merged upstream/master

This commit is contained in:
Ritvik Saraf 2018-12-04 21:20:26 +05:30
commit 4c49a347f6
23 changed files with 602 additions and 168 deletions

View file

@ -1,6 +1,6 @@
# NewPipe Extractor
[![Build Status](https://travis-ci.org/TeamNewPipe/NewPipeExtractor.svg?branch=master)](https://travis-ci.org/TeamNewPipe/NewPipeExtractor) [![JIT Pack Badge](https://jitpack.io/v/TeamNewPipe/NewPipeExtractor.svg)](https://jitpack.io/#TeamNewPipe/NewPipeExtractor) [Documentation](https://teamnewpipe.github.io/NewPipeExtractor/javadoc/)
[![Build Status](https://travis-ci.org/TeamNewPipe/NewPipeExtractor.svg?branch=master)](https://travis-ci.org/TeamNewPipe/NewPipeExtractor) [![JIT Pack Badge](https://jitpack.io/v/TeamNewPipe/NewPipeExtractor.svg)](https://jitpack.io/#TeamNewPipe/NewPipeExtractor) [Documentation](https://teamnewpipe.github.io/documentation/)
NewPipe Extractor is a library for extracting things from streaming sites. It is a core component of [NewPipe](https://github.com/TeamNewPipe/NewPipe), but could be used independently.

View file

@ -36,7 +36,14 @@ public enum MediaFormat {
M4A (0x3, "m4a", "m4a", "audio/mp4"),
WEBMA (0x4, "WebM", "webm", "audio/webm"),
MP3 (0x5, "MP3", "mp3", "audio/mpeg"),
OPUS (0x6, "opus", "opus", "audio/opus");
OPUS (0x6, "opus", "opus", "audio/opus"),
// subtitles formats
VTT (0x7, "WebVTT", "vtt", "text/vtt"),
TTML (0x8, "Timed Text Markup Language", "ttml", "application/ttml+xml"),
TRANSCRIPT1 (0x9, "TranScript v1", "srv1", "text/xml"),
TRANSCRIPT2 (0xA, "TranScript v2", "srv2", "text/xml"),
TRANSCRIPT3 (0xB, "TranScript v3", "srv3", "text/xml"),
SRT (0xC, "SubRip file format", "srt", "text/srt");
public final int id;
public final String name;

View file

@ -8,6 +8,24 @@ import java.util.List;
import static java.util.Arrays.asList;
import static java.util.Collections.unmodifiableList;
/*
* Copyright (C) Christian Schabesberger 2018 <chris.schabesberger@mailbox.org>
* ServiceList.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/>.
*/
/**
* A list of supported services.
*/
@ -19,6 +37,10 @@ public final class ServiceList {
public static final YoutubeService YouTube;
public static final SoundcloudService SoundCloud;
/**
* When creating a new service, put this service in the end of this list,
* and give it the next free id.
*/
private static final List<StreamingService> SERVICES = unmodifiableList(
asList(
YouTube = new YoutubeService(0),

View file

@ -20,11 +20,38 @@ import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.subscription.SubscriptionExtractor;
import org.schabi.newpipe.extractor.utils.Localization;
/*
* Copyright (C) Christian Schabesberger 2018 <chris.schabesberger@mailbox.org>
* StreamingService.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 abstract class StreamingService {
/**
* This class holds meta information about the service implementation.
*/
public static class ServiceInfo {
private final String name;
private final List<MediaCapability> mediaCapabilities;
/**
* Creates a new instance of a ServiceInfo
* @param name the name of the service
* @param mediaCapabilities the type of media this service can handle
*/
public ServiceInfo(String name, List<MediaCapability> mediaCapabilities) {
this.name = name;
this.mediaCapabilities = Collections.unmodifiableList(mediaCapabilities);
@ -43,6 +70,10 @@ public abstract class StreamingService {
}
}
/**
* LinkType will be used to determine which type of URL you are handling, and therefore which part
* of NewPipe should handle a certain URL.
*/
public enum LinkType {
NONE,
STREAM,
@ -53,6 +84,16 @@ public abstract class StreamingService {
private final int serviceId;
private final ServiceInfo serviceInfo;
/**
* Creates a new Streaming service.
* If you Implement one do not set id within your implementation of this extractor, instead
* set the id when you put the extractor into
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/ServiceList.html">ServiceList</a>.
* All other parameters can be set directly from the overriding constructor.
* @param id the number of the service to identify him within the NewPipe frontend
* @param name the name of the service
* @param capabilities the type of media this service can handle
*/
public StreamingService(int id, String name, List<ServiceInfo.MediaCapability> capabilities) {
this.serviceId = id;
this.serviceInfo = new ServiceInfo(name, capabilities);
@ -74,9 +115,31 @@ public abstract class StreamingService {
////////////////////////////////////////////
// Url Id handler
////////////////////////////////////////////
/**
* Must return a new instance of an implementation of LinkHandlerFactory for streams.
* @return an instance of a LinkHandlerFactory for streams
*/
public abstract LinkHandlerFactory getStreamLHFactory();
/**
* Must return a new instance of an implementation of ListLinkHandlerFactory for channels.
* If support for channels is not given null must be returned.
* @return an instance of a ListLinkHandlerFactory for channels or null
*/
public abstract ListLinkHandlerFactory getChannelLHFactory();
/**
* Must return a new instance of an implementation of ListLinkHandlerFactory for playlists.
* If support for playlists is not given null must be returned.
* @return an instance of a ListLinkHandlerFactory for playlists or null
*/
public abstract ListLinkHandlerFactory getPlaylistLHFactory();
/**
* Must return an instance of an implementation of SearchQueryHandlerFactory.
* @return an instance of a SearchQueryHandlerFactory
*/
public abstract SearchQueryHandlerFactory getSearchQHFactory();
public abstract ListLinkHandlerFactory getCommentsLHFactory();
@ -84,15 +147,62 @@ public abstract class StreamingService {
////////////////////////////////////////////
// Extractor
////////////////////////////////////////////
/**
* Must create a new instance of a SearchExtractor implementation.
* @param queryHandler specifies the keyword lock for, and the filters which should be applied.
* @param localization specifies the language/country for the extractor.
* @return a new SearchExtractor instance
*/
public abstract SearchExtractor getSearchExtractor(SearchQueryHandler queryHandler, Localization localization);
/**
* Must create a new instance of a SuggestionExtractor implementation.
* @param localization specifies the language/country for the extractor.
* @return a new SuggestionExtractor instance
*/
public abstract SuggestionExtractor getSuggestionExtractor(Localization localization);
/**
* Outdated or obsolete. null can be returned.
* @return just null
*/
public abstract SubscriptionExtractor getSubscriptionExtractor();
/**
* Must create a new instance of a KioskList implementation.
* @return a new KioskList instance
* @throws ExtractionException
*/
public abstract KioskList getKioskList() throws ExtractionException;
/**
* Must create a new instance of a ChannelExtractor implementation.
* @param linkHandler is pointing to the channel which should be handled by this new instance.
* @param localization specifies the language used for the request.
* @return a new ChannelExtractor
* @throws ExtractionException
*/
public abstract ChannelExtractor getChannelExtractor(ListLinkHandler linkHandler,
Localization localization) throws ExtractionException;
/**
* Must crete a new instance of a PlaylistExtractor implementation.
* @param linkHandler is pointing to the playlist which should be handled by this new instance.
* @param localization specifies the language used for the request.
* @return a new PlaylistExtractor
* @throws ExtractionException
*/
public abstract PlaylistExtractor getPlaylistExtractor(ListLinkHandler linkHandler,
Localization localization) throws ExtractionException;
/**
* Must create a new instance of a StreamExtractor implementation.
* @param linkHandler is pointing to the stream which should be handled by this new instance.
* @param localization specifies the language used for the request.
* @return a new StreamExtractor
* @throws ExtractionException
*/
public abstract StreamExtractor getStreamExtractor(LinkHandler linkHandler,
Localization localization) throws ExtractionException;
public abstract CommentsExtractor getCommentsExtractor(ListLinkHandler linkHandler,
@ -192,6 +302,11 @@ public abstract class StreamingService {
/**
* figure out where the link is pointing to (a channel, video, playlist, etc.)
/**
* Figures out where the link is pointing to (a channel, a video, a playlist, etc.)
* @param url the url on which it should be decided of which link type it is
* @return the link type of url
* @throws ParsingException
*/
public final LinkType getLinkTypeByUrl(String url) throws ParsingException {
LinkHandlerFactory sH = getStreamLHFactory();

View file

@ -1,34 +0,0 @@
package org.schabi.newpipe.extractor;
import org.schabi.newpipe.extractor.stream.SubtitlesFormat;
import java.io.Serializable;
import java.util.Locale;
public class Subtitles implements Serializable {
private final SubtitlesFormat format;
private final Locale locale;
private final String URL;
private final boolean autoGenerated;
public Subtitles(SubtitlesFormat format, Locale locale, String URL, boolean autoGenerated) {
this.format = format;
this.locale = locale;
this.URL = URL;
this.autoGenerated = autoGenerated;
}
public SubtitlesFormat getFileType() { return format; }
public Locale getLocale() {
return locale;
}
public String getURL() {
return URL;
}
public boolean isAutoGenerated() {
return autoGenerated;
}
}

View file

@ -172,13 +172,13 @@ public class SoundcloudStreamExtractor extends StreamExtractor {
@Override
@Nonnull
public List<Subtitles> getSubtitlesDefault() throws IOException, ExtractionException {
public List<SubtitlesStream> getSubtitlesDefault() throws IOException, ExtractionException {
return Collections.emptyList();
}
@Override
@Nonnull
public List<Subtitles> getSubtitles(SubtitlesFormat format) throws IOException, ExtractionException {
public List<SubtitlesStream> getSubtitles(MediaFormat format) throws IOException, ExtractionException {
return Collections.emptyList();
}
@ -188,12 +188,12 @@ public class SoundcloudStreamExtractor extends StreamExtractor {
}
@Override
public StreamInfoItem getNextVideo() throws IOException, ExtractionException {
public StreamInfoItem getNextStream() throws IOException, ExtractionException {
return null;
}
@Override
public StreamInfoItemsCollector getRelatedVideos() throws IOException, ExtractionException {
public StreamInfoItemsCollector getRelatedStreams() throws IOException, ExtractionException {
StreamInfoItemsCollector collector = new StreamInfoItemsCollector(getServiceId());
String apiUrl = "https://api-v2.soundcloud.com/tracks/" + urlEncode(getId()) + "/related"

View file

@ -53,7 +53,7 @@ public class YoutubeSearchExtractor extends SearchExtractor {
@Override
public void onFetchPage(@Nonnull Downloader downloader) throws IOException, ExtractionException {
final String site;
final String url = getUrl() + "?gl="+ getLocalization().getCountry();
final String url = getUrl();
//String url = builder.build().toString();
//if we've been passed a valid language code, append it to the URL
site = downloader.download(url, getLocalization());
@ -61,6 +61,11 @@ public class YoutubeSearchExtractor extends SearchExtractor {
doc = Jsoup.parse(site, url);
}
@Override
public String getUrl() throws ParsingException {
return super.getUrl() + "&gl="+ getLocalization().getCountry();
}
@Override
public String getSearchSuggestion() {
final Element el = doc.select("div[class*=\"spell-correction\"]").first();
@ -79,7 +84,7 @@ public class YoutubeSearchExtractor extends SearchExtractor {
@Override
public String getNextPageUrl() throws ExtractionException {
return getUrl() + "&page=" + 2 + "&gl=" + getLocalization().getCountry();
return getUrl() + "&page=" + 2;
}
@Override

View file

@ -7,6 +7,7 @@ import com.grack.nanojson.JsonParserException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.mozilla.javascript.Context;
import org.mozilla.javascript.Function;
import org.mozilla.javascript.ScriptableObject;
@ -460,15 +461,15 @@ public class YoutubeStreamExtractor extends StreamExtractor {
@Override
@Nonnull
public List<Subtitles> getSubtitlesDefault() throws IOException, ExtractionException {
return getSubtitles(SubtitlesFormat.TTML);
public List<SubtitlesStream> getSubtitlesDefault() throws IOException, ExtractionException {
return getSubtitles(MediaFormat.TTML);
}
@Override
@Nonnull
public List<Subtitles> getSubtitles(final SubtitlesFormat format) throws IOException, ExtractionException {
public List<SubtitlesStream> getSubtitles(final MediaFormat format) throws IOException, ExtractionException {
assertPageFetched();
List<Subtitles> subtitles = new ArrayList<>();
List<SubtitlesStream> subtitles = new ArrayList<>();
for (final SubtitlesInfo subtitlesInfo : subtitlesInfos) {
subtitles.add(subtitlesInfo.getSubtitle(format));
}
@ -490,13 +491,17 @@ public class YoutubeStreamExtractor extends StreamExtractor {
}
@Override
public StreamInfoItem getNextVideo() throws IOException, ExtractionException {
public StreamInfoItem getNextStream() throws IOException, ExtractionException {
assertPageFetched();
try {
StreamInfoItemsCollector collector = new StreamInfoItemsCollector(getServiceId());
collector.commit(extractVideoPreviewInfo(doc.select("div[class=\"watch-sidebar-section\"]")
.first().select("li").first()));
Elements watch = doc.select("div[class=\"watch-sidebar-section\"]");
if (watch.size() < 1) {
return null;// prevent the snackbar notification "report error" on age-restricted videos
}
collector.commit(extractVideoPreviewInfo(watch.first().select("li").first()));
return collector.getItems().get(0);
} catch (Exception e) {
throw new ParsingException("Could not get next video", e);
@ -504,7 +509,7 @@ public class YoutubeStreamExtractor extends StreamExtractor {
}
@Override
public StreamInfoItemsCollector getRelatedVideos() throws IOException, ExtractionException {
public StreamInfoItemsCollector getRelatedStreams() throws IOException, ExtractionException {
assertPageFetched();
try {
StreamInfoItemsCollector collector = new StreamInfoItemsCollector(getServiceId());
@ -815,21 +820,16 @@ public class YoutubeStreamExtractor extends StreamExtractor {
final String languageCode;
final boolean isGenerated;
final Locale locale;
public SubtitlesInfo(final String baseUrl, final String languageCode, final boolean isGenerated) {
this.cleanUrl = baseUrl
.replaceAll("&fmt=[^&]*", "") // Remove preexisting format if exists
.replaceAll("&tlang=[^&]*", ""); // Remove translation language
this.languageCode = languageCode;
this.isGenerated = isGenerated;
final String[] splits = languageCode.split("-");
this.locale = splits.length == 2 ? new Locale(splits[0], splits[1]) : new Locale(languageCode);
}
public Subtitles getSubtitle(final SubtitlesFormat format) {
return new Subtitles(format, locale, cleanUrl + "&fmt=" + format.getExtension(), isGenerated);
public SubtitlesStream getSubtitle(final MediaFormat format) {
return new SubtitlesStream(format, languageCode, cleanUrl + "&fmt=" + format.getSuffix(), isGenerated);
}
}

View file

@ -1,7 +1,7 @@
package org.schabi.newpipe.extractor.stream;
/*
* Created by Christian Schabesberger on 10.08.15.
* Created by Christian Schabesberger on 10.08.18.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamExtractor.java is part of NewPipe.
@ -21,8 +21,8 @@ package org.schabi.newpipe.extractor.stream;
*/
import org.schabi.newpipe.extractor.Extractor;
import org.schabi.newpipe.extractor.MediaFormat;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.Subtitles;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.linkhandler.LinkHandler;
@ -34,7 +34,7 @@ import java.io.IOException;
import java.util.List;
/**
* Scrapes information from a video streaming service (eg, YouTube).
* Scrapes information from a video/audio streaming service (eg, YouTube).
*/
public abstract class StreamExtractor extends Extractor {
@ -44,22 +44,235 @@ public abstract class StreamExtractor extends Extractor {
super(service, linkHandler, localization);
}
/**
* The day on which the stream got uploaded/created. The return information should be in the format
* dd.mm.yyyy, however it NewPipe will not crash if its not.
* @return The day on which the stream got uploaded.
* @throws ParsingException
*/
@Nonnull
public abstract String getUploadDate() throws ParsingException;
/**
* This will return the url to the thumbnail of the stream. Try to return the medium resolution here.
* @return The url of the thumbnail.
* @throws ParsingException
*/
@Nonnull
public abstract String getThumbnailUrl() throws ParsingException;
/**
* This is the stream description. On YouTube this is the video description. You can return simple HTML here.
* @return The description of the stream/video.
* @throws ParsingException
*/
@Nonnull
public abstract String getDescription() throws ParsingException;
/**
* Get the age limit
* Get the age limit.
* @return The age which limits the content or {@value NO_AGE_LIMIT} if there is no limit
* @throws ParsingException if an error occurs while parsing
*/
public abstract int getAgeLimit() throws ParsingException;
/**
* This should return the length of a video in seconds.
* @return The length of the stream in seconds.
* @throws ParsingException
*/
public abstract long getLength() throws ParsingException;
/**
* If the url you are currently handling contains a time stamp/seek, you can return the
* position it represents here.
* If the url has no time stamp simply return zero.
* @return the timestamp in seconds
* @throws ParsingException
*/
public abstract long getTimeStamp() throws ParsingException;
/**
* The count of how many people have watched the video/listened to the audio stream.
* If the current stream has no view count or its not available simply return -1
* @return amount of views.
* @throws ParsingException
*/
public abstract long getViewCount() throws ParsingException;
/**
* The Amount of likes a video/audio stream got.
* If the current stream has no likes or its not available simply return -1
* @return the amount of likes the stream got
* @throws ParsingException
*/
public abstract long getLikeCount() throws ParsingException;
/**
* The Amount of dislikes a video/audio stream got.
* If the current stream has no dislikes or its not available simply return -1
* @return the amount of likes the stream got
* @throws ParsingException
*/
public abstract long getDislikeCount() throws ParsingException;
/**
* The Url to the page of the creator/uploader of the stream. This must not be a homepage,
* but the page offered by the service the extractor handles. This url will be handled by the
* <a href="https://teamnewpipe.github.io/documentation/03_Implement_a_service/#channel">ChannelExtractor</a>,
* so be sure to implement that one before you return a value here, otherwise NewPipe will crash if one selects
* this url.
* @return the url to the page of the creator/uploader of the stream or an empty String
* @throws ParsingException
*/
@Nonnull
public abstract String getUploaderUrl() throws ParsingException;
/**
* The name of the creator/uploader of the stream.
* If the name is not available you can simply return an empty string.
* @return the name of the creator/uploader of the stream or an empty String
* @throws ParsingException
*/
@Nonnull
public abstract String getUploaderName() throws ParsingException;
/**
* The url to the image file/profile picture/avatar of the creator/uploader of the stream.
* If the url is not available you can return an empty String.
* @return The url of the image file of the uploader or an empty String
* @throws ParsingException
*/
@Nonnull
public abstract String getUploaderAvatarUrl() throws ParsingException;
/**
* Get the dash mpd url. If you don't know what a dash MPD is you can read about it
* <a href="https://www.brendanlong.com/the-structure-of-an-mpeg-dash-mpd.html">here</a>.
* @return the url as a string or an empty string
* @throws ParsingException if an error occurs while reading
*/
@Nonnull public abstract String getDashMpdUrl() throws ParsingException;
/**
* I am not sure if this is in use, and how this is used. However the frontend is missing support
* for HLS streams. Prove me if I am wrong. Please open an
* <a href="https://github.com/teamnewpipe/newpipe/issues">issue</a>,
* or fix this description if you know whats up with this.
* @return The Url to the hls stream.
* @throws ParsingException
*/
@Nonnull public abstract String getHlsUrl() throws ParsingException;
/**
* This should return a list of available
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/stream/AudioStream.html">AudioStream</a>s
* You can also return null or an empty list, however be aware that if you don't return anything
* in getVideoStreams(), getVideoOnlyStreams() and getDashMpdUrl() either the Collector will handle this as
* a failed extraction procedure.
* @return a list of audio only streams in the format of AudioStream
* @throws IOException
* @throws ExtractionException
*/
public abstract List<AudioStream> getAudioStreams() throws IOException, ExtractionException;
/**
* This should return a list of available
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/stream/VideoStream.html">VideoStream</a>s
* Be aware this is the list of video streams which do contain an audio stream.
* You can also return null or an empty list, however be aware that if you don't return anything
* in getAudioStreams(), getVideoOnlyStreams() and getDashMpdUrl() either the Collector will handle this as
* a failed extraction procedure.
* @return a list of combined video and streams in the format of AudioStream
* @throws IOException
* @throws ExtractionException
*/
public abstract List<VideoStream> getVideoStreams() throws IOException, ExtractionException;
/**
* This should return a list of available
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/stream/VideoStream.html">VideoStream</a>s.
* Be aware this is the list of video streams which do NOT contain an audio stream.
* You can also return null or an empty list, however be aware that if you don't return anything
* in getAudioStreams(), getVideoStreams() and getDashMpdUrl() either the Collector will handle this as
* a failed extraction procedure.
* @return a list of video and streams in the format of AudioStream
* @throws IOException
* @throws ExtractionException
*/
public abstract List<VideoStream> getVideoOnlyStreams() throws IOException, ExtractionException;
/**
* This will return a list of available
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/stream/Subtitles.html">Subtitles</a>s.
* If no subtitles are available an empty list can returned.
* @return a list of available subtitles or an empty list
* @throws IOException
* @throws ExtractionException
*/
@Nonnull
public abstract List<SubtitlesStream> getSubtitlesDefault() throws IOException, ExtractionException;
/**
* This will return a list of available
* <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/org/schabi/newpipe/extractor/stream/Subtitles.html">Subtitles</a>s.
* given by a specific type.
* If no subtitles in that specific format are available an empty list can returned.
* @param format the media format by which the subtitles should be filtered
* @return a list of available subtitles or an empty list
* @throws IOException
* @throws ExtractionException
*/
@Nonnull
public abstract List<SubtitlesStream> getSubtitles(MediaFormat format) throws IOException, ExtractionException;
/**
* Get the <a href="https://teamnewpipe.github.io/NewPipeExtractor/javadoc/">StreamType</a>.
* @return the type of the stream
* @throws ParsingException
*/
public abstract StreamType getStreamType() throws ParsingException;
/**
* should return the url of the next stream. NewPipe will automatically play
* the next stream if the user wants that.
* If the next stream is is not available simply return null
* @return the InfoItem of the next stream
* @throws IOException
* @throws ExtractionException
*/
public abstract StreamInfoItem getNextStream() throws IOException, ExtractionException;
/**
* Should return a list of streams related to the current handled. Many services show suggested
* streams. If you don't like suggested streams you should implement them anyway since they can
* be disabled by the user later in the frontend.
* This list MUST NOT contain the next available video as this should be return through getNextStream()
* If is is not available simply return null
* @return a list of InfoItems showing the related videos/streams
* @throws IOException
* @throws ExtractionException
*/
public abstract StreamInfoItemsCollector getRelatedStreams() throws IOException, ExtractionException;
/**
* Should analyse the webpage's document and extracts any error message there might be. (e.g. GEMA block)
*
* @return Error message; null if there is no error message.
*/
public abstract String getErrorMessage();
//////////////////////////////////////////////////////////////////
/// Helper
//////////////////////////////////////////////////////////////////
/**
* Override this function if the format of time stamp in the url is not the same format as that form youtube.
* Honestly I don't even know the time stamp fromat of youtube.
* @param regexPattern
* @return the sime stamp/seek for the video in seconds
* @throws ParsingException
*/
protected long getTimestampSeconds(String regexPattern) throws ParsingException {
String timeStamp;
try {
@ -103,43 +316,6 @@ public abstract class StreamExtractor extends Extractor {
}
} else {
return 0;
}};
public abstract long getViewCount() throws ParsingException;
public abstract long getLikeCount() throws ParsingException;
public abstract long getDislikeCount() throws ParsingException;
@Nonnull
public abstract String getUploaderUrl() throws ParsingException;
@Nonnull
public abstract String getUploaderName() throws ParsingException;
@Nonnull
public abstract String getUploaderAvatarUrl() throws ParsingException;
/**
* Get the dash mpd url
* @return the url as a string or an empty string
* @throws ParsingException if an error occurs while reading
*/
@Nonnull public abstract String getDashMpdUrl() throws ParsingException;
@Nonnull public abstract String getHlsUrl() throws ParsingException;
public abstract List<AudioStream> getAudioStreams() throws IOException, ExtractionException;
public abstract List<VideoStream> getVideoStreams() throws IOException, ExtractionException;
public abstract List<VideoStream> getVideoOnlyStreams() throws IOException, ExtractionException;
@Nonnull
public abstract List<Subtitles> getSubtitlesDefault() throws IOException, ExtractionException;
@Nonnull
public abstract List<Subtitles> getSubtitles(SubtitlesFormat format) throws IOException, ExtractionException;
public abstract StreamType getStreamType() throws ParsingException;
public abstract StreamInfoItem getNextVideo() throws IOException, ExtractionException;
public abstract StreamInfoItemsCollector getRelatedVideos() throws IOException, ExtractionException;
/**
* Analyses the webpage's document and extracts any error message there might be.
*
* @return Error message; null if there is no error message.
*/
public abstract String getErrorMessage();
}
}
}

View file

@ -8,13 +8,10 @@ import org.schabi.newpipe.extractor.Info;
import org.schabi.newpipe.extractor.InfoItem;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.StreamingService;
import org.schabi.newpipe.extractor.Subtitles;
import org.schabi.newpipe.extractor.comments.CommentsInfo;
import org.schabi.newpipe.extractor.exceptions.ContentNotAvailableException;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.utils.DashMpdParser;
import org.schabi.newpipe.extractor.utils.ExtractorHelper;
import org.schabi.newpipe.extractor.utils.Localization;
/*
* Created by Christian Schabesberger on 26.08.15.
@ -163,6 +160,9 @@ public class StreamInfo extends Info {
streamInfo.getVideoOnlyStreams().addAll(result.getVideoOnlyStreams());
streamInfo.getAudioStreams().addAll(result.getAudioStreams());
streamInfo.getVideoStreams().addAll(result.getVideoStreams());
streamInfo.segmentedVideoOnlyStreams = result.getSegmentedVideoOnlyStreams();
streamInfo.segmentedAudioStreams = result.getSegmentedAudioStreams();
streamInfo.segmentedVideoStreams = result.getSegmentedVideoStreams();
} catch (Exception e) {
// Sometimes we receive 403 (forbidden) error when trying to download the
// manifest (similar to what happens with youtube-dl),
@ -254,7 +254,7 @@ public class StreamInfo extends Info {
streamInfo.addError(e);
}
try {
streamInfo.setNextVideo(extractor.getNextVideo());
streamInfo.setNextVideo(extractor.getNextStream());
} catch (Exception e) {
streamInfo.addError(e);
}
@ -289,12 +289,17 @@ public class StreamInfo extends Info {
private List<VideoStream> videoOnlyStreams;
private String dashMpdUrl;
private List<VideoStream> segmentedVideoStreams;
private List<AudioStream> segmentedAudioStreams;
private List<VideoStream> segmentedVideoOnlyStreams;
private String hlsUrl;
private StreamInfoItem nextVideo;
private List<InfoItem> relatedStreams;
private long startPosition = 0;
private List<Subtitles> subtitles;
private List<SubtitlesStream> subtitles;
/**
* Get the stream type
@ -449,6 +454,30 @@ public class StreamInfo extends Info {
this.dashMpdUrl = dashMpdUrl;
}
public List<VideoStream> getSegmentedVideoStreams() {
return segmentedVideoStreams;
}
public void setSegmentedVideoStreams(List<VideoStream> segmentedVideoStreams) {
this.segmentedVideoStreams = segmentedVideoStreams;
}
public List<AudioStream> getSegmentedAudioStreams() {
return segmentedAudioStreams;
}
public void setSegmentedAudioStreams(List<AudioStream> segmentedAudioStreams) {
this.segmentedAudioStreams = segmentedAudioStreams;
}
public List<VideoStream> getSegmentedVideoOnlyStreams() {
return segmentedVideoOnlyStreams;
}
public void setSegmentedVideoOnlyStreams(List<VideoStream> segmentedVideoOnlyStreams) {
this.segmentedVideoOnlyStreams = segmentedVideoOnlyStreams;
}
public String getHlsUrl() {
return hlsUrl;
}
@ -481,11 +510,11 @@ public class StreamInfo extends Info {
this.startPosition = startPosition;
}
public List<Subtitles> getSubtitles() {
public List<SubtitlesStream> getSubtitles() {
return subtitles;
}
public void setSubtitles(List<Subtitles> subtitles) {
public void setSubtitles(List<SubtitlesStream> subtitles) {
this.subtitles = subtitles;
}

View file

@ -1,25 +0,0 @@
package org.schabi.newpipe.extractor.stream;
public enum SubtitlesFormat {
// YouTube subtitles formats
// TRANSCRIPT(3) is default YT format based on TTML,
// but unlike VTT or TTML, it is NOT W3 standard
// TRANSCRIPT subtitles are NOT supported by ExoPlayer, only VTT and TTML
VTT (0x0, "vtt"),
TTML (0x1, "ttml"),
TRANSCRIPT1 (0x2, "srv1"),
TRANSCRIPT2 (0x3, "srv2"),
TRANSCRIPT3 (0x4, "srv3");
private final int id;
private final String extension;
SubtitlesFormat(int id, String extension) {
this.id = id;
this.extension = extension;
}
public String getExtension() {
return extension;
}
}

View file

@ -0,0 +1,73 @@
package org.schabi.newpipe.extractor.stream;
import org.schabi.newpipe.extractor.MediaFormat;
import java.io.Serializable;
import java.util.Locale;
public class SubtitlesStream extends Stream implements Serializable {
private final MediaFormat format;
private final Locale locale;
private final String url;
private final boolean autoGenerated;
private final String code;
public SubtitlesStream(MediaFormat format, String languageCode, String url, boolean autoGenerated) {
super(url, format);
/*
* Locale.forLanguageTag only for API >= 21
* Locale.Builder only for API >= 21
* Country codes doesn't work well without
*/
final String[] splits = languageCode.split("-");
switch (splits.length) {
default:
this.locale = new Locale(splits[0]);
break;
case 3:
this.locale = new Locale(splits[0], splits[1], splits[2]);// complex variants doesn't work!
break;
case 2:
this.locale = new Locale(splits[0], splits[1]);
break;
}
this.code = languageCode;
this.format = format;
this.url = url;
this.autoGenerated = autoGenerated;
}
public String getExtension() {
return format.suffix;
}
public String getURL() {
return url;
}
public boolean isAutoGenerated() {
return autoGenerated;
}
@Override
public boolean equalStats(Stream cmp) {
return super.equalStats(cmp)&&
cmp instanceof SubtitlesStream &&
code.equals(((SubtitlesStream) cmp).code) &&
autoGenerated == ((SubtitlesStream) cmp).autoGenerated;
}
public String getDisplayLanguageName() {
return locale.getDisplayName(locale);
}
public String getLanguageTag() {
return code;
}
public Locale getLocale() {
return locale;
}
}

View file

@ -59,10 +59,23 @@ public class DashMpdParser {
private final List<AudioStream> audioStreams;
private final List<VideoStream> videoOnlyStreams;
public ParserResult(List<VideoStream> videoStreams, List<AudioStream> audioStreams, List<VideoStream> videoOnlyStreams) {
private final List<VideoStream> segmentedVideoStreams;
private final List<AudioStream> segmentedAudioStreams;
private final List<VideoStream> segmentedVideoOnlyStreams;
public ParserResult(List<VideoStream> videoStreams,
List<AudioStream> audioStreams,
List<VideoStream> videoOnlyStreams,
List<VideoStream> segmentedVideoStreams,
List<AudioStream> segmentedAudioStreams,
List<VideoStream> segmentedVideoOnlyStreams) {
this.videoStreams = videoStreams;
this.audioStreams = audioStreams;
this.videoOnlyStreams = videoOnlyStreams;
this.segmentedVideoStreams = segmentedVideoStreams;
this.segmentedAudioStreams = segmentedAudioStreams;
this.segmentedVideoOnlyStreams = segmentedVideoOnlyStreams;
}
public List<VideoStream> getVideoStreams() {
@ -76,10 +89,22 @@ public class DashMpdParser {
public List<VideoStream> getVideoOnlyStreams() {
return videoOnlyStreams;
}
public List<VideoStream> getSegmentedVideoStreams() {
return segmentedVideoStreams;
}
public List<AudioStream> getSegmentedAudioStreams() {
return segmentedAudioStreams;
}
public List<VideoStream> getSegmentedVideoOnlyStreams() {
return segmentedVideoOnlyStreams;
}
}
/**
* Will try to download (using {@link StreamInfo#dashMpdUrl}) and parse the dash manifest,
* Will try to download (using {@link StreamInfo#getDashMpdUrl()}) and parse the dash manifest,
* then it will search for any stream that the ItagItem has (by the id).
* <p>
* It has video, video only and audio streams and will only add to the list if it don't
@ -90,7 +115,8 @@ public class DashMpdParser {
*
* @param streamInfo where the parsed streams will be added
*/
public static ParserResult getStreams(final StreamInfo streamInfo) throws DashMpdParsingException, ReCaptchaException {
public static ParserResult getStreams(final StreamInfo streamInfo)
throws DashMpdParsingException, ReCaptchaException {
String dashDoc;
Downloader downloader = NewPipe.getDownloader();
try {
@ -113,6 +139,10 @@ public class DashMpdParser {
final List<AudioStream> audioStreams = new ArrayList<>();
final List<VideoStream> videoOnlyStreams = new ArrayList<>();
final List<VideoStream> segmentedVideoStreams = new ArrayList<>();
final List<AudioStream> segmentedAudioStreams = new ArrayList<>();
final List<VideoStream> segmentedVideoOnlyStreams = new ArrayList<>();
for (int i = 0; i < representationList.getLength(); i++) {
final Element representation = (Element) representationList.item(i);
try {
@ -126,34 +156,61 @@ public class DashMpdParser {
// instead we need to add the "media=" value from the <SegementURL/> tags inside the <SegmentList/>
// tag in order to get a full working url. However each of these is just pointing to a part of the
// video, so we can not return a URL with a working stream here.
// We decided not to ignore such streams for the moment.
if (itag != null && segmentationList == null) {
// Instead of putting those streams into the list of regular stream urls wie put them in a
// for example "segmentedVideoStreams" list.
if (itag != null) {
final MediaFormat mediaFormat = MediaFormat.getFromMimeType(mimeType);
if (itag.itagType.equals(ItagItem.ItagType.AUDIO)) {
final AudioStream audioStream = new AudioStream(url, mediaFormat, itag.avgBitrate);
if (!Stream.containSimilarStream(audioStream, streamInfo.getAudioStreams())) {
audioStreams.add(audioStream);
if(segmentationList == null) {
final AudioStream audioStream = new AudioStream(url, mediaFormat, itag.avgBitrate);
if (!Stream.containSimilarStream(audioStream, streamInfo.getAudioStreams())) {
audioStreams.add(audioStream);
}
} else {
segmentedAudioStreams.add(
new AudioStream(id, mediaFormat, itag.avgBitrate));
}
} else {
boolean isVideoOnly = itag.itagType.equals(ItagItem.ItagType.VIDEO_ONLY);
final VideoStream videoStream = new VideoStream(url, mediaFormat, itag.resolutionString, isVideoOnly);
if (isVideoOnly) {
if (!Stream.containSimilarStream(videoStream, streamInfo.getVideoOnlyStreams())) {
streamInfo.getVideoOnlyStreams().add(videoStream);
videoOnlyStreams.add(videoStream);
if(segmentationList == null) {
final VideoStream videoStream = new VideoStream(url,
mediaFormat,
itag.resolutionString,
isVideoOnly);
if (isVideoOnly) {
if (!Stream.containSimilarStream(videoStream, streamInfo.getVideoOnlyStreams())) {
videoOnlyStreams.add(videoStream);
}
} else if (!Stream.containSimilarStream(videoStream, streamInfo.getVideoStreams())) {
videoStreams.add(videoStream);
}
} else {
final VideoStream videoStream = new VideoStream(id,
mediaFormat,
itag.resolutionString,
isVideoOnly);
if(isVideoOnly) {
segmentedVideoOnlyStreams.add(videoStream);
} else {
segmentedVideoStreams.add(videoStream);
}
} else if (!Stream.containSimilarStream(videoStream, streamInfo.getVideoStreams())) {
videoStreams.add(videoStream);
}
}
}
} catch (Exception ignored) {
}
}
return new ParserResult(videoStreams, audioStreams, videoOnlyStreams);
return new ParserResult(
videoStreams,
audioStreams,
videoOnlyStreams,
segmentedVideoStreams,
segmentedAudioStreams,
segmentedVideoOnlyStreams);
} catch (Exception e) {
throw new DashMpdParsingException("Could not parse Dash mpd", e);
}

View file

@ -30,7 +30,7 @@ public class ExtractorHelper {
public static List<InfoItem> getRelatedVideosOrLogError(StreamInfo info, StreamExtractor extractor) {
try {
InfoItemsCollector<? extends InfoItem, ?> collector = extractor.getRelatedVideos();
InfoItemsCollector<? extends InfoItem, ?> collector = extractor.getRelatedStreams();
info.addAllErrors(collector.getErrors());
//noinspection unchecked

View file

@ -101,7 +101,7 @@ public class SoundcloudStreamExtractorDefaultTest {
@Test
public void testGetRelatedVideos() throws ExtractionException, IOException {
StreamInfoItemsCollector relatedVideos = extractor.getRelatedVideos();
StreamInfoItemsCollector relatedVideos = extractor.getRelatedStreams();
assertFalse(relatedVideos.getItems().isEmpty());
assertTrue(relatedVideos.getErrors().isEmpty());
}

View file

@ -219,7 +219,7 @@ public class YoutubePlaylistExtractorTest {
@Test
public void testUploaderName() throws Exception {
assertEquals("Tomas Nilsson", extractor.getUploaderName());
assertEquals("Tomas Nilsson TOMPA571", extractor.getUploaderName());
}
@Test

View file

@ -4,13 +4,13 @@ import org.junit.BeforeClass;
import org.junit.Ignore;
import org.junit.Test;
import org.schabi.newpipe.Downloader;
import org.schabi.newpipe.extractor.MediaFormat;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeStreamExtractor;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeStreamLinkHandlerFactory;
import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.stream.SubtitlesFormat;
import org.schabi.newpipe.extractor.stream.VideoStream;
import org.schabi.newpipe.extractor.utils.Localization;
@ -131,6 +131,6 @@ public class YoutubeStreamExtractorAgeRestrictedTest {
@Test
public void testGetSubtitlesList() throws IOException, ExtractionException {
// Video (/view?v=YQHsXMglC9A) set in the setUp() method has no captions => null
assertTrue(extractor.getSubtitles(SubtitlesFormat.TTML).isEmpty());
assertTrue(extractor.getSubtitles(MediaFormat.TTML).isEmpty());
}
}

View file

@ -4,13 +4,13 @@ import org.junit.BeforeClass;
import org.junit.Ignore;
import org.junit.Test;
import org.schabi.newpipe.Downloader;
import org.schabi.newpipe.extractor.MediaFormat;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeStreamExtractor;
import org.schabi.newpipe.extractor.services.youtube.linkHandler.YoutubeStreamLinkHandlerFactory;
import org.schabi.newpipe.extractor.stream.StreamExtractor;
import org.schabi.newpipe.extractor.stream.SubtitlesFormat;
import org.schabi.newpipe.extractor.stream.VideoStream;
import org.schabi.newpipe.extractor.utils.Localization;
@ -124,6 +124,6 @@ public class YoutubeStreamExtractorControversialTest {
@Test
public void testGetSubtitlesList() throws IOException, ExtractionException {
// Video (/view?v=YQHsXMglC9A) set in the setUp() method has no captions => null
assertTrue(!extractor.getSubtitles(SubtitlesFormat.TTML).isEmpty());
assertTrue(!extractor.getSubtitles(MediaFormat.TTML).isEmpty());
}
}

View file

@ -47,15 +47,21 @@ public class YoutubeStreamExtractorDASHTest {
@Test
public void testGetDashMpd() {
System.out.println(info.getDashMpdUrl());
assertTrue(info.getDashMpdUrl(),
info.getDashMpdUrl() != null && !info.getDashMpdUrl().isEmpty());
}
@Test
public void testDashMpdParser() {
public void testRegularStreams() {
assertEquals(0, info.getAudioStreams().size());
assertEquals(0, info.getVideoOnlyStreams().size());
assertEquals(4, info.getVideoStreams().size());
}
@Test
public void testSegmentedStreams() {
assertEquals(2, info.getSegmentedAudioStreams().size());
assertEquals(3, info.getSegmentedVideoOnlyStreams().size());
assertEquals(0, info.getSegmentedVideoStreams().size());
}
}

View file

@ -3,12 +3,12 @@ package org.schabi.newpipe.extractor.services.youtube;
import org.junit.BeforeClass;
import org.junit.Test;
import org.schabi.newpipe.Downloader;
import org.schabi.newpipe.extractor.MediaFormat;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import org.schabi.newpipe.extractor.services.youtube.extractors.YoutubeStreamExtractor;
import org.schabi.newpipe.extractor.stream.*;
import org.schabi.newpipe.extractor.utils.DashMpdParser;
import org.schabi.newpipe.extractor.utils.Localization;
import org.schabi.newpipe.extractor.utils.Utils;
@ -17,7 +17,6 @@ import java.io.IOException;
import static org.junit.Assert.*;
import static org.schabi.newpipe.extractor.ExtractorAsserts.assertIsSecureUrl;
import static org.schabi.newpipe.extractor.ServiceList.YouTube;
import static org.schabi.newpipe.extractor.services.youtube.YoutubeTrendingExtractorTest.extractor;
/*
* Created by Christian Schabesberger on 30.12.15.
@ -151,7 +150,7 @@ public class YoutubeStreamExtractorDefaultTest {
@Test
public void testGetRelatedVideos() throws ExtractionException, IOException {
StreamInfoItemsCollector relatedVideos = extractor.getRelatedVideos();
StreamInfoItemsCollector relatedVideos = extractor.getRelatedStreams();
Utils.printErrors(relatedVideos.getErrors());
assertFalse(relatedVideos.getItems().isEmpty());
assertTrue(relatedVideos.getErrors().isEmpty());
@ -166,7 +165,7 @@ public class YoutubeStreamExtractorDefaultTest {
@Test
public void testGetSubtitlesList() throws IOException, ExtractionException {
// Video (/view?v=YQHsXMglC9A) set in the setUp() method has no captions => null
assertTrue(extractor.getSubtitles(SubtitlesFormat.TTML).isEmpty());
assertTrue(extractor.getSubtitles(MediaFormat.TTML).isEmpty());
}
}

View file

@ -28,7 +28,7 @@ public class YoutubeSearchCountTest {
public void testViewCount() {
ChannelInfoItem ci = (ChannelInfoItem) itemsPage.getItems().get(0);
assertTrue("Count does not fit: " + Long.toString(ci.getSubscriberCount()),
65043316 < ci.getSubscriberCount() && ci.getSubscriberCount() < 68043316);
69043316 < ci.getSubscriberCount() && ci.getSubscriberCount() < 73043316);
}
}
}

View file

@ -45,12 +45,12 @@ public class YoutubeSearchExtractorChannelOnlyTest extends YoutubeSearchExtracto
}
assertFalse("First and second page are equal", equals);
assertEquals("https://www.youtube.com/results?q=pewdiepie&sp=EgIQAlAU&page=3&gl=GB", secondPage.getNextPageUrl());
assertEquals("https://www.youtube.com/results?q=pewdiepie&sp=EgIQAlAU&gl=GB&page=3", secondPage.getNextPageUrl());
}
@Test
public void testGetSecondPageUrl() throws Exception {
assertEquals("https://www.youtube.com/results?q=pewdiepie&sp=EgIQAlAU&page=2&gl=GB", extractor.getNextPageUrl());
assertEquals("https://www.youtube.com/results?q=pewdiepie&sp=EgIQAlAU&gl=GB&page=2", extractor.getNextPageUrl());
}
@Test

View file

@ -49,18 +49,22 @@ public class YoutubeSearchExtractorDefaultTest extends YoutubeSearchExtractorBas
itemsPage = extractor.getInitialPage();
}
@Test
public void testGetUrl() throws Exception {
assertEquals("https://www.youtube.com/results?q=pewdiepie&gl=GB", extractor.getUrl());
}
@Test
public void testGetSecondPageUrl() throws Exception {
assertEquals("https://www.youtube.com/results?q=pewdiepie&page=2&gl=GB", extractor.getNextPageUrl());
assertEquals("https://www.youtube.com/results?q=pewdiepie&gl=GB&page=2", extractor.getNextPageUrl());
}
@Test
public void testResultList_FirstElement() {
InfoItem firstInfoItem = itemsPage.getItems().get(1);
// THe channel should be the first item
// The channel should be the first item
assertTrue(firstInfoItem instanceof ChannelInfoItem);
assertEquals("name", "PewDiePie", firstInfoItem.getName());
assertEquals("url","https://www.youtube.com/user/PewDiePie", firstInfoItem.getUrl());
@ -96,7 +100,7 @@ public class YoutubeSearchExtractorDefaultTest extends YoutubeSearchExtractorBas
}
assertFalse("First and second page are equal", equals);
assertEquals("https://www.youtube.com/results?q=pewdiepie&page=3&gl=GB", secondPage.getNextPageUrl());
assertEquals("https://www.youtube.com/results?q=pewdiepie&gl=GB&page=3", secondPage.getNextPageUrl());
}
@Test