Last active
May 4, 2022 10:10
-
-
Save sagrawal31/55451ee85130f2dcda8e to your computer and use it in GitHub Desktop.
A simple Groovy script to scrape all URLs from a given string and download the content from those URLs
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
import java.util.regex.Matcher | |
import java.util.regex.Pattern | |
Pattern urlPattern = Pattern.compile("\\b(https?|ftp|file)://[-a-zA-Z0-9+&@#/%?=~_|!:,.;]*[-a-zA-Z0-9+&@#/%=~_|]",Pattern.CASE_INSENSITIVE); | |
String urlString = """This is a big string with lots of Image URL like: http://i.istockimg.com/file_thumbview_approve/69656987/3/stock-illustration-69656987-vector-of-flat-icon-life-buoy.jpg and | |
http://i.istockimg.com/file_thumbview_approve/69943823/3/stock-illustration-69943823-beach-ball.jpg few others below | |
http://i.istockimg.com/file_thumbview_approve/40877104/3/stock-photo-40877104-pollen-floating-on-water.jpg | |
http://i.istockimg.com/file_thumbview_approve/68944343/3/stock-illustration-68944343-ship-boat-flat-icon-with-long-shadow.jpg | |
""" | |
Matcher matcher = urlPattern.matcher(urlString); | |
while (matcher.find()) { | |
String address = matcher.group() | |
println("Got URL: " + address); | |
new File("./" + address.tokenize("/").last()).withOutputStream { out -> | |
out << new URL(address).openStream() | |
} | |
} | |
// References: | |
// 1. http://stackoverflow.com/questions/5713558/detect-and-extract-url-from-a-string | |
// 2. http://stackoverflow.com/questions/4674995/groovy-download-image-from-url |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment