Merge branch 'master' of https://github.com/ram-on/extractor into fix
This commit is contained in:
commit
ab530381cf
3 changed files with 49 additions and 14 deletions
|
@ -260,7 +260,7 @@ public class YoutubeStreamExtractor extends StreamExtractor {
|
||||||
Parser.matchGroup1("ytplayer.config\\s*=\\s*(\\{.*?\\});", pageContent);
|
Parser.matchGroup1("ytplayer.config\\s*=\\s*(\\{.*?\\});", pageContent);
|
||||||
return new JSONObject(ytPlayerConfigRaw);
|
return new JSONObject(ytPlayerConfigRaw);
|
||||||
} catch (Parser.RegexException e) {
|
} catch (Parser.RegexException e) {
|
||||||
String errorReason = findErrorReason(doc);
|
String errorReason = getErrorMessage();
|
||||||
switch(errorReason) {
|
switch(errorReason) {
|
||||||
case "GEMA":
|
case "GEMA":
|
||||||
throw new GemaException(errorReason);
|
throw new GemaException(errorReason);
|
||||||
|
@ -948,15 +948,28 @@ public class YoutubeStreamExtractor extends StreamExtractor {
|
||||||
return result == null ? "" : result.toString();
|
return result == null ? "" : result.toString();
|
||||||
}
|
}
|
||||||
|
|
||||||
private String findErrorReason(Document doc) {
|
|
||||||
String errorMessage = doc.select("h1[id=\"unavailable-message\"]").first().text();
|
/**
|
||||||
if(errorMessage.contains("GEMA")) {
|
* {@inheritDoc}
|
||||||
|
*/
|
||||||
|
public String getErrorMessage() {
|
||||||
|
String errorMessage = doc.select("h1[id=\"unavailable-message\"]").first().text();
|
||||||
|
StringBuilder errorReason;
|
||||||
|
|
||||||
|
if (errorMessage == null || errorMessage.isEmpty()) {
|
||||||
|
errorReason = null;
|
||||||
|
} else if(errorMessage.contains("GEMA")) {
|
||||||
// Gema sometimes blocks youtube music content in germany:
|
// Gema sometimes blocks youtube music content in germany:
|
||||||
// https://www.gema.de/en/
|
// https://www.gema.de/en/
|
||||||
// Detailed description:
|
// Detailed description:
|
||||||
// https://en.wikipedia.org/wiki/GEMA_%28German_organization%29
|
// https://en.wikipedia.org/wiki/GEMA_%28German_organization%29
|
||||||
return "GEMA";
|
errorReason = new StringBuilder("GEMA");
|
||||||
|
} else {
|
||||||
|
errorReason = new StringBuilder(errorMessage);
|
||||||
|
errorReason.append(" ");
|
||||||
|
errorReason.append(doc.select("[id=\"unavailable-submessage\"]").first().text());
|
||||||
}
|
}
|
||||||
return "";
|
|
||||||
|
return errorReason != null ? errorReason.toString() : null;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -49,7 +49,7 @@ public abstract class StreamExtractor {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
public class ContentNotAvailableException extends ParsingException {
|
public static class ContentNotAvailableException extends ParsingException {
|
||||||
public ContentNotAvailableException(String message) {
|
public ContentNotAvailableException(String message) {
|
||||||
super(message);
|
super(message);
|
||||||
}
|
}
|
||||||
|
@ -101,4 +101,11 @@ public abstract class StreamExtractor {
|
||||||
public int getServiceId() {
|
public int getServiceId() {
|
||||||
return serviceId;
|
return serviceId;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* 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();
|
||||||
}
|
}
|
||||||
|
|
|
@ -74,19 +74,34 @@ public class StreamInfo extends AbstractStreamInfo {
|
||||||
/**Fills out the video info fields which are common to all services.
|
/**Fills out the video info fields which are common to all services.
|
||||||
* Probably needs to be overridden by subclasses*/
|
* Probably needs to be overridden by subclasses*/
|
||||||
public static StreamInfo getVideoInfo(StreamExtractor extractor)
|
public static StreamInfo getVideoInfo(StreamExtractor extractor)
|
||||||
throws ExtractionException, IOException {
|
throws ExtractionException, StreamExtractor.ContentNotAvailableException {
|
||||||
StreamInfo streamInfo = new StreamInfo();
|
StreamInfo streamInfo = new StreamInfo();
|
||||||
|
|
||||||
streamInfo = extractImportantData(streamInfo, extractor);
|
try {
|
||||||
streamInfo = extractStreams(streamInfo, extractor);
|
streamInfo = extractImportantData(streamInfo, extractor);
|
||||||
streamInfo = extractOptionalData(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;
|
return streamInfo;
|
||||||
}
|
}
|
||||||
|
|
||||||
private static StreamInfo extractImportantData(
|
private static StreamInfo extractImportantData(
|
||||||
StreamInfo streamInfo, StreamExtractor extractor)
|
StreamInfo streamInfo, StreamExtractor extractor)
|
||||||
throws ExtractionException, IOException {
|
throws ExtractionException {
|
||||||
/* ---- important data, withoug the video can't be displayed goes here: ---- */
|
/* ---- 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.
|
// if one of these is not available an exception is meant to be thrown directly into the frontend.
|
||||||
|
|
||||||
|
@ -104,7 +119,7 @@ public class StreamInfo extends AbstractStreamInfo {
|
||||||
|| (streamInfo.id == null || streamInfo.id.isEmpty())
|
|| (streamInfo.id == null || streamInfo.id.isEmpty())
|
||||||
|| (streamInfo.title == null /* streamInfo.title can be empty of course */)
|
|| (streamInfo.title == null /* streamInfo.title can be empty of course */)
|
||||||
|| (streamInfo.age_limit == -1)) {
|
|| (streamInfo.age_limit == -1)) {
|
||||||
throw new ExtractionException("Some importand stream information was not given.");
|
throw new ExtractionException("Some important stream information was not given.");
|
||||||
}
|
}
|
||||||
|
|
||||||
return streamInfo;
|
return streamInfo;
|
||||||
|
@ -112,7 +127,7 @@ public class StreamInfo extends AbstractStreamInfo {
|
||||||
|
|
||||||
private static StreamInfo extractStreams(
|
private static StreamInfo extractStreams(
|
||||||
StreamInfo streamInfo, StreamExtractor extractor)
|
StreamInfo streamInfo, StreamExtractor extractor)
|
||||||
throws ExtractionException, IOException {
|
throws ExtractionException {
|
||||||
/* ---- stream extraction goes here ---- */
|
/* ---- stream extraction goes here ---- */
|
||||||
// At least one type of stream has to be available,
|
// At least one type of stream has to be available,
|
||||||
// otherwise an exception will be thrown directly into the frontend.
|
// otherwise an exception will be thrown directly into the frontend.
|
||||||
|
|
Loading…
Reference in a new issue