public void OfficeSupportExtractionTest()
{
var configPath = Path.Combine("TestData", "support.office.com.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "support.office.com.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual("Export data to Excel", parsedJson["title"].Value, "The extracted title is incorrect");
Assert.AreEqual("You can copy data from a Microsoft Office Access 2007 database into a worksheet by exporting a database object to a Microsoft Office Excel 2007 workbook. You do this by using the Export Wizard in Office Access 2007.", parsedJson["abstract"].Value, "The extracted abstract is incorrect");
Assert.AreEqual(9, parsedJson["versions"].Count, "The extracted versions field is incorrect");
Assert.AreEqual(5, parsedJson["sections"].Count, "The extracted json should have 5 sections");
var secondSection = parsedJson["sections"][1];
Assert.AreEqual("Exporting data to Excel: the basics", secondSection["title"].Value, "The title of the second section is incorrect");
Assert.AreEqual(9, secondSection["text"]["paragraphs"].Count, "The paragraphs count of the second section is incorrect");
Assert.AreEqual(2, secondSection["text"]["unorderedLists"].Count, "The paragraphs count of the second section is incorrect");
var secondList = secondSection["text"]["unorderedLists"][1];
Assert.AreEqual("If this is the first time you are exporting data to Excel", secondList["title"].Value, "The title of the second list in the second section is incorrect");
Assert.AreEqual(4, secondList["items"].Count, "The second list in the second section should have 4 items");
}
public void RemoveExtraWhitespaceTransformationTest()
{
var html = "<html><body><div id='content'><a href=''>A link</a>with adjacent text. "the final frontier"</div></body></html>";
var configJson = @"
{
'text': {
'_xpath': '//div[@id=\'content\']',
'_transformations': [
'ExtractTextTransformation',
'HtmlDecodeTransformation',
'RemoveExtraWhitespaceTransformation'
]
}
}
";
var config = StructuredDataConfig.ParseJsonString(configJson);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(html);
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual("A link with adjacent text. \"the final frontier\"", parsedJson["text"].Value);
}
static void Main(string[] args)
{
var configJson = @"
{
'':'//a[contains(text(), \'File\')]/@href'
}
";
var config = StructuredDataConfig.ParseJsonString(configJson);
var html = @"http://rule34.paheal.net/post/list";
HtmlWeb web = new HtmlWeb();
WebClient wc = new WebClient();
var htmlDoc = web.Load(html);
var body = htmlDoc.Text;
var path = Directory.GetCurrentDirectory() + "\\img\\";
void CreataFolder()
{
if (!Directory.Exists(path))
{
Directory.CreateDirectory(path);
}
}
CreataFolder();
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(body);
char[] charstotrim = { '\x5C', '\x22', '\x7B', '\x20' };
var output = JsonConvert.SerializeObject(scrapingResults, Formatting.Indented).Split(',');
output[0] = output[0].Remove(0, 10);
output[output.Length - 1] = output[output.Length - 1].Remove(output[output.Length - 1].Length - 8, 8);
string fileName;
for (int i = 0; i < output.Length; i++)
{
output[i] = output[i].Remove(0, 7);
output[i] = output[i].Trim(charstotrim);
if (output[i].Contains("webm"))
{
fileName = path + i + ".webm";
Console.WriteLine(fileName);
}
else
{
fileName = path + i + "." + output[i].Remove(0, output[i].Length - 3);
Console.WriteLine(fileName);
}
wc.DownloadFile((string)output[i], fileName);
}
Console.WriteLine("----------------------------");
for (int i = 0; i < output.Length; i++)
{
Console.WriteLine(output[i]);
}
Console.ReadKey();
}
public static void WorkerSummary1(int poolid)
{
var driver = new ChromeDriver();
var jsonConfig = File.ReadAllText(@"Json\\f2pool.json");
var config = StructuredDataConfig.ParseJsonString(jsonConfig);
string url = GetUrl(poolid);
driver.Navigate().GoToUrl(url);
Thread.Sleep(8000);
var source = driver.PageSource;
try
{
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(source);
JObject jObject = JObject.Parse(scrapingResults.ToString());
JToken json = jObject["data"];
//var all = (int)json[0];
var active = (int)json[1];
var inactive = (int)json[2];
var dead = 0;
if (json.Count() == 4)
{
dead = (int)json[3];
}
JToken json2 = jObject["currenthash"];
JToken json3 = jObject["dailyhash"];
var temp1 = (string)json2;
var temp2 = (string)json3;
var currentcalculation = GetFloat(temp1);
var dailycalculation = GetFloat(temp2);
var unit = GetString(temp1);
UpdateSummary(currentcalculation, dailycalculation, unit, active, inactive, dead, poolid);
}
catch (Exception ex)
{
if (Commonflag.flag1 != true)
{
// do nothing
}
else
{
string error = "Poolid=" + poolid + " " + ex.ToString();
Commonflag.flag1 = false;
UpdateErrorLog("f2pool", error);
}
}
finally
{
driver.Close();
driver.Quit();
}
}
public void Scrape()
{
var config = StructuredDataConfig.ParseJsonString(Top100Config);
var html = DownloadPage(saveTo: IMDBhtml);
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(html);
using (WebClient client = new WebClient())
{
foreach (var celeb in scrapingResults["celebrities"])
{
celeb["birth"] = ScrapeCeleb(celeb);
var wat = celeb["image"].ToString();
Uri uri = new Uri(wat);
string fn = Path.GetFileName(uri.LocalPath);
client.DownloadFile(wat, imgPath + fn);
}
}
JsonSerializerSettings jss = new JsonSerializerSettings
{
StringEscapeHandling = StringEscapeHandling.Default
};
string textresult = JsonConvert.SerializeObject(scrapingResults, jss);
File.WriteAllText(DBfile, textresult);
}
public void QuoraWithWikiExtractionTest()
{
var configPath = Path.Combine("TestData", "quora.com.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "quora.com.withwiki.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
// Question
Assert.AreNotEqual(null, parsedJson["question"], "Extractor should find a question in the HTML file");
var question = parsedJson["question"];
Assert.AreEqual("What can I learn/know right now in 10 minutes that will be useful for the rest of my life?", question["title"].Value, "The extracted title is incorrect");
// Answers
Assert.AreNotEqual(null, parsedJson["answers"], "Extractor should find answers in the HTML file");
Assert.AreEqual(5, parsedJson["answers"].Count, "Extractor should find 5 answers in the thread summary of the HTML file");
// Best Answer
Assert.AreNotEqual(null, parsedJson["bestAnswer"], "Extractor should find the best answer in the HTML file");
var bestAnswer = parsedJson["bestAnswer"];
Assert.AreNotEqual(null, bestAnswer["content"], "The content string should not be null in the extracted answer");
Assert.IsTrue(bestAnswer["content"].Value.Length > 0, "The content string should not be empty in the extracted answer");
Assert.AreEqual(9, bestAnswer["lists"].Count, "The lists array should have 9 items");
Assert.AreEqual(25, bestAnswer["lists"][1]["items"].Count, "Second item in the lists array should have 25 items");
// Check is textAboveLength exists in each list
foreach (var answer in parsedJson["answers"])
{
var lists = answer["lists"];
if (lists != null)
{
foreach (var list in lists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
var bestAnswerLists = bestAnswer["lists"];
if (bestAnswerLists != null)
{
foreach (var list in bestAnswerLists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
internal static Newtonsoft.Json.Linq.JContainer ExtractFromHtml(this string html, string resourceName)
{
var config = ScrapingExtensions.CreateConfig(resourceName);
var scraper = new StructuredDataExtractor(config);
var result = scraper.Extract(html);
return(result);
}
public async Task Transform(string content)
{
var config = StructuredDataConfig.ParseJsonString(_jsonConfig);
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(content);
await _sender.Send(scrapingResults.ToString());
}
public IActionResult JsonResult([FromBody] ObjectJson json)
{
var url = WebUtility.UrlDecode(json.url);
MyWebClient client = new MyWebClient()
{
Encoding = Encoding.UTF8
};
client.Headers[HttpRequestHeader.UserAgent] = "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36";
if (json.isID)
{
client.DownloadData(url);
var mainUrl = client.ResponseUri.ToString();
var regex = JsonConvert.DeserializeObject <JsonIDInput>(json.data);
string item = "";
try
{
var regexMatch = Regex.Match(mainUrl, regex._xpath);
item = regexMatch.Groups[regex.group_number].Value;
}
catch (Exception) { }
return(Json(JsonConvert.SerializeObject(new JsonIDresult {
url = mainUrl, id = item
}, Formatting.Indented)));
}
else
{
var baseUri = new Uri(url);
var isScript = json.javascript;
var config = StructuredDataConfig.ParseJsonString(json.data);
var html = client.DownloadString(!isScript ? url : this.configuration.GetAppSetting("UrlSeleniumGetHtmlExcuteJavascript") + "?url=" + WebUtility.UrlEncode(url));
HtmlDocument docc = new HtmlDocument();
docc.LoadHtml(html);
var urltmp = "";
HtmlNodeCollection nodes = docc.DocumentNode.SelectNodes("//a");
if (nodes != null)
{
foreach (HtmlNode node in nodes)
{
if ((node.Attributes["href"] != null) && (node.Attributes["href"].Value != ""))
{
try
{
urltmp = node.Attributes["href"].Value.Trim();
node.Attributes["href"].Value = new Uri(baseUri, urltmp).AbsoluteUri;
}
catch (Exception) { }
}
}
}
;
html = docc.DocumentNode.InnerHtml;
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(html);
var result = JsonConvert.SerializeObject(scrapingResults, Formatting.Indented);
return(Json(result));
}
}
public static void WorkerSummary7(int poolid)
{
var driver = new ChromeDriver();
var jsonConfig = File.ReadAllText(@"Json\\spiderpool.json");
var config = StructuredDataConfig.ParseJsonString(jsonConfig);
string url = GetUrl(poolid);
//var url = "https://www.spiderpool.com/coin/show/btc/yibobtc01/detail.html";
driver.Navigate().GoToUrl(url);
Thread.Sleep(1000);
var source = driver.PageSource;
try
{
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(source);
JObject jObject = JObject.Parse(scrapingResults.ToString());
JToken json = jObject["data"];
var temp1 = (string)json[8];
var temp2 = (string)json[10];
var currentcalculation = GetFloat(temp1);
var dailycalculation = GetFloat(temp2);
var unit = GetString(temp1);
var temp = (string)json[6];
var active = Int32.Parse(temp.Substring(0, temp.IndexOf('/')));
var total = Int32.Parse(temp.Substring(temp.LastIndexOf('/') + 1));
int inactive = total - active;
int dead = 0;
UpdateSummary(currentcalculation, dailycalculation, unit, active, inactive, dead, poolid);
}
catch (Exception ex)
{
if (Commonflag.flag7 != true)
{
// do nothing
}
else
{
string error = "Poolid=" + poolid + " " + ex.ToString();
Commonflag.flag7 = false;
UpdateErrorLog("viabtc", error);
}
}
finally
{
driver.Close();
driver.Quit();
}
}
public static void WorkerSummary6(int poolid)
{
var driver = new ChromeDriver();
var jsonConfig = File.ReadAllText(@"Json\\viabtc.json");
var config = StructuredDataConfig.ParseJsonString(jsonConfig);
string url = GetUrl(poolid);
//var url = "https://pool.viabtc.com/observer/dashboard?access_key=cb735a866859b626a748c0fb4a479394";
driver.Navigate().GoToUrl(url);
//Thread.Sleep(1000);
var source = driver.PageSource;
try
{
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(source);
JObject jObject = JObject.Parse(scrapingResults.ToString());
JToken json = jObject["data"];
var temp1 = (string)json[0];
var temp2 = (string)json[2];
var currentcalculation = GetFloat(temp1);
var dailycalculation = GetFloat(temp2);
var unit = GetString(temp1);
var active = Int32.Parse((string)json[3]);
var inactive = Int32.Parse((string)json[4]);
int total = 0;
int dead = 0;
UpdateSummary(currentcalculation, dailycalculation, unit, active, inactive, dead, poolid);
}
catch (Exception ex)
{
if (Commonflag.flag6 != true)
{
// do nothing
}
else
{
string error = "Poolid=" + poolid + " " + ex.ToString();
Commonflag.flag6 = false;
UpdateErrorLog("viabtc", error);
}
}
finally
{
driver.Close();
driver.Quit();
}
}
public async Task Transform(string content)
{
//transform intoJson, create object template in shared becouse we need the same object in Loader to deserialize
var configJson = GenerateJson();
var config = StructuredDataConfig.ParseJsonString(configJson);
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(content);
await _sender.Send(scrapingResults.ToString());
}
public static void WorkerSummary5(int poolid)
{
var driver = new ChromeDriver();
var jsonConfig = File.ReadAllText(@"Json\\antpool.json");
var config = StructuredDataConfig.ParseJsonString(jsonConfig);
string url = GetUrl(poolid);
driver.Navigate().GoToUrl(url);
Thread.Sleep(1000);
var source = driver.PageSource;
try
{
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(source);
JObject jObject = JObject.Parse(scrapingResults.ToString());
JToken json = jObject["data"];
var temp = (string)json[0];
var temp1 = (string)json[1];
var temp2 = (string)json[3];
var currentcalculation = GetFloat(temp1);
var dailycalculation = GetFloat(temp2);
var unit = GetString(temp1);
var numbers = Regex.Split(temp.Trim(), @"\D+");
var active = Int32.Parse(numbers[0]);
var total = Int32.Parse(numbers[1]);
var inactive = total - active;
int dead = 0;
UpdateSummary(currentcalculation, dailycalculation, unit, active, inactive, dead, poolid);
}
catch (Exception ex)
{
if (Commonflag.flag5 != true)
{
// do nothing
}
else
{
string error = "Poolid=" + poolid + " " + ex.ToString();
Commonflag.flag5 = false;
UpdateErrorLog("antpool", error);
}
}
finally
{
driver.Close();
driver.Quit();
}
}
public void MicrosoftAnswersExtractionTest()
{
var configPath = Path.Combine("TestData", "answers.microsoft.com.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "answers.microsoft.com.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
// Question
Assert.AreNotEqual(null, parsedJson["question"], "Extractor should find a question in the HTML file");
var question = parsedJson["question"];
Assert.AreEqual("8acb1ac5-0acd-4c68-9eeb-e4afff5b39d8", question["id"].Value, "The extracted id is incorrect");
Assert.AreEqual("I want to reserve my free copy of Windows 10, but I don’t see the icon on the taskbar", question["title"].Value, "The extracted title is incorrect");
Assert.AreNotEqual(null, question["content"], "The extracted question should have a content");
Assert.IsTrue(question["content"].Value.Length > 0, "The extracted question content should have a length > 0");
Assert.AreEqual(1642653, question["views"].Value, "The extracted views snippet is incorrect");
// Question context
Assert.AreNotEqual(null, question["hints"], "The extracted question should have hints");
Assert.AreEqual(4, question["hints"].Count, "The extracted question should have 4 hints");
Assert.AreEqual("PC", question["hints"][3].ToString(), "The 4th hint of the extracted question should be PC");
// Answers
Assert.AreNotEqual(null, parsedJson["answers"], "Extractor should find answers in the HTML file");
Assert.AreEqual(2, parsedJson["answers"].Count, "Extractor should find two answers in the thread summary of the HTML file");
var secondAnswer = parsedJson["answers"][1];
Assert.AreEqual("Most Helpful Reply", secondAnswer["type"].Value, "The extracted type of the answer is incorrect");
Assert.AreNotEqual(null, secondAnswer["content"], "The content array in the extracted answer should not be null");
Assert.IsTrue(secondAnswer["content"].Count > 0, "The content array in the extracted answer should have one or more items");
Assert.AreEqual(4, secondAnswer["lists"].Count, "The lists array should have 4 items");
Assert.IsTrue(secondAnswer["lists"][0]["items"].Count > 0, "First item in the lists array should have at least one item");
// Check is textAboveLength exists in each list
foreach (var answer in parsedJson["answers"])
{
var lists = answer["lists"];
if (lists != null)
{
foreach (var list in lists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
}
private JToken ScrapeCeleb(JToken jToken)
{
var config = StructuredDataConfig.ParseJsonString(CelebConfig);
jToken["page"] = "https://www.imdb.com" + jToken["page"];
var html = DownloadPage(jToken["page"].ToString());
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(html);
return(scrapingResults["celebrities"]["birth"]);
}
public void QuoraExtractionTest()
{
var configPath = Path.Combine("TestData", "quora.com.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "quora.com.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
// Question
Assert.AreNotEqual(null, parsedJson["question"], "Extractor should find a question in the HTML file");
var question = parsedJson["question"];
Assert.AreEqual("What are some tips for creating a successful Kickstarter project?", question["title"].Value, "The extracted title is incorrect");
// Question context
Assert.AreNotEqual(null, question["hints"], "The extracted question should have hints");
Assert.AreEqual(5, question["hints"].Count, "The extracted question should have 5 hints");
Assert.AreEqual("Kickstarter", question["hints"][3].ToString(), "The 4th hint of the extracted question should be Kickstarter");
// Answers
Assert.AreNotEqual(null, parsedJson["answers"], "Extractor should find answers in the HTML file");
Assert.AreEqual(5, parsedJson["answers"].Count, "Extractor should find 5 answers in the thread summary of the HTML file");
var firstAnswer = parsedJson["answers"][0];
Assert.AreNotEqual(null, firstAnswer["content"], "The content string should not be null in the extracted answer");
Assert.IsTrue(firstAnswer["content"].Value.Length > 0, "The content string should not be empty in the extracted answer");
Assert.AreEqual(6800, firstAnswer["views"].Value, "The extracted views count is incorrect");
Assert.AreEqual(1, firstAnswer["lists"].Count, "The lists array should have 1 item");
Assert.IsTrue(firstAnswer["lists"][0]["items"].Count > 0, "First item in the lists array should have at least one item");
var secondAnswer = parsedJson["answers"][1];
Assert.AreEqual(2, secondAnswer["views"].Value, "The extracted views count is incorrect");
// Check is textAboveLength exists in each list
foreach (var answer in parsedJson["answers"])
{
var lists = answer["lists"];
if (lists != null)
{
foreach (var list in lists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
}
public void StackExchangeEx2ExtractionTest()
{
var configPath = Path.Combine("TestData", "stackexchange.com.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "stackoverflow.com.example2.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
// Question
Assert.AreNotEqual(null, parsedJson["question"], "Extractor should find a question in the HTML file");
var question = parsedJson["question"];
Assert.AreEqual("How to configure Visual Studio 2008 to use IIS Express?", question["title"].Value, "The extracted title is incorrect");
Assert.AreNotEqual(null, question["content"], "The extracted question should have a content");
Assert.AreEqual(JTokenType.String, question["content"].Type, "The extracted question content should be a string");
Assert.IsTrue(question["content"].Value.Length > 0, "The extracted question content should have a length > 0");
Assert.AreNotEqual(null, question["votes"], "The extracted question should have a votes field");
Assert.AreEqual(JTokenType.Integer, question["votes"].Type, "The votes extracted from the question should be of type int");
Assert.AreEqual(9, question["votes"].Value, "The votes extracted from the question should have a value of 9");
// Question context
Assert.AreNotEqual(null, question["hints"], "The extracted question should have hints");
Assert.AreEqual(2, question["hints"].Count, "The extracted question should have 2 hints");
Assert.AreEqual("iis-express", question["hints"][1].ToString(), "The 2nd hint of the extracted question should be passwords");
// Best Answer
var bestAnswer = parsedJson["bestAnswer"];
Assert.AreNotEqual(null, bestAnswer["content"], "The extracted answer should have a content");
Assert.AreEqual(JTokenType.String, bestAnswer["content"].Type, "The extracted answer content should be a string");
Assert.IsTrue(bestAnswer["content"].Value.Length > 0, "The extracted answer content should have a length > 0");
Assert.AreNotEqual(null, bestAnswer["votes"], "The extracted answer should have a votes field");
Assert.AreEqual(JTokenType.Integer, bestAnswer["votes"].Type, "The votes extracted from the answer should be of type int");
Assert.AreEqual(17, bestAnswer["votes"].Value, "The votes extracted from the answer should have a value of 17");
Assert.AreEqual(1, bestAnswer["lists"].Count, "The lists array should have 1 item");
Assert.AreEqual(7, bestAnswer["lists"][0]["items"].Count, "The first item in the lists array should have 7 items");
// Check is textAboveLength exists in each list
var lists = bestAnswer["lists"];
if (lists != null)
{
foreach (var list in lists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
public void StackExchangeEx1ExtractionTest()
{
var configPath = "stackexchange.com.json";
var config = StructuredDataConfig.Parse(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText("stackoverflow.com.example1.html"));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
// Question
Assert.AreNotEqual(null, parsedJson["question"], "Extractor should find a question in the HTML file");
var question = parsedJson["question"];
Assert.AreEqual("Is there a way to crack the password on an Excel VBA Project?", question["title"].Value, "The extracted title is incorrect");
Assert.AreNotEqual(null, question["content"], "The extracted question should have a content");
Assert.AreEqual(JTokenType.String, question["content"].Type, "The extracted question content should be a string");
Assert.IsTrue(question["content"].Value.Length > 0, "The extracted question content should have a length > 0");
Assert.AreNotEqual(null, question["votes"], "The extracted question should have a votes field");
Assert.AreEqual(JTokenType.Integer, question["votes"].Type, "The votes extracted from the question should be of type int");
Assert.AreEqual(196, question["votes"].Value, "The votes extracted from the question should have a value of 196");
// Question context
Assert.AreNotEqual(null, question["hints"], "The extracted question should have hints");
Assert.AreEqual(4, question["hints"].Count, "The extracted question should have 4 hints");
Assert.AreEqual("passwords", question["hints"][3].ToString(), "The 4th hint of the extracted question should be passwords");
// Best Answer
var bestAnswer = parsedJson["bestAnswer"];
Assert.AreNotEqual(null, bestAnswer["content"], "The extracted answer should have a content");
Assert.AreEqual(JTokenType.String, bestAnswer["content"].Type, "The extracted answer content should be a string");
Assert.IsTrue(bestAnswer["content"].Value.Length > 0, "The extracted answer content should have a length > 0");
Assert.AreNotEqual(null, bestAnswer["votes"], "The extracted answer should have a votes field");
Assert.AreEqual(JTokenType.Integer, bestAnswer["votes"].Type, "The votes extracted from the answer should be of type int");
Assert.AreEqual(153, bestAnswer["votes"].Value, "The votes extracted from the answer should have a value of 153");
Assert.AreEqual(1, bestAnswer["lists"].Count, "The lists array should have 1 item");
Assert.AreEqual(8, bestAnswer["lists"][0]["items"].Count, "The first item in the lists array should have 4 items");
// Check is textAboveLength exists in each list
var lists = bestAnswer["lists"];
if (lists != null)
{
foreach (var list in lists)
{
Assert.AreEqual(JTokenType.Integer, list["textAboveLength"].Type, "The extracted textAboveLength should be an integer");
var textAboveLength = ((JValue)list["textAboveLength"]).ToObject <int>();
Assert.IsTrue(textAboveLength > 0, string.Format(CultureInfo.InvariantCulture, "textAboveLength was not greater than 0. The extracted value is: {0}", textAboveLength));
}
}
}
public void ParseDateTest()
{
var configPath = Path.Combine("TestData", "parse_date_rules.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "article_with_date.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual(DateTime.Parse("2018-11-24T00:00:00"), parsedJson["parsedDateNoFormat"].Value);
Assert.AreEqual(DateTime.Parse("2011-12-30T00:00:00"), parsedJson["parsedDateWithFormat"].Value);
Assert.AreEqual(DateTime.Parse("2008-06-12T00:00:00"), parsedJson["parsedDateNoFormatWithProviderStyle"].Value);
}
public void RemoveXPathsExtractionTest()
{
var configPath = Path.Combine("TestData", "article_with_comments_div.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "article_with_comments_div.html")));
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual("Article title", parsedJson["title"].Value, "The extracted title is incorrect");
Assert.AreEqual("Para1 content Para2 content", parsedJson["body"].Value, "The extracted body is incorrect");
}
public void RegexTest()
{
var configPath = Path.Combine("TestData", "regex_rules.json");
var config = StructuredDataConfig.ParseJsonFile(configPath);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(File.ReadAllText(Path.Combine("TestData", "article_with_date.html")));
var actualJson = JsonConvert.SerializeObject(result, Formatting.Indented);
var parsedActualJson = JObject.Parse(actualJson);
var expectedJsonPath = Path.Combine("TestData", "regex_expected_result.json");
var expectedJson = File.ReadAllText(expectedJsonPath);
var parsedExpectedJson = JObject.Parse(expectedJson);
Assert.IsTrue(JToken.DeepEquals(parsedActualJson, parsedExpectedJson));
}
private async Task Init()
{
// Path to the folder with classifiers models
var jarRoot = @"C:\stanford-ner-2018-10-16";
var classifiersDirecrory = jarRoot + @"\classifiers";
// Loading 3 class classifier model
_classifier = CRFClassifier.getClassifierNoExceptions(
classifiersDirecrory + @"\english.all.3class.distsim.crf.ser.gz");
// Define a regular expression for finding the location element
_locationRx = new Regex(@"<LOCATION\b[^>]*>(.*?)</LOCATION>",
RegexOptions.Compiled | RegexOptions.IgnoreCase);
// Define configurations for parsing artist and listener info
var configArtistInfoJson = @"
{
'artist': '//h1[contains(@class, \'view-header\')]',
'about': '//div[contains(@class, \'bio-primary\')]',
'more': '//div[contains(@class, \'bio-secondary\')]',
'listeners-city': '//span[contains(@class, \'horizontal-list__item__title\')]',
'listeners': '//span[contains(@class, \'horizontal-list__item__subtitle\')]'
}";
ConfigSection configArtist = StructuredDataConfig.ParseJsonString(configArtistInfoJson);
_artistScraping = new StructuredDataExtractor(configArtist);
// Get the hosted feature layers for editing
ArcGISPortal portal = await ArcGISPortal.CreateAsync();
PortalItem hometownLayerItem = await PortalItem.CreateAsync(portal, _hometownLayerId);
PortalItem otherPointsLayerItem = await PortalItem.CreateAsync(portal, _otherPointsLayerId);
PortalItem listenerLayerItem = await PortalItem.CreateAsync(portal, _listenerLayerId);
_hometownTable = new ServiceFeatureTable(hometownLayerItem, 0);
_otherPointsTable = new ServiceFeatureTable(otherPointsLayerItem, 0);
_listenerTable = new ServiceFeatureTable(listenerLayerItem, 0);
await _hometownTable.LoadAsync();
await _otherPointsTable.LoadAsync();
await _listenerTable.LoadAsync();
}
public T Run()
{
using (var client = new WebClient())
{
var html = client.DownloadString(UrlConstants.BaseUrl + _relativeUrl);
var configuration = StructuredDataConfig.ParseJsonString(ConfigurationJson);
var openScraping = new StructuredDataExtractor(configuration);
var scrapingResults = openScraping.Extract(html);
var serializedObject = JsonConvert.SerializeObject(scrapingResults, Formatting.Indented);
var deserializedObject = JsonConvert.DeserializeObject <T>(serializedObject);
WaitRandom();
return(deserializedObject);
}
}
static void Main(string[] args)
{
var jsonConfig = File.ReadAllText(@"match-result.config.json");
var config = StructuredDataConfig.ParseJsonString(jsonConfig);
var html = string.Empty;
using (WebClient client = new WebClient())
{
client.Encoding = Encoding.UTF8;
html = client.DownloadString("http://virtualsoccer.ru/viewmatch.php?day=12968&match_id=213340");
}
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(html);
Console.WriteLine(JsonConvert.SerializeObject(scrapingResults, Formatting.Indented));
Console.ReadKey();
}
private async Task ProcessAsync()
{
await this.Page.WaitForTimeoutAsync(this.DefaultTimeout);
string HTML = await this.Page.GetContentAsync();
try
{
var openScraping = new StructuredDataExtractor(this.config);
var scrapingResults = openScraping.Extract(html: HTML);
var records = scrapingResults.ToObject <Model.RootObject>();
if (records.PropertyRecords.Count > 0)
{
var first = records.PropertyRecords.First().Owner;
var last = records.PropertyRecords.Last().Owner;
if (string.IsNullOrEmpty(first) && string.IsNullOrEmpty(last))
{
// suspicious
HTML = null;
}
else
{
return;
}
}
else
{
HTML = null;
}
}
catch (Exception ex)
{
HTML = null;
throw ex;
}
if (HTML.Equals(null))
{
throw new Exception("NavigateCollect: No record data was returned");
}
}
public static MyRecipe ExtractRecipe(string url)
{
string urlResponse;
MyRecipe myRecipe = null;
// 1. Get Response from url
using (WebClient w = new WebClient())
{
urlResponse = w.DownloadString(url);
}
//2: Check and scrape if any structured JSON is present (application/ld+json)
var configJson = @"{
'data': '//script[contains(@type, \'application\/ld+json\')]'
}";
var config = StructuredDataConfig.ParseJsonString(configJson);
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(urlResponse);
if (scrapingResults != null && scrapingResults["data"] != null)
{
var content = scrapingResults["data"].ToString();
if (content.Contains("\"@type\":\"Recipe\""))
{
try
{
var serializerSettings = new JsonSerializerSettings()
{
DateParseHandling = DateParseHandling.DateTimeOffset
};
Recipe rec = JsonConvert.DeserializeObject <Recipe>(content, serializerSettings);
RecipeBuilder builder = new RecipeBuilder();
myRecipe = builder.Build(rec);
}
catch (Exception e)
{
}
}
}
return(myRecipe);
}
public void CastToIntegerTest()
{
var html = "<meta property=\"width\" content=\"1200\">";
var configJson = @"
{
'width': {
'_xpath': '/meta[@property=\'width\']/@content',
'_transformation': 'CastToIntegerTransformation'
}
}
";
var config = StructuredDataConfig.ParseJsonString(configJson);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(html);
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual(1200, parsedJson["width"].Value);
}
public void UrlEncodeTest()
{
var html = "<html><body><div id='content'><a href='hello world'></a></div></body></html>";
var configJson = @"
{
'text': {
'_xpath': '//div[@id=\'content\']/a/@href',
'_transformation': 'UrlEncodeTransformation'
}
}
";
var config = StructuredDataConfig.ParseJsonString(configJson);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(html);
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual("hello+world", parsedJson["text"].Value);
}
public void ExtractTextTest()
{
var html = "<html><body><div id='content'><a href=''>A link</a>with adjacent text.</div></body></html>";
var configJson = @"
{
'text': {
'_xpath': '//div[@id=\'content\']',
'_transformation': 'ExtractTextTransformation'
}
}
";
var config = StructuredDataConfig.ParseJsonString(configJson);
var extractor = new StructuredDataExtractor(config);
var result = extractor.Extract(html);
var json = JsonConvert.SerializeObject(result, Formatting.Indented);
dynamic parsedJson = JsonConvert.DeserializeObject(json);
Assert.AreEqual("A link with adjacent text.", parsedJson["text"].Value);
}
internal static StockPrice FilerTheStockpriceFromRediff(string httpResposeMessage)
{
TimeZoneInfo INDIAN_ZONE = TimeZoneInfo.FindSystemTimeZoneById("India Standard Time");
DateTime tm = TimeZoneInfo.ConvertTimeFromUtc(DateTime.UtcNow, INDIAN_ZONE);
DateTime dt = DateTime.Today;
StockPrice sp = new StockPrice();
var configJson = @"
{
'price':'//span[2]',
'LastTradedDate':'//span[6]',
'LastTradedTime':'//span[7]'
}";
// var configJson = @"
// {
// 'title1': '//h1',
// 'title': '//script',
// 'price':'//span[2]',
// 'LastTradedDate':'//span[6]',
// 'LastTradedTime':'//span[7]',
//'body': '//div[contains(@class, \'article\')]'
// }
// ";
// var html = "<html><body><h1>Article title</h1><div class='article'>Article contents</div></body></html>";
// html = httpResposeMessage;
try
{
var config = StructuredDataConfig.ParseJsonString(configJson);
var openScraping = new StructuredDataExtractor(config);
var scrapingResults = openScraping.Extract(httpResposeMessage);
System.Diagnostics.Debug.WriteLine(JsonConvert.SerializeObject(scrapingResults, Formatting.Indented));
var thePrice = scrapingResults["price"];
var theDate = scrapingResults["LastTradedDate"];
var theTime = scrapingResults["LastTradedTime"];
sp.Price = double.Parse(thePrice.ToString().Trim());
//DateTime dt = DateTime.ParseExact(theDate.ToString().Trim(), "dd MMM", CultureInfo.InvariantCulture);
//DateTime tm = DateTime.ParseExact(theTime.ToString().Trim(), "HH:mm:ss", CultureInfo.InvariantCulture);
//** precaution in case missing date & time**//
if (!string.IsNullOrEmpty(theDate.ToString()))
{
if (theDate.ToString().IsDateType())
{
// dt = (DateTime)Convert.ChangeType(theDate, typeof(DateTime));
dt = DateTime.ParseExact(theDate.ToString().Trim(), "dd MMM", CultureInfo.InvariantCulture);
}
if (theTime.ToString().IsDateType())
{
tm = (DateTime)Convert.ChangeType(theTime, typeof(DateTime));
}
}
else
{
var DataNTime = theTime.ToString().Split(',', StringSplitOptions.RemoveEmptyEntries);
if (DataNTime.Length == 2) //has date and time
{
if (DataNTime[0].IsDateType())
{
//dt = (DateTime)Convert.ChangeType(DataNTime[0], typeof(DateTime));
dt = DateTime.ParseExact(DataNTime[0], "dd MMM", CultureInfo.InvariantCulture);
}
if (DataNTime[1].ToString().IsDateType())
{
tm = (DateTime)Convert.ChangeType(DataNTime[1], typeof(DateTime));
}
}
else //has time only
{
if (DataNTime[0].ToString().IsDateType())
{
tm = (DateTime)Convert.ChangeType(DataNTime[0], typeof(DateTime));
}
}
}
//** adjust the date if date in missing in the downloaded time stamp**//
var currectedDate = dt.Date.Add(tm.TimeOfDay);
currectedDate = currectedDate > TimeZoneInfo.ConvertTimeFromUtc(DateTime.UtcNow, INDIAN_ZONE) ?
currectedDate.AddYears(-1) : currectedDate;
sp.ValueOn = currectedDate;
}
catch (Exception ex)
{
throw ex;
}
return(sp);
}
