mirror of
https://github.com/RipMeApp/ripme.git
synced 2025-08-15 10:24:04 +02:00
Fix rgif ripper
This commit is contained in:
@@ -1,10 +1,8 @@
|
|||||||
package com.rarchives.ripme.ripper.rippers;
|
package com.rarchives.ripme.ripper.rippers;
|
||||||
|
|
||||||
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
|
|
||||||
import com.rarchives.ripme.utils.Http;
|
import com.rarchives.ripme.utils.Http;
|
||||||
import org.json.JSONArray;
|
import org.json.JSONArray;
|
||||||
import org.json.JSONObject;
|
import org.json.JSONObject;
|
||||||
import org.jsoup.Jsoup;
|
|
||||||
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;
|
import org.jsoup.select.Elements;
|
||||||
@@ -19,14 +17,26 @@ import java.util.List;
|
|||||||
import java.util.regex.Matcher;
|
import java.util.regex.Matcher;
|
||||||
import java.util.regex.Pattern;
|
import java.util.regex.Pattern;
|
||||||
|
|
||||||
public class RedgifsRipper extends AbstractHTMLRipper {
|
import org.apache.http.client.utils.URIBuilder;
|
||||||
|
|
||||||
|
import com.rarchives.ripme.ripper.AbstractJSONRipper;
|
||||||
|
|
||||||
|
public class RedgifsRipper extends AbstractJSONRipper {
|
||||||
|
|
||||||
private static final String HOST = "redgifs.com";
|
private static final String HOST = "redgifs.com";
|
||||||
private static final String HOST_2 = "gifdeliverynetwork.com";
|
private static final String HOST_2 = "gifdeliverynetwork.com";
|
||||||
|
private static final String GIFS_DETAIL_ENDPOINT = "https://api.redgifs.com/v2/gifs/%s";
|
||||||
|
private static final String USERS_SEARCH_ENDPOINT = "https://api.redgifs.com/v2/users/%s/search";
|
||||||
|
private static final String TEMPORARY_AUTH_ENDPOINT = "https://api.redgifs.com/v2/auth/temporary";
|
||||||
String username = "";
|
String username = "";
|
||||||
|
String authToken = "";
|
||||||
|
// TODO remove
|
||||||
String cursor = "";
|
String cursor = "";
|
||||||
String count = "100";
|
int count = 40;
|
||||||
|
int currentPage = 1;
|
||||||
|
int maxPages = 1;
|
||||||
|
|
||||||
|
// TODO remove with search
|
||||||
String searchText = "";
|
String searchText = "";
|
||||||
int searchCount = 150;
|
int searchCount = 150;
|
||||||
int searchStart = 0;
|
int searchStart = 0;
|
||||||
@@ -73,18 +83,29 @@ public class RedgifsRipper extends AbstractHTMLRipper {
|
|||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public Document getFirstPage() throws IOException {
|
public JSONObject getFirstPage() throws IOException {
|
||||||
try {
|
try {
|
||||||
if (!isProfile().matches() && !isSearch().matches()) {
|
if (authToken == null || authToken.equals("")){
|
||||||
return Http.url(url).get();
|
fetchAuthToken();
|
||||||
|
}
|
||||||
|
|
||||||
|
if (isSingleton().matches()) {
|
||||||
|
maxPages = 1;
|
||||||
|
String gifDetailsURL = String.format(GIFS_DETAIL_ENDPOINT, getGID(url));
|
||||||
|
return Http.url(gifDetailsURL).header("Authorization", "Bearer " + authToken).getJSON();
|
||||||
} else if (isSearch().matches()) {
|
} else if (isSearch().matches()) {
|
||||||
searchText = getGID(url).replace("-", " ");
|
// TODO fix search
|
||||||
return Http.url(
|
// TODO remove
|
||||||
new URI("https://api.redgifs.com/v1/gfycats/search?search_text=" + searchText + "&count=" + searchCount + "&start=" + searchStart * searchCount).toURL()).ignoreContentType().get();
|
throw new IOException("TODO remove");
|
||||||
} else {
|
} else {
|
||||||
username = getGID(url);
|
username = getGID(url);
|
||||||
return Http.url(new URI("https://api.redgifs.com/v1/users/" + username + "/gfycats?count=" + count).toURL())
|
var uri = new URIBuilder(String.format(USERS_SEARCH_ENDPOINT, username));
|
||||||
.ignoreContentType().get();
|
uri.addParameter("order", "new");
|
||||||
|
uri.addParameter("count", Integer.toString(count));
|
||||||
|
uri.addParameter("page", Integer.toString(currentPage));
|
||||||
|
var json = Http.url(uri.build().toURL()).header("Authorization", "Bearer " + authToken).getJSON();
|
||||||
|
maxPages = json.getInt("pages");
|
||||||
|
return json;
|
||||||
}
|
}
|
||||||
} catch (URISyntaxException e) {
|
} catch (URISyntaxException e) {
|
||||||
throw new IOException(e);
|
throw new IOException(e);
|
||||||
@@ -118,6 +139,7 @@ public class RedgifsRipper extends AbstractHTMLRipper {
|
|||||||
+ " Got: " + url);
|
+ " Got: " + url);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// TODO remove
|
||||||
private String stripHTMLTags(String t) {
|
private String stripHTMLTags(String t) {
|
||||||
t = t.replaceAll("<html>\n" +
|
t = t.replaceAll("<html>\n" +
|
||||||
" <head></head>\n" +
|
" <head></head>\n" +
|
||||||
@@ -130,42 +152,47 @@ public class RedgifsRipper extends AbstractHTMLRipper {
|
|||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public Document getNextPage(Document doc) throws IOException, URISyntaxException {
|
public JSONObject getNextPage(JSONObject doc) throws IOException, URISyntaxException {
|
||||||
if (isSearch().matches()) {
|
if (currentPage == maxPages || isSingleton().matches()){
|
||||||
Document d = Http.url(
|
|
||||||
new URI("https://api.redgifs.com/v1/gfycats/search?search_text=" + searchText
|
|
||||||
+ "&count=" + searchCount + "&start=" + searchCount*++searchStart).toURL())
|
|
||||||
.ignoreContentType().get();
|
|
||||||
return (hasURLs(d).isEmpty()) ? null : d;
|
|
||||||
} else {
|
|
||||||
if (cursor.equals("") || cursor.equals("null")) {
|
|
||||||
return null;
|
return null;
|
||||||
} else {
|
|
||||||
Document d = Http.url(new URI("https://api.redgifs.com/v1/users/" + username + "/gfycats?count=" + count + "&cursor=" + cursor).toURL()).ignoreContentType().get();
|
|
||||||
return (hasURLs(d).isEmpty()) ? null : d;
|
|
||||||
}
|
}
|
||||||
|
currentPage++;
|
||||||
|
if (isSearch().matches()) {
|
||||||
|
// TODO search
|
||||||
|
// TODO remove
|
||||||
|
throw new IOException("// TODO remove");
|
||||||
|
} else if (isProfile().matches()) {
|
||||||
|
var uri = new URIBuilder(String.format(USERS_SEARCH_ENDPOINT, getGID(url)));
|
||||||
|
uri.addParameter("order", "new");
|
||||||
|
uri.addParameter("count", Integer.toString(count));
|
||||||
|
uri.addParameter("page", Integer.toString(currentPage));
|
||||||
|
var json = Http.url(uri.build().toURL()).header("Authorization", "Bearer " + authToken).getJSON();
|
||||||
|
// Handle rare maxPages change during a rip
|
||||||
|
maxPages = json.getInt("pages");
|
||||||
|
return json;
|
||||||
|
} else {
|
||||||
|
return null;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public List<String> getURLsFromPage(Document doc) {
|
public List<String> getURLsFromJSON(JSONObject json) {
|
||||||
List<String> result = new ArrayList<>();
|
List<String> result = new ArrayList<>();
|
||||||
if (isProfile().matches() || isSearch().matches()) {
|
if (isProfile().matches() || isSearch().matches()) {
|
||||||
result = hasURLs(doc);
|
// TODO check json keys for search
|
||||||
|
var gifs = json.getJSONArray("gifs");
|
||||||
|
for (var gif : gifs){
|
||||||
|
var hdURL = ((JSONObject)gif).getJSONObject("urls").getString("hd");
|
||||||
|
result.add(hdURL);
|
||||||
|
}
|
||||||
} else {
|
} else {
|
||||||
Elements videos = doc.select("script");
|
String hdURL = json.getJSONObject("gif").getJSONObject("urls").getString("hd");
|
||||||
for (Element el : videos) {
|
result.add(hdURL);
|
||||||
String json = el.html();
|
|
||||||
if (json.startsWith("{")) {
|
|
||||||
JSONObject page = new JSONObject(json);
|
|
||||||
result.add(page.getJSONObject("video").getString("contentUrl")
|
|
||||||
.replace("-mobile", ""));
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// TODO delete
|
||||||
/**
|
/**
|
||||||
* Helper method for retrieving URLs.
|
* Helper method for retrieving URLs.
|
||||||
* @param doc Document of the URL page to look through
|
* @param doc Document of the URL page to look through
|
||||||
@@ -182,6 +209,7 @@ public class RedgifsRipper extends AbstractHTMLRipper {
|
|||||||
return result;
|
return result;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// TODO delete
|
||||||
/**
|
/**
|
||||||
* Helper method for retrieving video URLs.
|
* Helper method for retrieving video URLs.
|
||||||
* @param url URL to gfycat page
|
* @param url URL to gfycat page
|
||||||
@@ -206,4 +234,15 @@ public class RedgifsRipper extends AbstractHTMLRipper {
|
|||||||
}
|
}
|
||||||
throw new IOException();
|
throw new IOException();
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Fetch a temorary auth token for the rip
|
||||||
|
* @throws IOException
|
||||||
|
*/
|
||||||
|
private void fetchAuthToken() throws IOException{
|
||||||
|
var json = Http.url(TEMPORARY_AUTH_ENDPOINT).getJSON();
|
||||||
|
var token = json.getString("token");
|
||||||
|
authToken = token;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
Reference in New Issue
Block a user