diff --git a/.gitignore b/.gitignore index 8e88e25..c0dc326 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,5 @@ -target/* +target *.iml out/ .idea + diff --git a/webmagic-selenium/src/main/java/us/codecraft/webmagic/downloader/selenium/SeleniumDownloader.java b/webmagic-selenium/src/main/java/us/codecraft/webmagic/downloader/selenium/SeleniumDownloader.java index 3d4fcdb..50d332b 100644 --- a/webmagic-selenium/src/main/java/us/codecraft/webmagic/downloader/selenium/SeleniumDownloader.java +++ b/webmagic-selenium/src/main/java/us/codecraft/webmagic/downloader/selenium/SeleniumDownloader.java @@ -84,6 +84,7 @@ public class SeleniumDownloader implements Downloader, Closeable { WebElement webElement = webDriver.findElement(By.xpath("/html")); String content = webElement.getAttribute("outerHTML"); Page page = new Page(); + page.setRawText(content); page.setHtml(new Html(UrlUtils.fixAllRelativeHrefs(content, request.getUrl()))); page.setUrl(new PlainText(request.getUrl())); page.setRequest(request);