Last active
March 14, 2020 07:23
-
-
Save rsato/820018dc8965254900fd to your computer and use it in GitHub Desktop.
Groovy + Geb + Selenium による、電子書籍試し読みサイト tameshiyo.me の画像を保存するスクリプトです。解説はこちら:https://reisato.plala.jp/rsato/weblog/2016/03/15/1830.html
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
@Grab('org.gebish:geb-core') | |
@Grab('org.seleniumhq.selenium:selenium-firefox-driver') | |
@GrabExclude('org.codehaus.groovy:groovy-all') | |
import geb.Browser | |
Browser.drive { | |
go args[0] // URL | |
sleep(2000) | |
// get number of pages | |
def pages = Integer.parseInt($('div#page_indicator')?.text().split(' ')[2]) | |
// get encoded iamges in data URI | |
def list = [] | |
(0..(pages-1)).each { page -> | |
list << $('div.page_pnl', 'data-page-prefix': "${page % 2 * 2}")?.children()[0].@src | |
list << $('div.page_pnl', 'data-page-prefix': "${page % 2 * 2 + 1}")?.children()[0].@src | |
$('img#tb_right').click() | |
sleep(1000) | |
} | |
// decode data & save iamges | |
list.eachWithIndex { url, index -> | |
if(url.startsWith('data:') && url.split(',').size() == 2) { | |
def encodedImage = url.split(',')[1] | |
new File("page-${index}.jpg").bytes = Base64.getDecoder().decode(encodedImage) | |
} | |
} | |
}.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment