Created
August 25, 2015 23:34
-
-
Save ruippeixotog/875bd2bce5fc8ff6e79a to your computer and use it in GitHub Desktop.
scala-scraper: modify the contents of an element
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
scala> import net.ruippeixotog.scalascraper.browser.Browser | |
import net.ruippeixotog.scalascraper.browser.Browser | |
scala> import net.ruippeixotog.scalascraper.dsl.DSL._ | |
import net.ruippeixotog.scalascraper.dsl.DSL._ | |
scala> import net.ruippeixotog.scalascraper.dsl.DSL.Extract._ | |
import net.ruippeixotog.scalascraper.dsl.DSL.Extract._ | |
scala> val browser = new Browser | |
browser: net.ruippeixotog.scalascraper.browser.Browser = net.ruippeixotog.scalascraper.browser.Browser@1838de6b | |
scala> val doc = browser.parseString(""" | |
| <html> | |
| <body> | |
| <p>aaa</p> | |
| <p id="xyz">bbb</p> | |
| </body> | |
| </html>""") | |
doc: org.jsoup.nodes.Document = | |
<html> | |
<head></head> | |
<body> | |
<p>aaa</p> | |
<p id="xyz">bbb</p> | |
</body> | |
</html> | |
scala> val elem = doc >> element("#xyz") | |
elem: org.jsoup.nodes.Element = <p id="xyz">bbb</p> | |
scala> elem.html("ccc") | |
res0: org.jsoup.nodes.Element = <p id="xyz">ccc</p> | |
scala> doc.html | |
res2: String = | |
<html> | |
<head></head> | |
<body> | |
<p>aaa</p> | |
<p id="xyz">ccc</p> | |
</body> | |
</html> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment