Youtube视频下载（Android / Java） [英] Youtube Video Download (Android/Java)
本文介绍了Youtube视频下载（Android / Java）的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
注意：原始问题已删除
这里答案已经过时，没有工作所以我会发布一个新问题并回答我自己
OLDCODE
new YouTubePageStreamUriGetter().execute("https://www.youtube.com/watch?v=4GuqB1BQVr4");
class Meta {
public String num;
public String type;
public String ext;
Meta(String num, String ext, String type) {
this.num = num;
this.ext = ext;
this.type = type;
}
}
class Video {
public String ext = "";
public String type = "";
public String url = "";
Video(String ext, String type, String url) {
this.ext = ext;
this.type = type;
this.url = url;
}
}
public ArrayList<Video> getStreamingUrisFromYouTubePage(String ytUrl)
throws IOException {
if (ytUrl == null) {
return null;
}
// Remove any query params in query string after the watch?v=<vid> in
// e.g.
// http://www.youtube.com/watch?v=0RUPACpf8Vs&feature=youtube_gdata_player
int andIdx = ytUrl.indexOf('&');
if (andIdx >= 0) {
ytUrl = ytUrl.substring(0, andIdx);
}
// Get the HTML response
String userAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0.1)";
HttpClient client = new DefaultHttpClient();
client.getParams().setParameter(CoreProtocolPNames.USER_AGENT,
userAgent);
HttpGet request = new HttpGet(ytUrl);
HttpResponse response = client.execute(request);
String html = "";
InputStream in = response.getEntity().getContent();
BufferedReader reader = new BufferedReader(new InputStreamReader(in));
StringBuilder str = new StringBuilder();
String line = null;
while ((line = reader.readLine()) != null) {
str.append(line.replace("\\u0026", "&"));
}
in.close();
html = str.toString();
// Parse the HTML response and extract the streaming URIs
if (html.contains("verify-age-thumb")) {
CLog.w("YouTube is asking for age verification. We can't handle that sorry.");
return null;
}
if (html.contains("das_captcha")) {
CLog.w("Captcha found, please try with different IP address.");
return null;
}
Pattern p = Pattern.compile("stream_map\": \"(.*?)?\"");
// Pattern p = Pattern.compile("/stream_map=(.[^&]*?)\"/");
Matcher m = p.matcher(html);
List<String> matches = new ArrayList<String>();
while (m.find()) {
matches.add(m.group());
}
if (matches.size() != 1) {
CLog.w("Found zero or too many stream maps.");
return null;
}
String urls[] = matches.get(0).split(",");
HashMap<String, String> foundArray = new HashMap<String, String>();
for (String ppUrl : urls) {
String url = URLDecoder.decode(ppUrl, "UTF-8");
Pattern p1 = Pattern.compile("itag=([0-9]+?)[&]");
Matcher m1 = p1.matcher(url);
String itag = null;
if (m1.find()) {
itag = m1.group(1);
}
Pattern p2 = Pattern.compile("sig=(.*?)[&]");
Matcher m2 = p2.matcher(url);
String sig = null;
if (m2.find()) {
sig = m2.group(1);
}
Pattern p3 = Pattern.compile("url=(.*?)[&]");
Matcher m3 = p3.matcher(ppUrl);
String um = null;
if (m3.find()) {
um = m3.group(1);
}
if (itag != null && sig != null && um != null) {
foundArray.put(itag, URLDecoder.decode(um, "UTF-8") + "&"
+ "signature=" + sig);
}
}
if (foundArray.size() == 0) {
CLog.w("Couldn't find any URLs and corresponding signatures");
return null;
}
HashMap<String, Meta> typeMap = new HashMap<String, Meta>();
typeMap.put("13", new Meta("13", "3GP", "Low Quality - 176x144"));
typeMap.put("17", new Meta("17", "3GP", "Medium Quality - 176x144"));
typeMap.put("36", new Meta("36", "3GP", "High Quality - 320x240"));
typeMap.put("5", new Meta("5", "FLV", "Low Quality - 400x226"));
typeMap.put("6", new Meta("6", "FLV", "Medium Quality - 640x360"));
typeMap.put("34", new Meta("34", "FLV", "Medium Quality - 640x360"));
typeMap.put("35", new Meta("35", "FLV", "High Quality - 854x480"));
typeMap.put("43", new Meta("43", "WEBM", "Low Quality - 640x360"));
typeMap.put("44", new Meta("44", "WEBM", "Medium Quality - 854x480"));
typeMap.put("45", new Meta("45", "WEBM", "High Quality - 1280x720"));
typeMap.put("18", new Meta("18", "MP4", "Medium Quality - 480x360"));
typeMap.put("22", new Meta("22", "MP4", "High Quality - 1280x720"));
typeMap.put("37", new Meta("37", "MP4", "High Quality - 1920x1080"));
typeMap.put("33", new Meta("38", "MP4", "High Quality - 4096x230"));
ArrayList<Video> videos = new ArrayList<ARViewer.Video>();
for (String format : typeMap.keySet()) {
Meta meta = typeMap.get(format);
if (foundArray.containsKey(format)) {
Video newVideo = new Video(meta.ext, meta.type,
foundArray.get(format));
videos.add(newVideo);
CLog.d("YouTube Video streaming details: ext:" + newVideo.ext
+ ", type:" + newVideo.type + ", url:" + newVideo.url);
}
}
return videos;
}
private class YouTubePageStreamUriGetter extends
AsyncTask<String, String, String> {
ProgressDialog progressDialog;
@Override
protected void onPreExecute() {
super.onPreExecute();
progressDialog = ProgressDialog.show(ARViewer.this, "",
"Connecting to YouTube...", true);
}
@Override
protected String doInBackground(String... params) {
String url = params[0];
try {
ArrayList<Video> videos = getStreamingUrisFromYouTubePage(url);
if (videos != null && !videos.isEmpty()) {
String retVidUrl = null;
for (Video video : videos) {
if (video.ext.toLowerCase().contains("mp4")
&& video.type.toLowerCase().contains("medium")) {
retVidUrl = video.url;
break;
}
}
if (retVidUrl == null) {
for (Video video : videos) {
if (video.ext.toLowerCase().contains("3gp")
&& video.type.toLowerCase().contains(
"medium")) {
retVidUrl = video.url;
break;
}
}
}
if (retVidUrl == null) {
for (Video video : videos) {
if (video.ext.toLowerCase().contains("mp4")
&& video.type.toLowerCase().contains("low")) {
retVidUrl = video.url;
break;
}
}
}
if (retVidUrl == null) {
for (Video video : videos) {
if (video.ext.toLowerCase().contains("3gp")
&& video.type.toLowerCase().contains("low")) {
retVidUrl = video.url;
break;
}
}
}
return retVidUrl;
}
} catch (Exception e) {
CLog.e("Couldn't get YouTube streaming URL", e);
}
CLog.w("Couldn't get stream URI for " + url);
return null;
}
@Override
protected void onPostExecute(String streamingUrl) {
super.onPostExecute(streamingUrl);
progressDialog.dismiss();
if (streamingUrl != null) {
/* Do what ever you want with streamUrl */
}
}
}
此代码不起作用
推荐答案
原始问题的启示
https://stackoverflow.com/a/15240012/9909365
为什么以前的答案无效
Pattern p2 = Pattern.compile("sig=(.*?)[&]");
Matcher m2 = p2.matcher(url);
String sig = null;
if (m2.find()) {
sig = m2.group(1);
}
截至2016年11月，这是一点点粗糙的边缘，但
显示基本原则。今天url_encoded_fmt_stream_map
在冒号之后没有空格（更好地使这个可选）和sig已经改为签名
当我在调试代码时，我发现新关键字为
许多视频网址中的签名& s
and while i am debuging the code i found the new keyword its
signature&s in many video's URL
此处编辑的答案
private static final HashMap<String, Meta> typeMap = new HashMap<String, Meta>();
initTypeMap（）;首先打电话
class Meta {
public String num;
public String type;
public String ext;
Meta(String num, String ext, String type) {
this.num = num;
this.ext = ext;
this.type = type;
}
}
class Video {
public String ext = "";
public String type = "";
public String url = "";
Video(String ext, String type, String url) {
this.ext = ext;
this.type = type;
this.url = url;
}
}
public ArrayList<Video> getStreamingUrisFromYouTubePage(String ytUrl)
throws IOException {
if (ytUrl == null) {
return null;
}
// Remove any query params in query string after the watch?v=<vid> in
// e.g.
// http://www.youtube.com/watch?v=0RUPACpf8Vs&feature=youtube_gdata_player
int andIdx = ytUrl.indexOf('&');
if (andIdx >= 0) {
ytUrl = ytUrl.substring(0, andIdx);
}
// Get the HTML response
/* String userAgent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0.1)";*/
/* HttpClient client = new DefaultHttpClient();
client.getParams().setParameter(CoreProtocolPNames.USER_AGENT,
userAgent);
HttpGet request = new HttpGet(ytUrl);
HttpResponse response = client.execute(request);*/
String html = "";
HttpsURLConnection c = (HttpsURLConnection) new URL(ytUrl).openConnection();
c.setRequestMethod("GET");
c.setDoOutput(true);
c.connect();
InputStream in = c.getInputStream();
BufferedReader reader = new BufferedReader(new InputStreamReader(in));
StringBuilder str = new StringBuilder();
String line = null;
while ((line = reader.readLine()) != null) {
str.append(line.replace("\\u0026", "&"));
}
in.close();
html = str.toString();
// Parse the HTML response and extract the streaming URIs
if (html.contains("verify-age-thumb")) {
Log.e("Downloader", "YouTube is asking for age verification. We can't handle that sorry.");
return null;
}
if (html.contains("das_captcha")) {
Log.e("Downloader", "Captcha found, please try with different IP address.");
return null;
}
Pattern p = Pattern.compile("stream_map\":\"(.*?)?\"");
// Pattern p = Pattern.compile("/stream_map=(.[^&]*?)\"/");
Matcher m = p.matcher(html);
List<String> matches = new ArrayList<String>();
while (m.find()) {
matches.add(m.group());
}
if (matches.size() != 1) {
Log.e("Downloader", "Found zero or too many stream maps.");
return null;
}
String urls[] = matches.get(0).split(",");
HashMap<String, String> foundArray = new HashMap<String, String>();
for (String ppUrl : urls) {
String url = URLDecoder.decode(ppUrl, "UTF-8");
Log.e("URL","URL : "+url);
Pattern p1 = Pattern.compile("itag=([0-9]+?)[&]");
Matcher m1 = p1.matcher(url);
String itag = null;
if (m1.find()) {
itag = m1.group(1);
}
Pattern p2 = Pattern.compile("signature=(.*?)[&]");
Matcher m2 = p2.matcher(url);
String sig = null;
if (m2.find()) {
sig = m2.group(1);
} else {
Pattern p23 = Pattern.compile("signature&s=(.*?)[&]");
Matcher m23 = p23.matcher(url);
if (m23.find()) {
sig = m23.group(1);
}
}
Pattern p3 = Pattern.compile("url=(.*?)[&]");
Matcher m3 = p3.matcher(ppUrl);
String um = null;
if (m3.find()) {
um = m3.group(1);
}
if (itag != null && sig != null && um != null) {
Log.e("foundArray","Adding Value");
foundArray.put(itag, URLDecoder.decode(um, "UTF-8") + "&"
+ "signature=" + sig);
}
}
Log.e("foundArray","Size : "+foundArray.size());
if (foundArray.size() == 0) {
Log.e("Downloader", "Couldn't find any URLs and corresponding signatures");
return null;
}
ArrayList<Video> videos = new ArrayList<Video>();
for (String format : typeMap.keySet()) {
Meta meta = typeMap.get(format);
if (foundArray.containsKey(format)) {
Video newVideo = new Video(meta.ext, meta.type,
foundArray.get(format));
videos.add(newVideo);
Log.d("Downloader", "YouTube Video streaming details: ext:" + newVideo.ext
+ ", type:" + newVideo.type + ", url:" + newVideo.url);
}
}
return videos;
}
private class YouTubePageStreamUriGetter extends AsyncTask<String, String, ArrayList<Video>> {
ProgressDialog progressDialog;
@Override
protected void onPreExecute() {
super.onPreExecute();
progressDialog = ProgressDialog.show(webViewActivity.this, "",
"Connecting to YouTube...", true);
}
@Override
protected ArrayList<Video> doInBackground(String... params) {
ArrayList<Video> fVideos = new ArrayList<>();
String url = params[0];
try {
ArrayList<Video> videos = getStreamingUrisFromYouTubePage(url);
/* Log.e("Downloader","Size of Video : "+videos.size());*/
if (videos != null && !videos.isEmpty()) {
for (Video video : videos)
{
Log.e("Downloader", "ext : " + video.ext);
if (video.ext.toLowerCase().contains("mp4") || video.ext.toLowerCase().contains("3gp") || video.ext.toLowerCase().contains("flv") || video.ext.toLowerCase().contains("webm")) {
ext = video.ext.toLowerCase();
fVideos.add(new Video(video.ext,video.type,video.url));
}
}
return fVideos;
}
} catch (Exception e) {
e.printStackTrace();
Log.e("Downloader", "Couldn't get YouTube streaming URL", e);
}
Log.e("Downloader", "Couldn't get stream URI for " + url);
return null;
}
@Override
protected void onPostExecute(ArrayList<Video> streamingUrl) {
super.onPostExecute(streamingUrl);
progressDialog.dismiss();
if (streamingUrl != null) {
if (!streamingUrl.isEmpty()) {
//Log.e("Steaming Url", "Value : " + streamingUrl);
for (int i = 0; i < streamingUrl.size(); i++) {
Video fX = streamingUrl.get(i);
Log.e("Founded Video", "URL : " + fX.url);
Log.e("Founded Video", "TYPE : " + fX.type);
Log.e("Founded Video", "EXT : " + fX.ext);
}
//new ProgressBack().execute(new String[]{streamingUrl, filename + "." + ext});
}
}
}
}
public void initTypeMap()
{
typeMap.put("13", new Meta("13", "3GP", "Low Quality - 176x144"));
typeMap.put("17", new Meta("17", "3GP", "Medium Quality - 176x144"));
typeMap.put("36", new Meta("36", "3GP", "High Quality - 320x240"));
typeMap.put("5", new Meta("5", "FLV", "Low Quality - 400x226"));
typeMap.put("6", new Meta("6", "FLV", "Medium Quality - 640x360"));
typeMap.put("34", new Meta("34", "FLV", "Medium Quality - 640x360"));
typeMap.put("35", new Meta("35", "FLV", "High Quality - 854x480"));
typeMap.put("43", new Meta("43", "WEBM", "Low Quality - 640x360"));
typeMap.put("44", new Meta("44", "WEBM", "Medium Quality - 854x480"));
typeMap.put("45", new Meta("45", "WEBM", "High Quality - 1280x720"));
typeMap.put("18", new Meta("18", "MP4", "Medium Quality - 480x360"));
typeMap.put("22", new Meta("22", "MP4", "High Quality - 1280x720"));
typeMap.put("37", new Meta("37", "MP4", "High Quality - 1920x1080"));
typeMap.put("33", new Meta("38", "MP4", "High Quality - 4096x230"));
}
编辑2：
一段时间此代码无法正常工作
Some time This Code Not worked proper
相同-origin政策
https://en.wikipedia.org/wiki/Same-origin_policy
https://en.wikipedia.org/wiki/Cross-origin_resource_sharing
problem of Same-origin policy. Essentially, you cannot download this file from www.youtube.com because they are different domains. A workaround of this problem is [CORS][1].
url_encoded_fmt_stream_map // traditional: contains video and audio stream
adaptive_fmts // DASH: contains video or audio stream
每个都是逗号分隔我称之为流对象的数组。每个流对象将包含这样的值
Each of these is a comma separated array of what I would call "stream objects". Each "stream object" will contain values like this
url // direct HTTP link to a video
itag // code specifying the quality
s // signature, security measure to counter downloading
每个URL都是编码，所以你需要解码它们。现在是棘手的部分。
Each URL will be encoded so you will need to decode them. Now the tricky part.
YouTube的视频至少有3个安全级别
YouTube has at least 3 security levels for their videos
unsecured // as expected, you can download these with just the unencoded URL
s // see below
RTMPE // uses "rtmpe://" protocol, no known method for these
RTMPE视频通常用于官方全长电影，并受SWF验证类型2保护。自2011年以来一直存在并且尚未进行逆向工程。
The RTMPE videos are typically used on official full length movies, and are protected with SWF Verification Type 2. This has been around since 2011 and has yet to be reverse engineered.
类型s视频实际上是最难下载的。你会在VEVO视频等上看到这些。它们以签名开头，例如
The type "s" videos are the most difficult that can actually be downloaded. You will typcially see these on VEVO videos and the like. They start with a signature such as
AA5D05FA7771AD4868BA4C977C3DEAAC620DE020E.0F421820F42978A1F8EAFCDAC4EF507DB5
然后用这样的函数对签名进行加扰
AA5D05FA7771AD4868BA4C977C3DEAAC620DE020E.0F421820F42978A1F8EAFCDAC4EF507DB5 Then the signature is scrambled with a function like this
function mo(a) {
a = a.split("");
a = lo.rw(a, 1);
a = lo.rw(a, 32);
a = lo.IC(a, 1);
a = lo.wS(a, 77);
a = lo.IC(a, 3);
a = lo.wS(a, 77);
a = lo.IC(a, 3);
a = lo.wS(a, 44);
return a.join("")
}
此功能是动态的，它通常每天都在变化。为了使这个功能更加困难，该功能被托管在一个URL上，例如
This function is dynamic, it typically changes every day. To make it more difficult the function is hosted at a URL such as
http://s.ytimg.com/yts/jsbin/html5player-en_US-vflycBCEX.js
这引入了同源策略的问题。基本上，您无法从www.youtube.com下载此文件，因为它们是不同的域。这个问题的解决方法是CORS。使用CORS，s.ytimg.com可以添加此标题
this introduces the problem of Same-origin policy. Essentially, you cannot download this file from www.youtube.com because they are different domains. A workaround of this problem is CORS. With CORS, s.ytimg.com could add this header
Access-Control-Allow-Origin: http://www.youtube.com
它允许JavaScript从www.youtube.com下载。当然他们不这样做。此解决方法的解决方法是使用CORS代理。这是一个代理，响应所有请求的以下标题
and it would allow the JavaScript to download from www.youtube.com. Of course they do not do this. A workaround for this workaround is to use a CORS proxy. This is a proxy that responds with the following header to all requests
Access-Control-Allow-Origin: *
因此，既然您已经代理了您的JS文件，并使用该函数来加密签名，那么您可以在用于下载视频的查询字符串。
So, now that you have proxied your JS file, and used the function to scramble the signature, you can use that in the querystring to download a video.
这篇关于Youtube视频下载（Android / Java）的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
