Refactor extractor

- Refactor info classes and extractors
- Reformat and fix indentation
- Organize packages and classes
- Rename variables/methods and fix regex
- Change the capitalization
- Add methods to playlist extractor
This commit is contained in:
Mauricio Colli
2017-06-29 15:12:55 -03:00
parent 7581c1200b
commit 21e542e7d2
53 changed files with 1043 additions and 902 deletions

View File

@@ -0,0 +1,41 @@
package org.schabi.newpipe.extractor.stream;
/*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* AbstractStreamInfo.java is part of NewPipe.
*
* NewPipe is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* NewPipe is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with NewPipe. If not, see <http://www.gnu.org/licenses/>.
*/
import org.schabi.newpipe.extractor.Info;
/**
* Common properties between StreamInfo and StreamInfoItem.
*/
public abstract class AbstractStreamInfo extends Info {
public enum StreamType {
NONE, // placeholder to check if stream type was checked or not
VIDEO_STREAM,
AUDIO_STREAM,
LIVE_STREAM,
AUDIO_LIVE_STREAM,
FILE
}
public StreamType stream_type;
public String uploader = "";
public String thumbnail_url = "";
public String upload_date = "";
public long view_count = -1;
}

52
stream/AudioStream.java Normal file
View File

@@ -0,0 +1,52 @@
package org.schabi.newpipe.extractor.stream;
import java.io.Serializable;
/*
* Created by Christian Schabesberger on 04.03.16.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* AudioStream.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 AudioStream implements Serializable {
public String url = "";
public int format = -1;
public int bandwidth = -1;
public int sampling_rate = -1;
public int avgBitrate = -1;
public AudioStream(String url, int format, int avgBitrate, int bandwidth, int samplingRate) {
this.url = url;
this.format = format;
this.avgBitrate = avgBitrate;
this.bandwidth = bandwidth;
this.sampling_rate = samplingRate;
}
// reveals whether two streams are the same, but have different urls
public boolean equalStats(AudioStream cmp) {
return format == cmp.format
&& bandwidth == cmp.bandwidth
&& sampling_rate == cmp.sampling_rate
&& avgBitrate == cmp.avgBitrate;
}
// reveals whether two streams are equal
public boolean equals(AudioStream cmp) {
return cmp != null && equalStats(cmp) && url.equals(cmp.url);
}
}

View File

@@ -0,0 +1,77 @@
package org.schabi.newpipe.extractor.stream;
/*
* Created by Christian Schabesberger on 10.08.15.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamExtractor.java is part of NewPipe.
*
* NewPipe is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* NewPipe is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with NewPipe. If not, see <http://www.gnu.org/licenses/>.
*/
import org.schabi.newpipe.extractor.Extractor;
import org.schabi.newpipe.extractor.UrlIdHandler;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
import java.util.List;
/**
* Scrapes information from a video streaming service (eg, YouTube).
*/
public abstract class StreamExtractor extends Extractor {
public static class ContentNotAvailableException extends ParsingException {
public ContentNotAvailableException(String message) {
super(message);
}
public ContentNotAvailableException(String message, Throwable cause) {
super(message, cause);
}
}
public StreamExtractor(UrlIdHandler urlIdHandler, String url, int serviceId) {
super(urlIdHandler, serviceId, url);
}
public abstract int getTimeStamp() throws ParsingException;
public abstract String getTitle() throws ParsingException;
public abstract String getDescription() throws ParsingException;
public abstract String getUploader() throws ParsingException;
public abstract String getChannelUrl() throws ParsingException;
public abstract int getLength() throws ParsingException;
public abstract long getViewCount() throws ParsingException;
public abstract String getUploadDate() throws ParsingException;
public abstract String getThumbnailUrl() throws ParsingException;
public abstract String getUploaderThumbnailUrl() throws ParsingException;
public abstract List<AudioStream> getAudioStreams() throws ParsingException;
public abstract List<VideoStream> getVideoStreams() throws ParsingException;
public abstract List<VideoStream> getVideoOnlyStreams() throws ParsingException;
public abstract String getDashMpdUrl() throws ParsingException;
public abstract int getAgeLimit() throws ParsingException;
public abstract String getAverageRating() throws ParsingException;
public abstract int getLikeCount() throws ParsingException;
public abstract int getDislikeCount() throws ParsingException;
public abstract StreamInfoItemExtractor getNextVideo() throws ParsingException;
public abstract StreamInfoItemCollector getRelatedVideos() throws ParsingException;
public abstract String getPageUrl();
public abstract StreamInfo.StreamType getStreamType() throws ParsingException;
/**
* 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();
}

307
stream/StreamInfo.java Normal file
View File

@@ -0,0 +1,307 @@
package org.schabi.newpipe.extractor.stream;
import org.schabi.newpipe.extractor.InfoItem;
import org.schabi.newpipe.extractor.UrlIdHandler;
import org.schabi.newpipe.extractor.exceptions.ExtractionException;
import org.schabi.newpipe.extractor.utils.DashMpdParser;
import java.util.List;
import java.util.Vector;
/*
* Created by Christian Schabesberger on 26.08.15.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamInfo.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/>.
*/
/**
* Info object for opened videos, ie the video ready to play.
*/
@SuppressWarnings("ALL")
public class StreamInfo extends AbstractStreamInfo {
public static class StreamExctractException extends ExtractionException {
StreamExctractException(String message) {
super(message);
}
}
public StreamInfo() {
}
/**
* Creates a new StreamInfo object from an existing AbstractVideoInfo.
* All the shared properties are copied to the new StreamInfo.
*/
@SuppressWarnings("WeakerAccess")
public StreamInfo(AbstractStreamInfo avi) {
this.id = avi.id;
this.url = avi.url;
this.name = avi.name;
this.uploader = avi.uploader;
this.thumbnail_url = avi.thumbnail_url;
this.upload_date = avi.upload_date;
this.upload_date = avi.upload_date;
this.view_count = avi.view_count;
//todo: better than this
if (avi instanceof StreamInfoItem) {
//shitty String to convert code
/*
String dur = ((StreamInfoItem)avi).duration;
int minutes = Integer.parseInt(dur.substring(0, dur.indexOf(":")));
int seconds = Integer.parseInt(dur.substring(dur.indexOf(":")+1, dur.length()));
*/
this.duration = ((StreamInfoItem) avi).duration;
}
}
public void addException(Exception e) {
errors.add(e);
}
/**
* Fills out the video info fields which are common to all services.
* Probably needs to be overridden by subclasses
*/
public static StreamInfo getVideoInfo(StreamExtractor extractor)
throws ExtractionException, StreamExtractor.ContentNotAvailableException {
StreamInfo streamInfo = new StreamInfo();
try {
streamInfo = extractImportantData(streamInfo, extractor);
streamInfo = extractStreams(streamInfo, extractor);
streamInfo = extractOptionalData(streamInfo, extractor);
} catch (ExtractionException e) {
// Currently YouTube does not distinguish between age restricted videos and videos blocked
// by country. This means that during the initialisation of the extractor, the extractor
// will assume that a video is age restricted while in reality it it blocked by country.
//
// We will now detect whether the video is blocked by country or not.
String errorMsg = extractor.getErrorMessage();
if (errorMsg != null) {
throw new StreamExtractor.ContentNotAvailableException(errorMsg);
} else {
throw e;
}
}
return streamInfo;
}
private static StreamInfo extractImportantData(
StreamInfo streamInfo, StreamExtractor extractor)
throws ExtractionException {
/* ---- important data, withoug the video can't be displayed goes here: ---- */
// if one of these is not available an exception is meant to be thrown directly into the frontend.
UrlIdHandler uiconv = extractor.getUrlIdHandler();
streamInfo.service_id = extractor.getServiceId();
streamInfo.url = extractor.getPageUrl();
streamInfo.stream_type = extractor.getStreamType();
streamInfo.id = uiconv.getId(extractor.getPageUrl());
streamInfo.name = extractor.getTitle();
streamInfo.age_limit = extractor.getAgeLimit();
if ((streamInfo.stream_type == StreamType.NONE)
|| (streamInfo.url == null || streamInfo.url.isEmpty())
|| (streamInfo.id == null || streamInfo.id.isEmpty())
|| (streamInfo.name == null /* streamInfo.title can be empty of course */)
|| (streamInfo.age_limit == -1)) {
throw new ExtractionException("Some important stream information was not given.");
}
return streamInfo;
}
private static StreamInfo extractStreams(
StreamInfo streamInfo, StreamExtractor extractor)
throws ExtractionException {
/* ---- stream extraction goes here ---- */
// At least one type of stream has to be available,
// otherwise an exception will be thrown directly into the frontend.
try {
streamInfo.dashMpdUrl = extractor.getDashMpdUrl();
} catch (Exception e) {
streamInfo.addException(new ExtractionException("Couldn't get Dash manifest", e));
}
/* Load and extract audio */
try {
streamInfo.audio_streams = extractor.getAudioStreams();
} catch (Exception e) {
streamInfo.addException(new ExtractionException("Couldn't get audio streams", e));
}
// also try to get streams from the dashMpd
if (streamInfo.dashMpdUrl != null && !streamInfo.dashMpdUrl.isEmpty()) {
if (streamInfo.audio_streams == null) {
streamInfo.audio_streams = new Vector<>();
}
//todo: make this quick and dirty solution a real fallback
// same as the quick and dirty above
try {
streamInfo.audio_streams.addAll(
DashMpdParser.getAudioStreams(streamInfo.dashMpdUrl));
} catch (Exception e) {
streamInfo.addException(
new ExtractionException("Couldn't get audio streams from dash mpd", e));
}
}
/* Extract video stream url*/
try {
streamInfo.video_streams = extractor.getVideoStreams();
} catch (Exception e) {
streamInfo.addException(
new ExtractionException("Couldn't get video streams", e));
}
/* Extract video only stream url*/
try {
streamInfo.video_only_streams = extractor.getVideoOnlyStreams();
} catch (Exception e) {
streamInfo.addException(
new ExtractionException("Couldn't get video only streams", e));
}
// either dash_mpd audio_only or video has to be available, otherwise we didn't get a stream,
// and therefore failed. (Since video_only_streams are just optional they don't caunt).
if ((streamInfo.video_streams == null || streamInfo.video_streams.isEmpty())
&& (streamInfo.audio_streams == null || streamInfo.audio_streams.isEmpty())
&& (streamInfo.dashMpdUrl == null || streamInfo.dashMpdUrl.isEmpty())) {
throw new StreamExctractException(
"Could not get any stream. See error variable to get further details.");
}
return streamInfo;
}
private static StreamInfo extractOptionalData(
StreamInfo streamInfo, StreamExtractor extractor) {
/* ---- optional data goes here: ---- */
// If one of these fails, the frontend needs to handle that they are not available.
// Exceptions are therefore not thrown into the frontend, but stored into the error List,
// so the frontend can afterwards check where errors happened.
try {
streamInfo.thumbnail_url = extractor.getThumbnailUrl();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.duration = extractor.getLength();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.uploader = extractor.getUploader();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.channel_url = extractor.getChannelUrl();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.description = extractor.getDescription();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.view_count = extractor.getViewCount();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.upload_date = extractor.getUploadDate();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.uploader_thumbnail_url = extractor.getUploaderThumbnailUrl();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.start_position = extractor.getTimeStamp();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.average_rating = extractor.getAverageRating();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.like_count = extractor.getLikeCount();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
streamInfo.dislike_count = extractor.getDislikeCount();
} catch (Exception e) {
streamInfo.addException(e);
}
try {
StreamInfoItemCollector c = new StreamInfoItemCollector(
extractor.getUrlIdHandler(), extractor.getServiceId());
StreamInfoItemExtractor nextVideo = extractor.getNextVideo();
c.commit(nextVideo);
if (c.getItemList().size() != 0) {
streamInfo.next_video = (StreamInfoItem) c.getItemList().get(0);
}
streamInfo.errors.addAll(c.getErrors());
} catch (Exception e) {
streamInfo.addException(e);
}
try {
// get related videos
StreamInfoItemCollector c = extractor.getRelatedVideos();
streamInfo.related_streams = c.getItemList();
streamInfo.errors.addAll(c.getErrors());
} catch (Exception e) {
streamInfo.addException(e);
}
return streamInfo;
}
public String uploader_thumbnail_url = "";
public String channel_url = "";
public String description = "";
public List<VideoStream> video_streams = null;
public List<AudioStream> audio_streams = null;
public List<VideoStream> video_only_streams = null;
// video streams provided by the dash mpd do not need to be provided as VideoStream.
// Later on this will also aplly to audio streams. Since dash mpd is standarized,
// crawling such a file is not service dependent. Therefore getting audio only streams by yust
// providing the dash mpd fille will be possible in the future.
public String dashMpdUrl = "";
public int duration = -1;
public int age_limit = -1;
public int like_count = -1;
public int dislike_count = -1;
public String average_rating = "";
public StreamInfoItem next_video = null;
public List<InfoItem> related_streams = null;
//in seconds. some metadata is not passed using a StreamInfo object!
public int start_position = 0;
}

View File

@@ -0,0 +1,42 @@
package org.schabi.newpipe.extractor.stream;
/*
* Created by Christian Schabesberger on 26.08.15.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamInfoItem.java is part of NewPipe.
*
* NewPipe is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* NewPipe is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with NewPipe. If not, see <http://www.gnu.org/licenses/>.
*/
import org.schabi.newpipe.extractor.InfoItem;
/**
* Info object for previews of unopened videos, eg search results, related videos
*/
public class StreamInfoItem extends AbstractStreamInfo implements InfoItem {
public int duration;
public InfoType infoType() {
return InfoType.STREAM;
}
public String getTitle() {
return name;
}
public String getLink() {
return url;
}
}

View File

@@ -0,0 +1,99 @@
package org.schabi.newpipe.extractor.stream;
import org.schabi.newpipe.extractor.InfoItemCollector;
import org.schabi.newpipe.extractor.NewPipe;
import org.schabi.newpipe.extractor.UrlIdHandler;
import org.schabi.newpipe.extractor.exceptions.FoundAdException;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
/*
* Created by Christian Schabesberger on 28.02.16.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamInfoItemCollector.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 StreamInfoItemCollector extends InfoItemCollector {
private UrlIdHandler urlIdHandler;
public StreamInfoItemCollector(UrlIdHandler handler, int serviceId) {
super(serviceId);
urlIdHandler = handler;
}
private UrlIdHandler getUrlIdHandler() {
return urlIdHandler;
}
public StreamInfoItem extract(StreamInfoItemExtractor extractor) throws Exception {
if (extractor.isAd()) {
throw new FoundAdException("Found ad");
}
StreamInfoItem resultItem = new StreamInfoItem();
// important information
resultItem.service_id = getServiceId();
resultItem.url = extractor.getWebPageUrl();
if (getUrlIdHandler() == null) {
throw new ParsingException("Error: UrlIdHandler not set");
} else if (!resultItem.url.isEmpty()) {
resultItem.id = NewPipe.getService(getServiceId())
.getStreamUrlIdHandlerInstance()
.getId(resultItem.url);
}
resultItem.name = extractor.getTitle();
resultItem.stream_type = extractor.getStreamType();
// optional information
try {
resultItem.duration = extractor.getDuration();
} catch (Exception e) {
addError(e);
}
try {
resultItem.uploader = extractor.getUploader();
} catch (Exception e) {
addError(e);
}
try {
resultItem.upload_date = extractor.getUploadDate();
} catch (Exception e) {
addError(e);
}
try {
resultItem.view_count = extractor.getViewCount();
} catch (Exception e) {
addError(e);
}
try {
resultItem.thumbnail_url = extractor.getThumbnailUrl();
} catch (Exception e) {
addError(e);
}
return resultItem;
}
public void commit(StreamInfoItemExtractor extractor) throws ParsingException {
try {
addItem(extract(extractor));
} catch (FoundAdException ae) {
//System.out.println("AD_WARNING: " + ae.getMessage());
} catch (Exception e) {
addError(e);
}
}
}

View File

@@ -0,0 +1,35 @@
package org.schabi.newpipe.extractor.stream;
import org.schabi.newpipe.extractor.exceptions.ParsingException;
/*
* Created by Christian Schabesberger on 28.02.16.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* StreamInfoItemExtractor.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 interface StreamInfoItemExtractor {
AbstractStreamInfo.StreamType getStreamType() throws ParsingException;
String getWebPageUrl() throws ParsingException;
String getTitle() throws ParsingException;
int getDuration() throws ParsingException;
String getUploader() throws ParsingException;
String getUploadDate() throws ParsingException;
long getViewCount() throws ParsingException;
String getThumbnailUrl() throws ParsingException;
boolean isAd() throws ParsingException;
}

52
stream/VideoStream.java Normal file
View File

@@ -0,0 +1,52 @@
package org.schabi.newpipe.extractor.stream;
import java.io.Serializable;
/*
* Created by Christian Schabesberger on 04.03.16.
*
* Copyright (C) Christian Schabesberger 2016 <chris.schabesberger@mailbox.org>
* VideoStream.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 VideoStream implements Serializable {
//url of the stream
public String url = "";
public int format = -1;
public String resolution = "";
public boolean isVideoOnly = false;
public VideoStream(String url, int format, String res) {
this(false, url, format, res);
}
public VideoStream(boolean isVideoOnly, String url, int format, String res) {
this.url = url;
this.format = format;
this.resolution = res;
this.isVideoOnly = isVideoOnly;
}
// reveals whether two streams are the same, but have different urls
public boolean equalStats(VideoStream cmp) {
return format == cmp.format && resolution.equals(cmp.resolution);
}
// reveals whether two streams are equal
public boolean equals(VideoStream cmp) {
return cmp != null && equalStats(cmp) && url.equals(cmp.url);
}
}