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

IG ripper can now rip videos

Browse Source
This commit is contained in:
cyian-1756 2017-11-07 23:40:14 -05:00
parent dbdedd7d5a
commit b5d09cdc97
1 changed files with 17 additions and 64 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
src/main/java/com/rarchives/ripme/ripper/rippers/InstagramRipper.java
View File

@ -15,10 +15,8 @@ import org.json.JSONObject;
import com.rarchives.ripme.ripper.AbstractJSONRipper; import com.rarchives.ripme.ripper.AbstractJSONRipper;
import com.rarchives.ripme.utils.Http; import com.rarchives.ripme.utils.Http;
import org.jsoup.Connection.Response;
import org.jsoup.nodes.Document; import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element; import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class InstagramRipper extends AbstractJSONRipper { public class InstagramRipper extends AbstractJSONRipper {
@ -97,30 +95,15 @@ public class InstagramRipper extends AbstractJSONRipper {
return getJSONFromPage("http://instagram.com/" + userID); return getJSONFromPage("http://instagram.com/" + userID);
} }
// @Override private String getVideoFromPage(String videoID) {
// public JSONObject getNextPage(JSONObject json) throws IOException { try {
// Document doc = Http.url("https://www.instagram.com/p/" + videoID).get();
// boolean nextPageAvailable; return doc.select("meta[property=og:video]").attr("content");
// try { } catch (IOException e) {
// nextPageAvailable = json.getBoolean("more_available"); logger.warn("Unable to get page " + "https://www.instagram.com/p/" + videoID);
// } catch (Exception e) { }
// throw new IOException("No additional pages found"); return "";
// } }
//
// if (nextPageAvailable) {
// JSONArray items = json.getJSONArray("items");
// JSONObject last_item = items.getJSONObject(items.length() - 1);
// String nextMaxID = last_item.getString("id");
//
// String baseURL = "http://instagram.com/" + userID + "/?max_id=" + nextMaxID;
// logger.info("Loading " + baseURL);
// sleep(1000);
//
// return Http.url(baseURL).getJSON();
// } else {
// throw new IOException("No more images found");
// }
// }
private String getOriginalUrl(String imageURL) { private String getOriginalUrl(String imageURL) {
imageURL = imageURL.replaceAll("scontent.cdninstagram.com/hphotos-", "igcdn-photos-d-a.akamaihd.net/hphotos-ak-"); imageURL = imageURL.replaceAll("scontent.cdninstagram.com/hphotos-", "igcdn-photos-d-a.akamaihd.net/hphotos-ak-");
@ -148,23 +131,6 @@ public class InstagramRipper extends AbstractJSONRipper {
return imageURL; return imageURL;
} }
private String getMedia(JSONObject data) {
String imageURL = "";
JSONObject mediaObject;
if (data.has("videos")) {
mediaObject = data.getJSONObject("videos");
if (!mediaObject.isNull("standard_resolution")) {
imageURL = mediaObject.getJSONObject("standard_resolution").getString("url");
}
} else if (data.has("images")) {
mediaObject = data.getJSONObject("images");
if (!mediaObject.isNull("standard_resolution")) {
imageURL = mediaObject.getJSONObject("standard_resolution").getString("url");
}
}
return imageURL;
}
@Override @Override
public List<String> getURLsFromJSON(JSONObject json) { public List<String> getURLsFromJSON(JSONObject json) {
String nextPageID = ""; String nextPageID = "";
@ -174,30 +140,16 @@ public class InstagramRipper extends AbstractJSONRipper {
for (int i = 0; i < datas.length(); i++) { for (int i = 0; i < datas.length(); i++) {
JSONObject data = (JSONObject) datas.get(i); JSONObject data = (JSONObject) datas.get(i);
try { try {
addURLToDownload(new URL(getOriginalUrl(data.getString("thumbnail_src")))); if (!data.getBoolean("is_video")) {
addURLToDownload(new URL(getOriginalUrl(data.getString("thumbnail_src"))));
} else {
addURLToDownload(new URL(getVideoFromPage(data.getString("code"))));
}
} catch (MalformedURLException e) { } catch (MalformedURLException e) {
return imageURLs; return imageURLs;
} }
nextPageID = data.getString("id"); nextPageID = data.getString("id");
// String dataType = data.getString("type");
// if (dataType.equals("carousel")) {
// JSONArray carouselMedias = data.getJSONArray("carousel_media");
// for (int carouselIndex = 0; carouselIndex < carouselMedias.length(); carouselIndex++) {
// JSONObject carouselMedia = (JSONObject) carouselMedias.get(carouselIndex);
// String imageURL = getMedia(carouselMedia);
// if (!imageURL.equals("")) {
// imageURL = getOriginalUrl(imageURL);
// imageURLs.add(imageURL);
// }
// }
// } else {
// String imageURL = getMedia(data);
// if (!imageURL.equals("")) {
// imageURL = getOriginalUrl(imageURL);
// imageURLs.add(imageURL);
// }
// }
if (isThisATest()) { if (isThisATest()) {
break; break;
@ -205,8 +157,9 @@ public class InstagramRipper extends AbstractJSONRipper {
} }
if (!nextPageID.equals("")) { if (!nextPageID.equals("")) {
try { try {
sleep(1000); // Sleep for a while to avoid a ban
getURLsFromJSON(getJSONFromPage("https://www.instagram.com/annabellpeaksxx/?max_id=" + nextPageID)); sleep(2500);
getURLsFromJSON(getJSONFromPage("https://www.instagram.com/" + userID + "/?max_id=" + nextPageID));
} catch (IOException e){ return imageURLs;} } catch (IOException e){ return imageURLs;}
} }
return imageURLs; return imageURLs;