Created
August 30, 2017 11:02
-
-
Save pldmgg/c118cdbf9226a94faad11fd1583ba6cb to your computer and use it in GitHub Desktop.
OpenScrapingTest_For_scriptcs_cli.csx
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#r "C:\Windows\Microsoft.NET\Framework64\v4.0.30319\mscorlib.dll" | |
#r "System" | |
#r "System.Core" | |
#r ".\scriptcs_packages\System.Runtime.4.3.0\lib\net462\System.Runtime.dll" | |
#r ".\scriptcs_packages\System.Runtime.Extensions.4.3.0\lib\net462\System.Runtime.Extensions.dll" | |
#r "System.Collections" | |
#r ".\scriptcs_packages\Newtonsoft.Json.10.0.3\lib\netstandard1.3\Newtonsoft.Json.dll" | |
#r ".\scriptcs_packages\OpenScraping.1.0.1\lib\netcoreapp2.0\OpenScraping.dll" | |
#r ".\scriptcs_packages\HtmlAgilityPack.1.5.1\lib\netstandard1.6\HtmlAgilityPack.dll" | |
using System; | |
using Newtonsoft.Json; | |
using OpenScraping; | |
using OpenScraping.Config; | |
var configJson = @" | |
{ | |
'title': '//h1', | |
'body': '//div[contains(@class, \'article\')]' | |
} | |
"; | |
var config = StructuredDataConfig.ParseJsonString(configJson); | |
var html = "<html><body><h1>Article title</h1><div class='article'>Article contents</div></body></html>"; | |
var openScraping = new StructuredDataExtractor(config); | |
var scrapingResults = openScraping.Extract(html); | |
Console.WriteLine(scrapingResults["title"]); | |
Console.WriteLine("----------------------------"); | |
Console.WriteLine(JsonConvert.SerializeObject(scrapingResults, Formatting.Indented)); | |
Console.ReadKey(); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment