[YouTube] Switch to new search suggestion domain and improve error handling

- Switch to the new domain used by YouTube for search suggestions,
suggestqueries-clients6.youtube.com, and add the xhr query parameter with the
t value, to allow getting responses without requiring trim;
- Use the Java 8 Stream API to collect search suggestions and improve invalid
response detection by checking whether the content type of the response
returned is JSON;
- Move the licence header at the top of the file.
This commit is contained in:
AudricV 2022-10-03 18:31:13 +02:00
parent d61dc27406
commit e923fca440
No known key found for this signature in database
GPG Key ID: DA92EC7905614198
1 changed files with 61 additions and 47 deletions

View File

@ -1,6 +1,27 @@
/*
* Created by Christian Schabesberger on 28.09.16.
*
* Copyright (C) Christian Schabesberger 2015 <chris.schabesberger@mailbox.org>
* YoutubeSuggestionExtractor.java is part of NewPipe Extractor.
*
* NewPipe Extractor is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* NewPipe Extractor is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with NewPipe Extractor. If not, see <https://www.gnu.org/licenses/>.
*/
package org.schabi.newpipe.extractor.services.youtube.extractors;
import static org.schabi.newpipe.extractor.services.youtube.YoutubeParsingHelper.getCookieHeader;
import static org.schabi.newpipe.extractor.utils.Utils.isBlank;
import static org.schabi.newpipe.extractor.utils.Utils.isNullOrEmpty;
import com.grack.nanojson.JsonArray;
import com.grack.nanojson.JsonParser;
@ -8,35 +29,18 @@ import com.grack.nanojson.JsonParserException;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.downloader.Downloader;
import org.schabi.newpipe.extractor.downloader.Response;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.suggestion.SuggestionExtractor;
import org.schabi.newpipe.extractor.utils.Utils;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
/*
* Created by Christian Schabesberger on 28.09.16.
*
* Copyright (C) Christian Schabesberger 2015 <chris.schabesberger@mailbox.org>
* YoutubeSuggestionExtractor.java is part of NewPipe.
*
* NewPipe is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* NewPipe is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with NewPipe. If not, see <http://www.gnu.org/licenses/>.
*/
import java.util.Map;
import java.util.stream.Collectors;
public class YoutubeSuggestionExtractor extends SuggestionExtractor {
@ -46,35 +50,45 @@ public class YoutubeSuggestionExtractor extends SuggestionExtractor {
@Override
public List<String> suggestionList(final String query) throws IOException, ExtractionException {
final Downloader dl = NewPipe.getDownloader();
final List<String> suggestions = new ArrayList<>();
final String url = "https://suggestqueries.google.com/complete/search"
+ "?client=" + "youtube" //"firefox" for JSON, 'toolbar' for xml
+ "&jsonp=" + "JP"
final String url = "https://suggestqueries-clients6.youtube.com/complete/search"
+ "?client=" + "youtube"
+ "&ds=" + "yt"
+ "&gl=" + Utils.encodeUrlUtf8(getExtractorContentCountry().getCountryCode())
+ "&q=" + Utils.encodeUrlUtf8(query);
+ "&q=" + Utils.encodeUrlUtf8(query)
+ "&xhr=t";
final Map<String, List<String>> headers = new HashMap<>();
headers.put("Origin", Collections.singletonList("https://www.youtube.com"));
headers.put("Referer", Collections.singletonList("https://www.youtube.com"));
final Response response = NewPipe.getDownloader()
.get(url, headers, getExtractorLocalization());
final String contentTypeHeader = response.getHeader("Content-Type");
if (isNullOrEmpty(contentTypeHeader) || !contentTypeHeader.contains("application/json")) {
throw new ExtractionException("Invalid response type (got \"" + contentTypeHeader
+ "\", excepted a JSON response) (response code "
+ response.responseCode() + ")");
}
final String responseBody = response.responseBody();
if (responseBody.isEmpty()) {
throw new ExtractionException("Empty response received");
}
String response = dl.get(url, getCookieHeader(), getExtractorLocalization()).responseBody();
// trim JSONP part "JP(...)"
response = response.substring(3, response.length() - 1);
try {
final JsonArray collection = JsonParser.array().from(response).getArray(1);
for (final Object suggestion : collection) {
if (!(suggestion instanceof JsonArray)) {
continue;
}
final String suggestionStr = ((JsonArray) suggestion).getString(0);
if (suggestionStr == null) {
continue;
}
suggestions.add(suggestionStr);
}
return suggestions;
final JsonArray suggestions = JsonParser.array()
.from(responseBody)
.getArray(1); // 0: search query, 1: search suggestions, 2: tracking data?
return suggestions.stream()
.filter(JsonArray.class::isInstance)
.map(JsonArray.class::cast)
.map(suggestion -> suggestion.getString(0)) // 0 is the search suggestion
.filter(suggestion -> !isBlank(suggestion)) // Filter blank suggestions
.collect(Collectors.toUnmodifiableList());
} catch (final JsonParserException e) {
throw new ParsingException("Could not parse json response", e);
throw new ParsingException("Could not parse JSON response", e);
}
}
}