CypherpunkSamurai
/
NewPipeExtractor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

added comments extractor

This commit is contained in:
Ritvik Saraf 2018-08-20 04:22:19 +05:30
parent 1e7bcfbd66
commit 53d3997904
17 changed files with 1007 additions and 159 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
build.gradle
View File

@ -1,7 +1,7 @@
allprojects {
apply plugin: 'java-library'
sourceCompatibility = 1.7
targetCompatibility = 1.7
sourceCompatibility = 1.8
targetCompatibility = 1.8
version 'v0.13.0'

1
extractor/build.gradle
View File

@ -6,6 +6,7 @@ dependencies {
implementation 'org.mozilla:rhino:1.7.7.1'
implementation 'com.github.spotbugs:spotbugs-annotations:3.1.0'
implementation 'org.nibor.autolink:autolink:0.8.0'
implementation 'com.fasterxml.jackson.core:jackson-databind:2.9.5'
testImplementation 'junit:junit:4.12'
}

26
extractor/src/main/java/org/schabi/newpipe/extractor/DownloadResponse.java Normal file
View File

@ -0,0 +1,26 @@
package org.schabi.newpipe.extractor;
import java.util.List;
import java.util.Map;
public class DownloadResponse {
private final String responseBody;
private final Map<String, List<String>> responseHeaders;
public DownloadResponse(String responseBody, Map<String, List<String>> headers) {
super();
this.responseBody = responseBody;
this.responseHeaders = headers;
}
public String getResponseBody() {
return responseBody;
}
public Map<String, List<String>> getResponseHeaders() {
return responseHeaders;
}
}

69
extractor/src/main/java/org/schabi/newpipe/extractor/Downloader.java
View File

@ -1,10 +1,11 @@
package org.schabi.newpipe.extractor;
import org.schabi.newpipe.extractor.exceptions.ReCaptchaException;
import java.io.IOException;
import java.util.List;
import java.util.Map;
import org.schabi.newpipe.extractor.exceptions.ReCaptchaException;
/*
* Created by Christian Schabesberger on 28.01.16.
*
@ -27,35 +28,41 @@ import java.util.Map;
public interface Downloader {
/**
* Download the text file at the supplied URL as in download(String),
* but set the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param language the language (usually a 2-character code) to set as the preferred language
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl, String language) throws IOException, ReCaptchaException;
/**
* Download the text file at the supplied URL as in download(String), but set
* the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param language the language (usually a 2-character code) to set as the
* preferred language
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl, String language) throws IOException, ReCaptchaException;
/**
* Download the text file at the supplied URL as in download(String),
* but set the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param customProperties set request header properties
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl, Map<String, String> customProperties) throws IOException, ReCaptchaException;
/**
* Download the text file at the supplied URL as in download(String), but set
* the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param customProperties set request header properties
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl, Map<String, String> customProperties) throws IOException, ReCaptchaException;
/**
* Download (via HTTP) the text file located at the supplied URL, and return its contents.
* Primarily intended for downloading web pages.
*
* @param siteUrl the URL of the text file to download
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl) throws IOException, ReCaptchaException;
/**
* Download (via HTTP) the text file located at the supplied URL, and return its
* contents. Primarily intended for downloading web pages.
*
* @param siteUrl the URL of the text file to download
* @return the contents of the specified text file
* @throws IOException
*/
String download(String siteUrl) throws IOException, ReCaptchaException;
DownloadResponse downloadWithHeaders(String siteUrl, Map<String, List<String>> requestHeaders)
throws IOException, ReCaptchaException;
DownloadResponse downloadWithHeaders(String siteUrl) throws IOException, ReCaptchaException;
}

3
extractor/src/main/java/org/schabi/newpipe/extractor/InfoItem.java
View File

@ -68,6 +68,7 @@ public abstract class InfoItem implements Serializable {
public enum InfoType {
STREAM,
PLAYLIST,
CHANNEL
CHANNEL,
COMMENT
}
}

36
extractor/src/main/java/org/schabi/newpipe/extractor/StreamingService.java
View File

@ -1,18 +1,24 @@
package org.schabi.newpipe.extractor;
import org.schabi.newpipe.extractor.channel.ChannelExtractor;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.kiosk.KioskList;
import org.schabi.newpipe.extractor.playlist.PlaylistExtractor;
import org.schabi.newpipe.extractor.search.SearchExtractor;
import org.schabi.newpipe.extractor.linkhandler.*;
import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.subscription.SubscriptionExtractor;
import java.util.Collections;
import java.util.List;
import org.schabi.newpipe.extractor.channel.ChannelExtractor;
import org.schabi.newpipe.extractor.comments.CommentsExtractor;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.kiosk.KioskList;
import org.schabi.newpipe.extractor.linkhandler.LinkHandler;
import org.schabi.newpipe.extractor.linkhandler.LinkHandlerFactory;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandlerFactory;
import org.schabi.newpipe.extractor.linkhandler.SearchQueryHandler;
import org.schabi.newpipe.extractor.linkhandler.SearchQueryHandlerFactory;
import org.schabi.newpipe.extractor.playlist.PlaylistExtractor;
import org.schabi.newpipe.extractor.search.SearchExtractor;
import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.subscription.SubscriptionExtractor;
public abstract class StreamingService {
public static class ServiceInfo {
private final String name;
@ -71,6 +77,7 @@ public abstract class StreamingService {
public abstract ListLinkHandlerFactory getChannelLHFactory();
public abstract ListLinkHandlerFactory getPlaylistLHFactory();
public abstract SearchQueryHandlerFactory getSearchQHFactory();
public abstract ListLinkHandlerFactory getCommentsLHFactory();
////////////////////////////////////////////
@ -84,6 +91,7 @@ public abstract class StreamingService {
public abstract ChannelExtractor getChannelExtractor(ListLinkHandler urlIdHandler) throws ExtractionException;
public abstract PlaylistExtractor getPlaylistExtractor(ListLinkHandler urlIdHandler) throws ExtractionException;
public abstract StreamExtractor getStreamExtractor(LinkHandler UIHFactory) throws ExtractionException;
public abstract CommentsExtractor getCommentsExtractor(ListLinkHandler urlIdHandler) throws ExtractionException;
public SearchExtractor getSearchExtractor(String query, List<String> contentFilter, String sortFilter, String contentCountry) throws ExtractionException {
return getSearchExtractor(getSearchQHFactory().fromQuery(query, contentFilter, sortFilter), contentCountry);
@ -112,10 +120,16 @@ public abstract class StreamingService {
public StreamExtractor getStreamExtractor(String url) throws ExtractionException {
return getStreamExtractor(getStreamLHFactory().fromUrl(url));
}
public CommentsExtractor getCommentsExtractor(String url) throws ExtractionException {
return getCommentsExtractor(getCommentsLHFactory().fromUrl(url));
}
/**
/**
* figure out where the link is pointing to (a channel, video, playlist, etc.)
*/
public final LinkType getLinkTypeByUrl(String url) throws ParsingException {

14
extractor/src/main/java/org/schabi/newpipe/extractor/comments/CommentsExtractor.java Normal file
View File

@ -0,0 +1,14 @@
package org.schabi.newpipe.extractor.comments;
import org.schabi.newpipe.extractor.ListExtractor;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
public abstract class CommentsExtractor extends ListExtractor<CommentsInfoItem> {
public CommentsExtractor(StreamingService service, ListLinkHandler uiHandler) {
super(service, uiHandler);
// TODO Auto-generated constructor stub
}
}

27
extractor/src/main/java/org/schabi/newpipe/extractor/comments/CommentsInfo.java Normal file
View File

@ -0,0 +1,27 @@
package org.schabi.newpipe.extractor.comments;
import java.io.IOException;
import org.schabi.newpipe.extractor.ListInfo;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
public class CommentsInfo extends ListInfo<CommentsInfoItem>{
private CommentsInfo(int serviceId, ListLinkHandler listUrlIdHandler, String name) {
super(serviceId, listUrlIdHandler, name);
// TODO Auto-generated constructor stub
}
public static CommentsInfo getInfo(String url) throws IOException, ExtractionException {
return getInfo(NewPipe.getServiceByUrl(url), url);
}
private static CommentsInfo getInfo(StreamingService serviceByUrl, String url) {
// TODO Auto-generated method stub
return null;
}
}

76
extractor/src/main/java/org/schabi/newpipe/extractor/comments/CommentsInfoItem.java Normal file
View File

@ -0,0 +1,76 @@
package org.schabi.newpipe.extractor.comments;
import org.schabi.newpipe.extractor.InfoItem;
public class CommentsInfoItem extends InfoItem{
private String commentId;
private String commentText;
private String authorName;
private String authorThumbnail;
private String authorEndpoint;
private String publishedTime;
private Integer likeCount;
public CommentsInfoItem(int serviceId, String url, String name) {
super(InfoType.COMMENT, serviceId, url, name);
// TODO Auto-generated constructor stub
}
public String getCommentText() {
return commentText;
}
public void setCommentText(String contentText) {
this.commentText = contentText;
}
public String getAuthorName() {
return authorName;
}
public void setAuthorName(String authorName) {
this.authorName = authorName;
}
public String getAuthorThumbnail() {
return authorThumbnail;
}
public void setAuthorThumbnail(String authorThumbnail) {
this.authorThumbnail = authorThumbnail;
}
public String getAuthorEndpoint() {
return authorEndpoint;
}
public void setAuthorEndpoint(String authorEndpoint) {
this.authorEndpoint = authorEndpoint;
}
public String getPublishedTime() {
return publishedTime;
}
public void setPublishedTime(String publishedTime) {
this.publishedTime = publishedTime;
}
public Integer getLikeCount() {
return likeCount;
}
public void setLikeCount(Integer likeCount) {
this.likeCount = likeCount;
}
public String getCommentId() {
return commentId;
}
public void setCommentId(String commentId) {
this.commentId = commentId;
}
}

22
extractor/src/main/java/org/schabi/newpipe/extractor/comments/CommentsInfoItemExtractor.java Normal file
View File

@ -0,0 +1,22 @@
package org.schabi.newpipe.extractor.comments;
import org.schabi.newpipe.extractor.InfoItemExtractor;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
public interface CommentsInfoItemExtractor extends InfoItemExtractor {
String getCommentId() throws ParsingException;
String getCommentText() throws ParsingException;
String getAuthorName() throws ParsingException;
String getAuthorThumbnail() throws ParsingException;
String getAuthorEndpoint() throws ParsingException;
String getPublishedTime() throws ParsingException;
Integer getLikeCount() throws ParsingException;
}

103
extractor/src/main/java/org/schabi/newpipe/extractor/comments/CommentsInfoItemsCollector.java Normal file
View File

@ -0,0 +1,103 @@
package org.schabi.newpipe.extractor.comments;
import java.util.List;
import java.util.Vector;
import org.schabi.newpipe.extractor.InfoItem;
import org.schabi.newpipe.extractor.InfoItemsCollector;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
/*
* Created by Christian Schabesberger on 28.02.16.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* CommentsInfoItemsCollector.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/>.
*/
public class CommentsInfoItemsCollector extends InfoItemsCollector<CommentsInfoItem, CommentsInfoItemExtractor> {
public CommentsInfoItemsCollector(int serviceId) {
super(serviceId);
}
@Override
public CommentsInfoItem extract(CommentsInfoItemExtractor extractor) throws ParsingException {
// important information
int serviceId = getServiceId();
String url = extractor.getUrl();
String name = extractor.getName();
CommentsInfoItem resultItem = new CommentsInfoItem(serviceId, url, name);
// optional information
try {
resultItem.setCommentId(extractor.getCommentId());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setCommentText(extractor.getCommentText());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setAuthorName(extractor.getAuthorName());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setAuthorThumbnail(extractor.getAuthorThumbnail());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setAuthorEndpoint(extractor.getAuthorEndpoint());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setPublishedTime(extractor.getPublishedTime());
} catch (Exception e) {
addError(e);
}
try {
resultItem.setLikeCount(extractor.getLikeCount());
} catch (Exception e) {
addError(e);
}
return resultItem;
}
@Override
public void commit(CommentsInfoItemExtractor extractor) {
try {
addItem(extract(extractor));
} catch (Exception e) {
addError(e);
}
}
public List<CommentsInfoItem> getCommentsInfoItemList() {
List<CommentsInfoItem> siiList = new Vector<>();
for (InfoItem ii : super.getItems()) {
if (ii instanceof CommentsInfoItem) {
siiList.add((CommentsInfoItem) ii);
}
}
return siiList;
}
}

13
extractor/src/main/java/org/schabi/newpipe/extractor/services/soundcloud/SoundcloudService.java
View File

@ -3,6 +3,7 @@ package org.schabi.newpipe.extractor.services.soundcloud;
import org.schabi.newpipe.extractor.*;
import org.schabi.newpipe.extractor.linkhandler.*;
import org.schabi.newpipe.extractor.channel.ChannelExtractor;
import org.schabi.newpipe.extractor.comments.CommentsExtractor;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.kiosk.KioskExtractor;
import org.schabi.newpipe.extractor.kiosk.KioskList;
@ -98,4 +99,16 @@ public class SoundcloudService extends StreamingService {
public SubscriptionExtractor getSubscriptionExtractor() {
return new SoundcloudSubscriptionExtractor(this);
}
@Override
public ListLinkHandlerFactory getCommentsLHFactory() {
// TODO Auto-generated method stub
return null;
}
@Override
public CommentsExtractor getCommentsExtractor(ListLinkHandler urlIdHandler) throws ExtractionException {
// TODO Auto-generated method stub
return null;
}
}

45
extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/YoutubeService.java
View File

@ -1,21 +1,42 @@
package org.schabi.newpipe.extractor.services.youtube;
import org.schabi.newpipe.extractor.*;
import org.schabi.newpipe.extractor.linkhandler.*;
import static java.util.Arrays.asList;
import static org.schabi.newpipe.extractor.StreamingService.ServiceInfo.MediaCapability.AUDIO;
import static org.schabi.newpipe.extractor.StreamingService.ServiceInfo.MediaCapability.LIVE;
import static org.schabi.newpipe.extractor.StreamingService.ServiceInfo.MediaCapability.VIDEO;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.SuggestionExtractor;
import org.schabi.newpipe.extractor.channel.ChannelExtractor;
import org.schabi.newpipe.extractor.comments.CommentsExtractor;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.kiosk.KioskExtractor;
import org.schabi.newpipe.extractor.kiosk.KioskList;
import org.schabi.newpipe.extractor.linkhandler.LinkHandler;
import org.schabi.newpipe.extractor.linkhandler.LinkHandlerFactory;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandlerFactory;
import org.schabi.newpipe.extractor.linkhandler.SearchQueryHandler;
import org.schabi.newpipe.extractor.linkhandler.SearchQueryHandlerFactory;
import org.schabi.newpipe.extractor.playlist.PlaylistExtractor;
import org.schabi.newpipe.extractor.search.SearchExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.*;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.*;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeChannelExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeCommentsExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubePlaylistExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeSearchExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeStreamExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeSubscriptionExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeSuggestionExtractor;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeTrendingExtractor;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeChannelLinkHandlerFactory;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeCommentsLinkHandlerFactory;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubePlaylistLinkHandlerFactory;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeSearchQueryHandlerFactory;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeStreamLinkHandlerFactory;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeTrendingLinkHandlerFactory;
import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.subscription.SubscriptionExtractor;
import static java.util.Arrays.asList;
import static org.schabi.newpipe.extractor.StreamingService.ServiceInfo.MediaCapability.*;
/*
* Created by Christian Schabesberger on 23.08.15.
@ -115,4 +136,14 @@ public class YoutubeService extends StreamingService {
return new YoutubeSubscriptionExtractor(this);
}
@Override
public ListLinkHandlerFactory getCommentsLHFactory() {
return YoutubeCommentsLinkHandlerFactory.getInstance();
}
@Override
public CommentsExtractor getCommentsExtractor(ListLinkHandler urlIdHandler) throws ExtractionException {
return new YoutubeCommentsExtractor(this, urlIdHandler);
}
}

262
extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/extractors/YoutubeCommentsExtractor.java Normal file
View File

@ -0,0 +1,262 @@
package org.schabi.newpipe.extractor.services.youtube.extractors;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.UnsupportedEncodingException;
import java.net.URL;
import java.net.URLEncoder;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import javax.net.ssl.HttpsURLConnection;
import org.schabi.newpipe.extractor.DownloadResponse;
import org.schabi.newpipe.extractor.Downloader;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.comments.CommentsExtractor;
import org.schabi.newpipe.extractor.comments.CommentsInfoItem;
import org.schabi.newpipe.extractor.comments.CommentsInfoItemExtractor;
import org.schabi.newpipe.extractor.comments.CommentsInfoItemsCollector;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandler;
import com.fasterxml.jackson.databind.JsonNode;
import com.fasterxml.jackson.databind.ObjectMapper;
public class YoutubeCommentsExtractor extends CommentsExtractor {
private static final String USER_AGENT = "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0";
private List<String> cookies;
private String sessionToken;
private String commentsToken;
private ObjectMapper mapper = new ObjectMapper();
public YoutubeCommentsExtractor(StreamingService service, ListLinkHandler uiHandler) {
super(service, uiHandler);
// TODO Auto-generated constructor stub
}
@Override
public InfoItemsPage<CommentsInfoItem> getInitialPage() throws IOException, ExtractionException {
// initial page does not load any comments but is required to get session token
// and cookies
return getPage(getNextPageUrl());
}
@Override
public String getNextPageUrl() throws IOException, ExtractionException {
return getNextPageUrl(commentsToken);
}
private String getNextPageUrl(JsonNode ajaxJson) throws IOException, ExtractionException {
String continuation;
try {
continuation = ajaxJson.findValue("itemSectionContinuation").get("continuations").findValue("continuation")
.asText();
} catch (Exception e) {
// no more comments
return "";
}
return getNextPageUrl(continuation);
}
private String getNextPageUrl(String continuation) throws ParsingException {
Map<String, String> params = new HashMap<>();
params.put("action_get_comments", "1");
params.put("pbj", "1");
params.put("ctoken", continuation);
params.put("continuation", continuation);
try {
return "https://www.youtube.com/comment_service_ajax?" + getDataString(params);
} catch (UnsupportedEncodingException e) {
throw new ParsingException("Could not get next page url", e);
}
}
@Override
public InfoItemsPage<CommentsInfoItem> getPage(String pageUrl) throws IOException, ExtractionException {
if (pageUrl == null || pageUrl.isEmpty()) {
throw new ExtractionException(new IllegalArgumentException("Page url is empty or null"));
}
String ajaxResponse = makeAjaxRequest(pageUrl);
JsonNode ajaxJson = mapper.readTree(ajaxResponse);
CommentsInfoItemsCollector collector = new CommentsInfoItemsCollector(getServiceId());
collectCommentsFrom(collector, ajaxJson, pageUrl);
return new InfoItemsPage<>(collector, getNextPageUrl(ajaxJson));
}
private void collectCommentsFrom(CommentsInfoItemsCollector collector, JsonNode ajaxJson, String pageUrl) {
List<JsonNode> comments = ajaxJson.findValues("commentRenderer");
comments.stream().forEach(c -> {
CommentsInfoItemExtractor extractor = new CommentsInfoItemExtractor() {
@Override
public String getUrl() throws ParsingException {
return pageUrl;
}
@Override
public String getThumbnailUrl() throws ParsingException {
try {
return c.get("authorThumbnail").get("thumbnails").get(0).get("url").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getName() throws ParsingException {
try {
return c.get("authorText").get("simpleText").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getPublishedTime() throws ParsingException {
try {
return c.get("publishedTimeText").get("runs").get(0).get("text").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public Integer getLikeCount() throws ParsingException {
try {
return c.get("likeCount").intValue();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getCommentText() throws ParsingException {
try {
if (null != c.get("contentText").get("simpleText")) {
return c.get("contentText").get("simpleText").asText();
} else {
return c.get("contentText").get("runs").get(0).get("text").asText();
}
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getCommentId() throws ParsingException {
try {
return c.get("commentId").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getAuthorThumbnail() throws ParsingException {
try {
return c.get("authorThumbnail").get("thumbnails").get(0).get("url").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getAuthorName() throws ParsingException {
try {
return c.get("authorText").get("simpleText").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
@Override
public String getAuthorEndpoint() throws ParsingException {
try {
return "https://youtube.com"
+ c.get("authorEndpoint").get("browseEndpoint").get("canonicalBaseUrl").asText();
} catch (Exception e) {
throw new ParsingException("Could not get thumbnail url", e);
}
}
};
collector.commit(extractor);
});
}
@Override
public void onFetchPage(Downloader downloader) throws IOException, ExtractionException {
DownloadResponse response = downloader.downloadWithHeaders(getUrl());
String responseBody = response.getResponseBody();
cookies = response.getResponseHeaders().get("Set-Cookie");
sessionToken = findValue(responseBody, "XSRF_TOKEN");
commentsToken = findValue(responseBody, "COMMENTS_TOKEN");
}
@Override
public String getName() throws ParsingException {
// TODO Auto-generated method stub
return null;
}
private String makeAjaxRequest(String siteUrl) throws IOException {
StringBuilder postData = new StringBuilder();
postData.append(URLEncoder.encode("session_token", "UTF-8"));
postData.append('=');
postData.append(URLEncoder.encode(sessionToken, "UTF-8"));
byte[] postDataBytes = postData.toString().getBytes("UTF-8");
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
con.setRequestMethod("POST");
con.setRequestProperty("Content-Type", "application/x-www-form-urlencoded");
con.setRequestProperty("Content-Length", String.valueOf(postDataBytes.length));
con.setRequestProperty("Accept", "*/*");
con.setRequestProperty("User-Agent", USER_AGENT);
con.setRequestProperty("X-YouTube-Client-Version", "2.20180815");
con.setRequestProperty("X-YouTube-Client-Name", "1");
// set cookies
cookies.stream().forEach(c -> con.addRequestProperty("Cookie", c));
con.setDoOutput(true);
con.getOutputStream().write(postDataBytes);
BufferedReader in = new BufferedReader(new InputStreamReader(con.getInputStream(), "UTF-8"));
StringBuilder sb = new StringBuilder();
String inputLine;
while ((inputLine = in.readLine()) != null) {
sb.append(inputLine);
}
return sb.toString();
}
private String getDataString(Map<String, String> params) throws UnsupportedEncodingException {
StringBuilder result = new StringBuilder();
boolean first = true;
for (Map.Entry<String, String> entry : params.entrySet()) {
if (first)
first = false;
else
result.append("&");
result.append(URLEncoder.encode(entry.getKey(), "UTF-8"));
result.append("=");
result.append(URLEncoder.encode(entry.getValue(), "UTF-8"));
}
return result.toString();
}
private String findValue(String doc, String key) {
int beginIndex = doc.indexOf(key) + key.length() + 4;
int endIndex = doc.indexOf("\"", beginIndex);
return doc.substring(beginIndex, endIndex);
}
}

183
extractor/src/main/java/org/schabi/newpipe/extractor/services/youtube/linkHandler/YoutubeCommentsLinkHandlerFactory.java Normal file
View File

@ -0,0 +1,183 @@
package org.schabi.newpipe.extractor.services.youtube.linkHandler;
import org.schabi.newpipe.extractor.linkhandler.ListLinkHandlerFactory;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.schabi.newpipe.extractor.Downloader;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.exceptions.FoundAdException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.exceptions.ReCaptchaException;
import org.schabi.newpipe.extractor.utils.Parser;
import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URISyntaxException;
import java.net.URLDecoder;
import java.util.List;
/*
* Created by Christian Schabesberger on 25.07.16.
*
* Copyright (C) Christian Schabesberger 2018 <chrźis.schabesberger@mailbox.org>
* YoutubeChannelLinkHandlerFactory.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/>.
*/
public class YoutubeCommentsLinkHandlerFactory extends ListLinkHandlerFactory {
private static final YoutubeCommentsLinkHandlerFactory instance = new YoutubeCommentsLinkHandlerFactory();
private static final String ID_PATTERN = "([\\-a-zA-Z0-9_]{11})";
public static YoutubeCommentsLinkHandlerFactory getInstance() {
return instance;
}
@Override
public String getId(String url) throws ParsingException, IllegalArgumentException {
if (url.isEmpty()) {
throw new IllegalArgumentException("The url parameter should not be empty");
}
String id;
String lowercaseUrl = url.toLowerCase();
if (lowercaseUrl.contains("youtube")) {
if (url.contains("attribution_link")) {
try {
String escapedQuery = Parser.matchGroup1("u=(.[^&|$]*)", url);
String query = URLDecoder.decode(escapedQuery, "UTF-8");
id = Parser.matchGroup1("v=" + ID_PATTERN, query);
} catch (UnsupportedEncodingException uee) {
throw new ParsingException("Could not parse attribution_link", uee);
}
} else if (lowercaseUrl.contains("youtube.com/shared?ci=")) {
return getRealIdFromSharedLink(url);
} else if (url.contains("vnd.youtube")) {
id = Parser.matchGroup1(ID_PATTERN, url);
} else if (url.contains("embed")) {
id = Parser.matchGroup1("embed/" + ID_PATTERN, url);
} else if (url.contains("googleads")) {
throw new FoundAdException("Error found add: " + url);
} else {
id = Parser.matchGroup1("[?&]v=" + ID_PATTERN, url);
}
} else if (lowercaseUrl.contains("youtu.be")) {
if (url.contains("v=")) {
id = Parser.matchGroup1("v=" + ID_PATTERN, url);
} else {
id = Parser.matchGroup1("[Yy][Oo][Uu][Tt][Uu]\\.[Bb][Ee]/" + ID_PATTERN, url);
}
} else if(lowercaseUrl.contains("hooktube")) {
if(lowercaseUrl.contains("&v=")
|| lowercaseUrl.contains("?v=")) {
id = Parser.matchGroup1("[?&]v=" + ID_PATTERN, url);
} else if (url.contains("/embed/")) {
id = Parser.matchGroup1("embed/" + ID_PATTERN, url);
} else if (url.contains("/v/")) {
id = Parser.matchGroup1("v/" + ID_PATTERN, url);
} else if (url.contains("/watch/")) {
id = Parser.matchGroup1("watch/" + ID_PATTERN, url);
} else {
throw new ParsingException("Error no suitable url: " + url);
}
} else {
throw new ParsingException("Error no suitable url: " + url);
}
if (!id.isEmpty()) {
return id;
} else {
throw new ParsingException("Error could not parse url: " + url);
}
}
/**
* Get the real url from a shared uri.
* <p>
* Shared URI's look like this:
* <pre>
* * https://www.youtube.com/shared?ci=PJICrTByb3E
* * vnd.youtube://www.youtube.com/shared?ci=PJICrTByb3E&amp;feature=twitter-deep-link
* </pre>
*
* @param url The shared url
* @return the id of the stream
* @throws ParsingException
*/
private String getRealIdFromSharedLink(String url) throws ParsingException {
URI uri;
try {
uri = new URI(url);
} catch (URISyntaxException e) {
throw new ParsingException("Invalid shared link", e);
}
String sharedId = getSharedId(uri);
Downloader downloader = NewPipe.getDownloader();
String content;
try {
content = downloader.download("https://www.youtube.com/shared?ci=" + sharedId);
} catch (IOException | ReCaptchaException e) {
throw new ParsingException("Unable to resolve shared link", e);
}
final Document document = Jsoup.parse(content);
final Element element = document.select("link[rel=\"canonical\"]").first();
final String urlWithRealId = (element != null)
? element.attr("abs:href")
: document.select("meta[property=\"og:url\"]").first()
.attr("abs:content");
String realId = Parser.matchGroup1(ID_PATTERN, urlWithRealId);
if (sharedId.equals(realId)) {
throw new ParsingException("Got same id for as shared info_id: " + sharedId);
}
return realId;
}
private String getSharedId(URI uri) throws ParsingException {
if (!"/shared".equals(uri.getPath())) {
throw new ParsingException("Not a shared link: " + uri.toString() + " (path != " + uri.getPath() + ")");
}
return Parser.matchGroup1("ci=" + ID_PATTERN, uri.getQuery());
}
@Override
public boolean onAcceptUrl(final String url) throws FoundAdException {
final String lowercaseUrl = url.toLowerCase();
if (lowercaseUrl.contains("youtube")
|| lowercaseUrl.contains("youtu.be")
|| lowercaseUrl.contains("hooktube")) {
// bad programming I know
try {
getId(url);
return true;
} catch (FoundAdException fe) {
throw fe;
} catch (ParsingException e) {
return false;
}
} else {
return false;
}
}
@Override
public String getUrl(String id, List<String> contentFilter, String sortFilter) throws ParsingException {
return "https://www.youtube.com/watch?v=" + id;
}
}

236
extractor/src/test/java/org/schabi/newpipe/Downloader.java
View File

@ -1,16 +1,18 @@
package org.schabi.newpipe;
import org.schabi.newpipe.extractor.exceptions.ReCaptchaException;
import javax.net.ssl.HttpsURLConnection;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.UnknownHostException;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import javax.net.ssl.HttpsURLConnection;
import org.schabi.newpipe.extractor.DownloadResponse;
import org.schabi.newpipe.extractor.exceptions.ReCaptchaException;
/*
* Created by Christian Schabesberger on 28.01.16.
@ -34,124 +36,144 @@ import java.util.Map;
public class Downloader implements org.schabi.newpipe.extractor.Downloader {
private static final String USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0";
private static String mCookies = "";
private static final String USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0";
private static String mCookies = "";
private static Downloader instance = null;
private static Downloader instance = null;
private Downloader() {
}
private Downloader() {
}
public static Downloader getInstance() {
if (instance == null) {
synchronized (Downloader.class) {
if (instance == null) {
instance = new Downloader();
}
}
}
return instance;
}
public static Downloader getInstance() {
if (instance == null) {
synchronized (Downloader.class) {
if (instance == null) {
instance = new Downloader();
}
}
}
return instance;
}
public static synchronized void setCookies(String cookies) {
Downloader.mCookies = cookies;
}
public static synchronized void setCookies(String cookies) {
Downloader.mCookies = cookies;
}
public static synchronized String getCookies() {
return Downloader.mCookies;
}
public static synchronized String getCookies() {
return Downloader.mCookies;
}
/**
* Download the text file at the supplied URL as in download(String),
* but set the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param language the language (usually a 2-character code) to set as the preferred language
* @return the contents of the specified text file
*/
public String download(String siteUrl, String language) throws IOException, ReCaptchaException {
Map<String, String> requestProperties = new HashMap<>();
requestProperties.put("Accept-Language", language);
return download(siteUrl, requestProperties);
}
/**
* Download the text file at the supplied URL as in download(String), but set
* the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param language the language (usually a 2-character code) to set as the
* preferred language
* @return the contents of the specified text file
*/
public String download(String siteUrl, String language) throws IOException, ReCaptchaException {
Map<String, String> requestProperties = new HashMap<>();
requestProperties.put("Accept-Language", language);
return download(siteUrl, requestProperties);
}
/**
* Download the text file at the supplied URL as in download(String), but set
* the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param customProperties set request header properties
* @return the contents of the specified text file
* @throws IOException
*/
public String download(String siteUrl, Map<String, String> customProperties)
throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
for (Map.Entry<String, String> pair : customProperties.entrySet()) {
con.setRequestProperty(pair.getKey(), pair.getValue());
}
return dl(con);
}
/**
* Download the text file at the supplied URL as in download(String),
* but set the HTTP header field "Accept-Language" to the supplied string.
*
* @param siteUrl the URL of the text file to return the contents of
* @param customProperties set request header properties
* @return the contents of the specified text file
* @throws IOException
*/
public String download(String siteUrl, Map<String, String> customProperties) throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
for (Map.Entry<String, String> pair: customProperties.entrySet()) {
con.setRequestProperty(pair.getKey(), pair.getValue());
}
return dl(con);
}
/**
* Common functionality between download(String url) and download(String url,
* String language)
*/
private static String dl(HttpsURLConnection con) throws IOException, ReCaptchaException {
StringBuilder response = new StringBuilder();
BufferedReader in = null;
/**
* Common functionality between download(String url) and download(String url, String language)
*/
private static String dl(HttpsURLConnection con) throws IOException, ReCaptchaException {
StringBuilder response = new StringBuilder();
BufferedReader in = null;
try {
con.setConnectTimeout(30 * 1000);// 30s
con.setReadTimeout(30 * 1000);// 30s
con.setRequestMethod("GET");
con.setRequestProperty("User-Agent", USER_AGENT);
try {
con.setConnectTimeout(30 * 1000);// 30s
con.setReadTimeout(30 * 1000);// 30s
con.setRequestMethod("GET");
con.setRequestProperty("User-Agent", USER_AGENT);
if (getCookies().length() > 0) {
con.addRequestProperty("Cookie", getCookies());
}
if (getCookies().length() > 0) {
con.setRequestProperty("Cookie", getCookies());
}
in = new BufferedReader(new InputStreamReader(con.getInputStream()));
String inputLine;
in = new BufferedReader(
new InputStreamReader(con.getInputStream()));
String inputLine;
while ((inputLine = in.readLine()) != null) {
response.append(inputLine);
}
} catch (UnknownHostException uhe) {// thrown when there's no internet connection
throw new IOException("unknown host or no network", uhe);
// Toast.makeText(getActivity(), uhe.getMessage(), Toast.LENGTH_LONG).show();
} catch (Exception e) {
/*
* HTTP 429 == Too Many Request Receive from Youtube.com = ReCaptcha challenge
* request See : https://github.com/rg3/youtube-dl/issues/5138
*/
if (con.getResponseCode() == 429) {
throw new ReCaptchaException("reCaptcha Challenge requested");
}
while ((inputLine = in.readLine()) != null) {
response.append(inputLine);
}
} catch (UnknownHostException uhe) {//thrown when there's no internet connection
throw new IOException("unknown host or no network", uhe);
//Toast.makeText(getActivity(), uhe.getMessage(), Toast.LENGTH_LONG).show();
} catch (Exception e) {
/*
* HTTP 429 == Too Many Request
* Receive from Youtube.com = ReCaptcha challenge request
* See : https://github.com/rg3/youtube-dl/issues/5138
*/
if (con.getResponseCode() == 429) {
throw new ReCaptchaException("reCaptcha Challenge requested");
}
throw new IOException(con.getResponseCode() + " " + con.getResponseMessage(), e);
} finally {
if (in != null) {
in.close();
}
}
throw new IOException(con.getResponseCode() + " " + con.getResponseMessage(), e);
} finally {
if (in != null) {
in.close();
}
}
return response.toString();
}
return response.toString();
}
/**
* Download (via HTTP) the text file located at the supplied URL, and return its
* contents. Primarily intended for downloading web pages.
*
* @param siteUrl the URL of the text file to download
* @return the contents of the specified text file
*/
public String download(String siteUrl) throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
// HttpsURLConnection con = NetCipher.getHttpsURLConnection(url);
return dl(con);
}
/**
* Download (via HTTP) the text file located at the supplied URL, and return its contents.
* Primarily intended for downloading web pages.
*
* @param siteUrl the URL of the text file to download
* @return the contents of the specified text file
*/
public String download(String siteUrl) throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
//HttpsURLConnection con = NetCipher.getHttpsURLConnection(url);
return dl(con);
}
@Override
public DownloadResponse downloadWithHeaders(String siteUrl, Map<String, List<String>> requestHeaders)
throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
for (Map.Entry<String, List<String>> pair : requestHeaders.entrySet()) {
pair.getValue().stream().forEach(value -> con.addRequestProperty(pair.getKey(), value));
}
String responseBody = dl(con);
return new DownloadResponse(responseBody, con.getHeaderFields());
}
@Override
public DownloadResponse downloadWithHeaders(String siteUrl) throws IOException, ReCaptchaException {
URL url = new URL(siteUrl);
HttpsURLConnection con = (HttpsURLConnection) url.openConnection();
String responseBody = dl(con);
return new DownloadResponse(responseBody, con.getHeaderFields());
}
}

46
extractor/src/test/java/org/schabi/newpipe/extractor/services/youtube/YoutubeCommentsExtractorTest.java Normal file
View File

@ -0,0 +1,46 @@
package org.schabi.newpipe.extractor.services.youtube;
import static org.junit.Assert.assertTrue;
import static org.schabi.newpipe.extractor.ServiceList.YouTube;
import java.io.IOException;
import org.junit.BeforeClass;
import org.junit.Test;
import org.schabi.newpipe.Downloader;
import org.schabi.newpipe.extractor.ListExtractor.InfoItemsPage;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.comments.CommentsInfoItem;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeCommentsExtractor;
public class YoutubeCommentsExtractorTest {
private static YoutubeCommentsExtractor extractor;
@BeforeClass
public static void setUp() throws Exception {
NewPipe.init(Downloader.getInstance());
extractor = (YoutubeCommentsExtractor) YouTube
.getCommentsExtractor("https://www.youtube.com/watch?v=rrgFN3AxGfs");
extractor.fetchPage();
}
@Test
public void testGetComments() throws IOException, ExtractionException {
boolean result = false;
InfoItemsPage<CommentsInfoItem> comments = extractor.getInitialPage();
result = findInComments(comments, "i should really be in the top comment.lol");
while (comments.hasNextPage()) {
comments = extractor.getPage(comments.getNextPageUrl());
result = findInComments(comments, "i should really be in the top comment.lol");
}
assertTrue(result);
}
private boolean findInComments(InfoItemsPage<CommentsInfoItem> comments, String comment) {
return comments.getItems().stream().filter(c -> c.getCommentText().contains(comment)).findAny().isPresent();
}
}