Last active
December 3, 2021 12:46
-
-
Save mahozad/a55245b84ae86294f5481ae7b9df6839 to your computer and use it in GitHub Desktop.
A Kotlin script to scrape a phrase from a dynamic page using Selenium and jsoup (mentioned in a Stack Overflow post)
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
#!/usr/bin/env kotlin | |
/** | |
* A Kotlin script for extracting (scraping) a phrase from a dynamic page. | |
* NOTE: Download and place the executable [Chrome driver](https://chromedriver.storage.googleapis.com/index.html) beside this script. | |
* See [this stackoverflow post](https://stackoverflow.com/a/69974518/8583692) for more information. | |
* Alternatively, use the [WebDriverManager](https://github.com/bonigarcia/webdrivermanager) library. | |
*/ | |
@file:JvmName("Scraper") | |
@file:CompilerOptions("-jvm-target", "11") | |
@file:Repository("https://repo.maven.apache.org/maven2") | |
@file:Repository("https://jcenter.bintray.com") | |
@file:Repository("https://jitpack.io") | |
@file:DependsOn("org.jsoup:jsoup:1.14.3") | |
@file:DependsOn("org.seleniumhq.selenium:selenium-java:4.0.0") | |
import org.jsoup.Jsoup | |
import org.openqa.selenium.chrome.ChromeDriver | |
import java.io.File | |
System.setProperty("webdriver.chrome.driver", "chromedriver.exe") | |
val result = File("output.html") | |
val driver = ChromeDriver() // OR FirefoxDriver(); download its driver and set the system property above | |
driver.get("https://www.singaporepools.com.sg/en/product/sr/Pages/toto_results.aspx") | |
result.writeText(driver.pageSource) | |
driver.close() | |
// Could also have used Jsoup.parse(driver.pageSource) | |
// instead of writing to and then reading from a file | |
val document = Jsoup.parse(result, "UTF-8") | |
val targetElement = document | |
.body() | |
.children() | |
.select(":containsOwn(Next Jackpot)") | |
.single() | |
.parent()!! | |
val phrase = targetElement.text() | |
val prize = targetElement.select("span").text().removeSuffix(" est") | |
println(phrase) // Next Jackpot $8,000,000 est | |
println(prize) // $8,000,000 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment