageContents, string startTag, string endTag)
{
Regex rx = new Regex(startTag + "(.*?)" + endTag);
MatchCollection col = rx.Matches(value);
List<string> tags = new List<string>();
foreach(Match s in col)
tags.Add(s.ToString());
return tags;
}
Edit: Wow didn't know of HTML Agility Pack, thanks #Gauravsa i'll update my project to use it!
I'm trying to modify the code below to scrape jobs from www.itoworld.com/careers. The jobs are in a table format and return all the <'td> values.
I believe it comes from the line:
var parentnode = node.ParentNode.ParentNode.ParentNode.FirstChild.NextSibling
However, I want it to write:
<a class="std-btn" href="http://www.itoworld.com/office-manager/">Office Manager</a>
Currently it is writing
<a href='http://www.itoworld.com/office-manager/' target='_blank'>Office ManagerOffice & AdminCambridgeFind out more</a>
I plan on 'brute force' modifying the output to remove unnecessary extras but was hoping there is a smarter way to do this. Is there a way for example to remove the second and third ParentNode after they have been called? (So they do not get written?)
public string ExtractIto()
{
string sUrl = "http://www.itoworld.com/careers/";
GlobusHttpHelper ghh = new GlobusHttpHelper();
List<Links> link = new List<Links>();
bool Next = true;
int count = 1;
string html = ghh.getHtmlfromUrl(new Uri(string.Format(sUrl)));
HtmlAgilityPack.HtmlDocument hd = new HtmlAgilityPack.HtmlDocument();
hd.LoadHtml(html);
var hn = hd.DocumentNode.SelectSingleNode("//*[#class='btn-wrapper']");
var hnc = hn.SelectNodes(".//a");
foreach (var node in hnc)
{
try
{
var parentnode = node.ParentNode.ParentNode.ParentNode.FirstChild.NextSibling;
Links l = new Links();
l.Name = ParseHtmlContainingText(parentnode.InnerText);
l.Link = node.GetAttributeValue("href", "");
link.Add(l);
}
}
string Xml = getXml(link);
return WriteXml(Xml);
For completeness below is the definition of ParseHtmlContainingText
public string ParseHtmlContainingText(string htmlString)
{
return Regex.Replace(Regex.Replace(WebUtility.HtmlDecode(htmlString), #"<[^>]+>| ", ""), #"\s{2,}", " ").Trim();
}
You just need to create a "name node" and use that for your parse method.
I tested with this code and it worked for me.
var parentnode = node.ParentNode.ParentNode.ParentNode.FirstChild.NextSibling;
var nameNode = parentnode.FirstChild;
Links l = new Links();
l.Name = ParseHtmlContainingText(nameNode.InnerText);
l.Link = node.GetAttributeValue("href", "");
I need to create a method that find the newest version of application on a website (Hudson server) and allow to download it.
till now I use regex to scan all the HTML and find the href tags and search for the string I wish to.
I want to know if there is a simplest way to do so.
I attached the code I use today:
namespace SDKGui
{
public struct LinkItem
{
public string Href;
public string Text;
public override string ToString()
{
return Href;
}
}
static class LinkFinder
{
public static string Find(string file)
{
string t=null;
List<LinkItem> list = new List<LinkItem>();
// 1.
// Find all matches in file.
MatchCollection m1 = Regex.Matches(file, #"(<a.*?>.*?</a>)",
RegexOptions.Singleline);
// 2.
// Loop over each match.
foreach (Match m in m1)
{
string value = m.Groups[1].Value;
LinkItem i = new LinkItem();
// 3.
// Get href attribute.
Match m2 = Regex.Match(value, #"href=\""(.*?)\""",
RegexOptions.Singleline);
if (m2.Success)
{
i.Href = m2.Groups[1].Value;
}
// 4.
// Remove inner tags from text.
t = Regex.Replace(value, #"\s*<.*?>\s*", "",
RegexOptions.Singleline);
if (t.Contains("hms_sdk_tool_"))
{
i.Text = t;
list.Add(i);
break;
}
}
return t;
}
}
}
It is easy to collect all href values and filter against any of your conditions using HtmlAgilityPack. The following method shows how to access a page, get all <a> tags, and return a list of all href values containing hms_sdk_tool_:
private List<string> HtmlAgilityCollectHrefs(string url)
{
var webGet = new HtmlAgilityPack.HtmlWeb();
var doc = webGet.Load(url);
var a_nodes = doc.DocumentNode.SelectNodes("//a");
return a_nodes.Select(p => p.GetAttributeValue("href", "")).Where(n => n.Contains("hms_sdk_tool_")).ToList();
}
Or, if you are interested in 1 return string, use
private string GetLink(string url)
{
var webGet = new HtmlAgilityPack.HtmlWeb();
var doc = webGet.Load(url);
var a_nodes = doc.DocumentNode.SelectNodes("//a");
return a_nodes.Select(p => p.GetAttributeValue("href", "")).Where(n => n.Contains("hms_sdk_tool_")).FirstOrDefault();
}