Add bug number that we are closing.

[youtubedl] / youtube_dl / PostProcessor.py

diff --git a/youtube_dl/PostProcessor.py b/youtube_dl/PostProcessor.py
index af00f80eed35ecb6b6826d01fc22bb58e4ce188f..3ee1d3c5865e203f564d87c8beb55a3de3a46934 100644 (file)
--- a/youtube_dl/PostProcessor.py
+++ b/youtube_dl/PostProcessor.py
@@ -1,8 +1,3 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-from __future__ import absolute_import
-

 import os
 import subprocess
 import sys
 import os
 import subprocess
 import sys


@@ -45,30 +40,24 @@ class PostProcessor(object):
         one has an extra field called "filepath" that points to the
         downloaded file.
 
         one has an extra field called "filepath" that points to the
         downloaded file.
 

-        When this method returns None, the postprocessing chain is
-        stopped. However, this method may return an information
-        dictionary that will be passed to the next postprocessing
-        object in the chain. It can be the one it received after
-        changing some fields.
+        This method returns a tuple, the first element of which describes
+        whether the original file should be kept (i.e. not deleted - None for
+        no preference), and the second of which is the updated information.

 
         In addition, this method may raise a PostProcessingError
 
         In addition, this method may raise a PostProcessingError

-        exception that will be taken into account by the downloader
-        it was called from.
+        exception if post processing fails.

         """
         """

-        return information # by default, do nothing
+        return None, information # by default, keep file and do nothing

 
 

-class AudioConversionError(BaseException):
-    def __init__(self, message):
-        self.message = message
+class FFmpegPostProcessorError(PostProcessingError):
+    pass

 
 

-class FFmpegExtractAudioPP(PostProcessor):
-    def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, keepvideo=False):
+class AudioConversionError(PostProcessingError):
+    pass
+
+class FFmpegPostProcessor(PostProcessor):
+    def __init__(self,downloader=None):

         PostProcessor.__init__(self, downloader)
         PostProcessor.__init__(self, downloader)

-        if preferredcodec is None:
-            preferredcodec = 'best'
-        self._preferredcodec = preferredcodec
-        self._preferredquality = preferredquality
-        self._keepvideo = keepvideo

         self._exes = self.detect_executables()
 
     @staticmethod
         self._exes = self.detect_executables()
 
     @staticmethod


@@ -82,18 +71,55 @@ class FFmpegExtractAudioPP(PostProcessor):
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
         return dict((program, executable(program)) for program in programs)
 
         programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
         return dict((program, executable(program)) for program in programs)
 

+    def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
+        if not self._exes['ffmpeg'] and not self._exes['avconv']:
+            raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
+
+        files_cmd = []
+        for path in input_paths:
+            files_cmd.extend(['-i', encodeFilename(path)])
+        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
+               + opts +
+               [encodeFilename(self._ffmpeg_filename_argument(out_path))])
+
+        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+        stdout,stderr = p.communicate()
+        if p.returncode != 0:
+            stderr = stderr.decode('utf-8', 'replace')
+            msg = stderr.strip().split('\n')[-1]
+            raise FFmpegPostProcessorError(msg)
+
+    def run_ffmpeg(self, path, out_path, opts):
+        self.run_ffmpeg_multiple_files([path], out_path, opts)
+
+    def _ffmpeg_filename_argument(self, fn):
+        # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
+        if fn.startswith(u'-'):
+            return u'./' + fn
+        return fn
+
+class FFmpegExtractAudioPP(FFmpegPostProcessor):
+    def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, nopostoverwrites=False):
+        FFmpegPostProcessor.__init__(self, downloader)
+        if preferredcodec is None:
+            preferredcodec = 'best'
+        self._preferredcodec = preferredcodec
+        self._preferredquality = preferredquality
+        self._nopostoverwrites = nopostoverwrites
+

     def get_audio_codec(self, path):
     def get_audio_codec(self, path):

-        if not self._exes['ffprobe'] and not self._exes['avprobe']: return None
+        if not self._exes['ffprobe'] and not self._exes['avprobe']:
+            raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.')

         try:
         try:

-            cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', '--', encodeFilename(path)]
-            handle = subprocess.Popen(cmd, stderr=file(os.path.devnull, 'w'), stdout=subprocess.PIPE)
+            cmd = [self._exes['avprobe'] or self._exes['ffprobe'], '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path))]
+            handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE)

             output = handle.communicate()[0]
             if handle.wait() != 0:
                 return None
         except (IOError, OSError):
             return None
         audio_codec = None
             output = handle.communicate()[0]
             if handle.wait() != 0:
                 return None
         except (IOError, OSError):
             return None
         audio_codec = None

-        for line in output.split('\n'):
+        for line in output.decode('ascii', 'ignore').split('\n'):

             if line.startswith('codec_name='):
                 audio_codec = line.split('=')[1].strip()
             elif line.strip() == 'codec_type=audio' and audio_codec is not None:
             if line.startswith('codec_name='):
                 audio_codec = line.split('=')[1].strip()
             elif line.strip() == 'codec_type=audio' and audio_codec is not None:


@@ -102,36 +128,32 @@ class FFmpegExtractAudioPP(PostProcessor):
 
     def run_ffmpeg(self, path, out_path, codec, more_opts):
         if not self._exes['ffmpeg'] and not self._exes['avconv']:
 
     def run_ffmpeg(self, path, out_path, codec, more_opts):
         if not self._exes['ffmpeg'] and not self._exes['avconv']:

-            raise AudioConversionError('ffmpeg or avconv not found. Please install one.')   
+            raise AudioConversionError('ffmpeg or avconv not found. Please install one.')

         if codec is None:
             acodec_opts = []
         else:
             acodec_opts = ['-acodec', codec]
         if codec is None:
             acodec_opts = []
         else:
             acodec_opts = ['-acodec', codec]

-        cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path), '-vn']
-               + acodec_opts + more_opts +
-               ['--', encodeFilename(out_path)])
-        p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-        stdout,stderr = p.communicate()
-        if p.returncode != 0:
-            msg = stderr.strip().split('\n')[-1]
-            raise AudioConversionError(msg)
+        opts = ['-vn'] + acodec_opts + more_opts
+        try:
+            FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
+        except FFmpegPostProcessorError as err:
+            raise AudioConversionError(err.msg)

 
     def run(self, information):
         path = information['filepath']
 
         filecodec = self.get_audio_codec(path)
         if filecodec is None:
 
     def run(self, information):
         path = information['filepath']
 
         filecodec = self.get_audio_codec(path)
         if filecodec is None:

-            self._downloader.to_stderr(u'WARNING: unable to obtain file audio codec with ffprobe')
-            return None
+            raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe')

 
         more_opts = []
         if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):
 
         more_opts = []
         if self._preferredcodec == 'best' or self._preferredcodec == filecodec or (self._preferredcodec == 'm4a' and filecodec == 'aac'):

-            if self._preferredcodec == 'm4a' and filecodec == 'aac':
+            if filecodec == 'aac' and self._preferredcodec in ['m4a', 'best']:

                 # Lossless, but in another container
                 acodec = 'copy'
                 # Lossless, but in another container
                 acodec = 'copy'

-                extension = self._preferredcodec
+                extension = 'm4a'

                 more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']
                 more_opts = [self._exes['avconv'] and '-bsf:a' or '-absf', 'aac_adtstoasc']

-            elif filecodec in ['aac', 'mp3', 'vorbis']:
+            elif filecodec in ['aac', 'mp3', 'vorbis', 'opus']:

                 # Lossless if possible
                 acodec = 'copy'
                 extension = filecodec
                 # Lossless if possible
                 acodec = 'copy'
                 extension = filecodec


@@ -151,7 +173,7 @@ class FFmpegExtractAudioPP(PostProcessor):
                         more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
         else:
             # We convert the audio (lossy)
                         more_opts += [self._exes['avconv'] and '-b:a' or '-ab', self._preferredquality + 'k']
         else:
             # We convert the audio (lossy)

-            acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]
+            acodec = {'mp3': 'libmp3lame', 'aac': 'aac', 'm4a': 'aac', 'opus': 'opus', 'vorbis': 'libvorbis', 'wav': None}[self._preferredcodec]

             extension = self._preferredcodec
             more_opts = []
             if self._preferredquality is not None:
             extension = self._preferredcodec
             more_opts = []
             if self._preferredquality is not None:


@@ -171,30 +193,277 @@ class FFmpegExtractAudioPP(PostProcessor):
 
         prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
         new_path = prefix + sep + extension
 
         prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
         new_path = prefix + sep + extension

-        self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+
+        # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
+        if new_path == path:
+            self._nopostoverwrites = True
+

         try:
         try:

-            self.run_ffmpeg(path, new_path, acodec, more_opts)
+            if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
+                self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
+            else:
+                self._downloader.to_screen(u'[' + (self._exes['avconv'] and 'avconv' or 'ffmpeg') + '] Destination: ' + new_path)
+                self.run_ffmpeg(path, new_path, acodec, more_opts)

         except:
             etype,e,tb = sys.exc_info()
             if isinstance(e, AudioConversionError):
         except:
             etype,e,tb = sys.exc_info()
             if isinstance(e, AudioConversionError):

-                self._downloader.to_stderr(u'ERROR: audio conversion failed: ' + e.message)
+                msg = u'audio conversion failed: ' + e.msg

             else:
             else:

-                self._downloader.to_stderr(u'ERROR: error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg'))
-            return None
+                msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
+            raise PostProcessingError(msg)

 
         # Try to update the date time for extracted audio file.
         if information.get('filetime') is not None:
             try:
                 os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
             except:
 
         # Try to update the date time for extracted audio file.
         if information.get('filetime') is not None:
             try:
                 os.utime(encodeFilename(new_path), (time.time(), information['filetime']))
             except:

-                self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
-
-        if not self._keepvideo:
-            try:
-                os.remove(encodeFilename(path))
-            except (IOError, OSError):
-                self._downloader.to_stderr(u'WARNING: Unable to remove downloaded video file')
-                return None
+                self._downloader.report_warning(u'Cannot update utime of audio file')

 
         information['filepath'] = new_path
 
         information['filepath'] = new_path

-        return information
+        return self._nopostoverwrites,information
+
+class FFmpegVideoConvertor(FFmpegPostProcessor):
+    def __init__(self, downloader=None,preferedformat=None):
+        super(FFmpegVideoConvertor, self).__init__(downloader)
+        self._preferedformat=preferedformat
+
+    def run(self, information):
+        path = information['filepath']
+        prefix, sep, ext = path.rpartition(u'.')
+        outpath = prefix + sep + self._preferedformat
+        if information['ext'] == self._preferedformat:
+            self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat))
+            return True,information
+        self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath)
+        self.run_ffmpeg(path, outpath, [])
+        information['filepath'] = outpath
+        information['format'] = self._preferedformat
+        information['ext'] = self._preferedformat
+        return False,information
+
+
+class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
+    # See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
+    _lang_map = {
+        'aa': 'aar',
+        'ab': 'abk',
+        'ae': 'ave',
+        'af': 'afr',
+        'ak': 'aka',
+        'am': 'amh',
+        'an': 'arg',
+        'ar': 'ara',
+        'as': 'asm',
+        'av': 'ava',
+        'ay': 'aym',
+        'az': 'aze',
+        'ba': 'bak',
+        'be': 'bel',
+        'bg': 'bul',
+        'bh': 'bih',
+        'bi': 'bis',
+        'bm': 'bam',
+        'bn': 'ben',
+        'bo': 'bod',
+        'br': 'bre',
+        'bs': 'bos',
+        'ca': 'cat',
+        'ce': 'che',
+        'ch': 'cha',
+        'co': 'cos',
+        'cr': 'cre',
+        'cs': 'ces',
+        'cu': 'chu',
+        'cv': 'chv',
+        'cy': 'cym',
+        'da': 'dan',
+        'de': 'deu',
+        'dv': 'div',
+        'dz': 'dzo',
+        'ee': 'ewe',
+        'el': 'ell',
+        'en': 'eng',
+        'eo': 'epo',
+        'es': 'spa',
+        'et': 'est',
+        'eu': 'eus',
+        'fa': 'fas',
+        'ff': 'ful',
+        'fi': 'fin',
+        'fj': 'fij',
+        'fo': 'fao',
+        'fr': 'fra',
+        'fy': 'fry',
+        'ga': 'gle',
+        'gd': 'gla',
+        'gl': 'glg',
+        'gn': 'grn',
+        'gu': 'guj',
+        'gv': 'glv',
+        'ha': 'hau',
+        'he': 'heb',
+        'hi': 'hin',
+        'ho': 'hmo',
+        'hr': 'hrv',
+        'ht': 'hat',
+        'hu': 'hun',
+        'hy': 'hye',
+        'hz': 'her',
+        'ia': 'ina',
+        'id': 'ind',
+        'ie': 'ile',
+        'ig': 'ibo',
+        'ii': 'iii',
+        'ik': 'ipk',
+        'io': 'ido',
+        'is': 'isl',
+        'it': 'ita',
+        'iu': 'iku',
+        'ja': 'jpn',
+        'jv': 'jav',
+        'ka': 'kat',
+        'kg': 'kon',
+        'ki': 'kik',
+        'kj': 'kua',
+        'kk': 'kaz',
+        'kl': 'kal',
+        'km': 'khm',
+        'kn': 'kan',
+        'ko': 'kor',
+        'kr': 'kau',
+        'ks': 'kas',
+        'ku': 'kur',
+        'kv': 'kom',
+        'kw': 'cor',
+        'ky': 'kir',
+        'la': 'lat',
+        'lb': 'ltz',
+        'lg': 'lug',
+        'li': 'lim',
+        'ln': 'lin',
+        'lo': 'lao',
+        'lt': 'lit',
+        'lu': 'lub',
+        'lv': 'lav',
+        'mg': 'mlg',
+        'mh': 'mah',
+        'mi': 'mri',
+        'mk': 'mkd',
+        'ml': 'mal',
+        'mn': 'mon',
+        'mr': 'mar',
+        'ms': 'msa',
+        'mt': 'mlt',
+        'my': 'mya',
+        'na': 'nau',
+        'nb': 'nob',
+        'nd': 'nde',
+        'ne': 'nep',
+        'ng': 'ndo',
+        'nl': 'nld',
+        'nn': 'nno',
+        'no': 'nor',
+        'nr': 'nbl',
+        'nv': 'nav',
+        'ny': 'nya',
+        'oc': 'oci',
+        'oj': 'oji',
+        'om': 'orm',
+        'or': 'ori',
+        'os': 'oss',
+        'pa': 'pan',
+        'pi': 'pli',
+        'pl': 'pol',
+        'ps': 'pus',
+        'pt': 'por',
+        'qu': 'que',
+        'rm': 'roh',
+        'rn': 'run',
+        'ro': 'ron',
+        'ru': 'rus',
+        'rw': 'kin',
+        'sa': 'san',
+        'sc': 'srd',
+        'sd': 'snd',
+        'se': 'sme',
+        'sg': 'sag',
+        'si': 'sin',
+        'sk': 'slk',
+        'sl': 'slv',
+        'sm': 'smo',
+        'sn': 'sna',
+        'so': 'som',
+        'sq': 'sqi',
+        'sr': 'srp',
+        'ss': 'ssw',
+        'st': 'sot',
+        'su': 'sun',
+        'sv': 'swe',
+        'sw': 'swa',
+        'ta': 'tam',
+        'te': 'tel',
+        'tg': 'tgk',
+        'th': 'tha',
+        'ti': 'tir',
+        'tk': 'tuk',
+        'tl': 'tgl',
+        'tn': 'tsn',
+        'to': 'ton',
+        'tr': 'tur',
+        'ts': 'tso',
+        'tt': 'tat',
+        'tw': 'twi',
+        'ty': 'tah',
+        'ug': 'uig',
+        'uk': 'ukr',
+        'ur': 'urd',
+        'uz': 'uzb',
+        've': 'ven',
+        'vi': 'vie',
+        'vo': 'vol',
+        'wa': 'wln',
+        'wo': 'wol',
+        'xh': 'xho',
+        'yi': 'yid',
+        'yo': 'yor',
+        'za': 'zha',
+        'zh': 'zho',
+        'zu': 'zul',
+    }
+
+    def __init__(self, downloader=None, subtitlesformat='srt'):
+        super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
+        self._subformat = subtitlesformat
+
+    @classmethod
+    def _conver_lang_code(cls, code):
+        """Convert language code from ISO 639-1 to ISO 639-2/T"""
+        return cls._lang_map.get(code[:2])
+
+    def run(self, information):
+        if information['ext'] != u'mp4':
+            self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
+            return True, information
+        if not information.get('subtitles'):
+            self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed') 
+            return True, information
+
+        sub_langs = [key for key in information['subtitles']]
+        filename = information['filepath']
+        input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
+
+        opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
+        for (i, lang) in enumerate(sub_langs):
+            opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
+            lang_code = self._conver_lang_code(lang)
+            if lang_code is not None:
+                opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
+        opts.extend(['-f', 'mp4'])
+
+        temp_filename = filename + u'.temp'
+        self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
+        self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
+        os.remove(encodeFilename(filename))
+        os.rename(encodeFilename(temp_filename), encodeFilename(filename))
+
+        return True, information