Gurkengewuerz/ImgScroll
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Improved instagram regex and added sanitizeURL

Browse Source
This commit is contained in:
cyian-1756 2017-11-18 03:52:17 -05:00
parent 67db5f3d99
commit 5c185c05df
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/main/java/com/rarchives/ripme/ripper/rippers/InstagramRipper.java
View File

@ -43,6 +43,13 @@ public class InstagramRipper extends AbstractHTMLRipper {
return (url.getHost().endsWith("instagram.com")); return (url.getHost().endsWith("instagram.com"));
} }
@Override
public URL sanitizeURL(URL url) throws MalformedURLException {
URL san_url = new URL(url.toExternalForm().replaceAll("\\?hl=\\S*", ""));
logger.info("sanitized URL is " + san_url.toExternalForm());
return san_url;
}
@Override @Override
public String getGID(URL url) throws MalformedURLException { public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("^https?://instagram.com/([^/]+)/?"); Pattern p = Pattern.compile("^https?://instagram.com/([^/]+)/?");
@ -51,7 +58,7 @@ public class InstagramRipper extends AbstractHTMLRipper {
return m.group(1); return m.group(1);
} }
p = Pattern.compile("^https?://www.instagram.com/([^/]+)/?"); p = Pattern.compile("^https?://www.instagram.com/([^/]+)/?(?:\\?hl=\\S*)?/?");
m = p.matcher(url.toExternalForm()); m = p.matcher(url.toExternalForm());
if (m.matches()) { if (m.matches()) {
return m.group(1); return m.group(1);