在此页面中,Albert Armea 分享了一个代码,使用 ffmpeg
按章节拆分视频。代码很简单,但不是很好看。
ffmpeg -i "$SOURCE.$EXT" 2>&1 |
grep Chapter |
sed -E "s/ *Chapter #([0-9]+.[0-9]+): start ([0-9]+.[0-9]+), end ([0-9]+.[0-9]+)/-i "$SOURCE.$EXT" -vcodec copy -acodec copy -ss 2 -to 3 "$SOURCE-1.$EXT"/" |
xargs -n 11 ffmpeg
有没有一种优雅的方式来完成这项工作?
(编辑:此提示来自 https://github.com/phiresky 通过此问题:https://github.com/harryjackson/ffmpeg_split/issues/2(
您可以使用以下方法获取章节:
ffprobe -i fname -print_format json -show_chapters -loglevel error
如果我再写一次,我会使用 ffprobe 的 json 选项
(原答案如下(
这是一个有效的python脚本。我在几个视频上测试了它,效果很好。Python不是我的第一门语言,但我注意到你使用它,所以我认为用Python编写它可能更有意义。我已将其添加到Github。如果您想改进,请提交拉取请求。
#!/usr/bin/env python
import os
import re
import subprocess as sp
from subprocess import *
from optparse import OptionParser
def parseChapters(filename):
chapters = []
command = [ "ffmpeg", '-i', filename]
output = ""
try:
# ffmpeg requires an output file and so it errors
# when it does not get one so we need to capture stderr,
# not stdout.
output = sp.check_output(command, stderr=sp.STDOUT, universal_newlines=True)
except CalledProcessError, e:
output = e.output
for line in iter(output.splitlines()):
m = re.match(r".*Chapter #(d+:d+): start (d+.d+), end (d+.d+).*", line)
num = 0
if m != None:
chapters.append({ "name": m.group(1), "start": m.group(2), "end": m.group(3)})
num += 1
return chapters
def getChapters():
parser = OptionParser(usage="usage: %prog [options] filename", version="%prog 1.0")
parser.add_option("-f", "--file",dest="infile", help="Input File", metavar="FILE")
(options, args) = parser.parse_args()
if not options.infile:
parser.error('Filename required')
chapters = parseChapters(options.infile)
fbase, fext = os.path.splitext(options.infile)
for chap in chapters:
print "start:" + chap['start']
chap['outfile'] = fbase + "-ch-"+ chap['name'] + fext
chap['origfile'] = options.infile
print chap['outfile']
return chapters
def convertChapters(chapters):
for chap in chapters:
print "start:" + chap['start']
print chap
command = [
"ffmpeg", '-i', chap['origfile'],
'-vcodec', 'copy',
'-acodec', 'copy',
'-ss', chap['start'],
'-to', chap['end'],
chap['outfile']]
output = ""
try:
# ffmpeg requires an output file and so it errors
# when it does not get one
output = sp.check_output(command, stderr=sp.STDOUT, universal_newlines=True)
except CalledProcessError, e:
output = e.output
raise RuntimeError("command '{}' return with error (code {}): {}".format(e.cmd, e.returncode, e.output))
if __name__ == '__main__':
chapters = getChapters()
convertChapters(chapters)
原始shell代码的一个版本,包括:
- 提高效率
- 使用
ffprobe
而不是ffmpeg
- 拆分输入而不是输出
- 使用
- 通过避免
xargs
和sed
来提高可靠性 - 通过使用多行提高了可读性
- 传输多个音频或字幕流
- 从输出文件中删除章节(因为它们将是无效的时间码(
- 简化的命令行参数
#!/bin/sh -efu
input="$1"
ffprobe
-print_format csv
-show_chapters
"$input" |
cut -d ',' -f '5,7,8' |
while IFS=, read start end chapter
do
ffmpeg
-nostdin
-ss "$start" -to "$end"
-i "$input"
-c copy
-map 0
-map_chapters -1
"${input%.*}-$chapter.${input##*.}"
done
为了防止它干扰循环,指示ffmpeg
不要读取stdin
。
ffmpeg -i "$SOURCE.$EXT" 2>&1 # get metadata about file
| grep Chapter # search for Chapter in metadata and pass the results
| sed -E "s/ *Chapter #([0-9]+.[0-9]+): start ([0-9]+.[0-9]+), end ([0-9]+.[0-9]+)/-i "$SOURCE.$EXT" -vcodec copy -acodec copy -ss 2 -to 3 "$SOURCE-1.$EXT"/" # filter the results, explicitly defining the timecode markers for each chapter
| xargs -n 11 ffmpeg # construct argument list with maximum of 11 arguments and execute ffmpeg
您的命令将解析文件元数据并读出每章的时间码标记。 您可以为每个章节手动执行此操作。
ffmpeg -i ORIGINALFILE.mp4 -acodec copy -vcodec copy -ss 0 -t 00:15:00 OUTFILE-1.mp4
或者你可以写出章节标记,并用这个bash脚本运行它们,只是更容易阅读。
#!/bin/bash
# Author: http://crunchbang.org/forums/viewtopic.php?id=38748#p414992
# m4bronto
# Chapter #0:0: start 0.000000, end 1290.013333
# first _ _ start _ end
while [ $# -gt 0 ]; do
ffmpeg -i "$1" 2> tmp.txt
while read -r first _ _ start _ end; do
if [[ $first = Chapter ]]; then
read # discard line with Metadata:
read _ _ chapter
ffmpeg -vsync 2 -i "$1" -ss "${start%?}" -to "$end" -vn -ar 44100 -ac 2 -ab 128 -f mp3 "$chapter.mp3" </dev/null
fi
done <tmp.txt
rm tmp.txt
shift
done
或者你可以使用HandbrakeCLI,正如本文最初提到的,这个例子将第3章提取到3.mkv
HandBrakeCLI -c 3 -i originalfile.mkv -o 3.mkv
或者这篇文章中提到的其他工具
mkvmerge -o output.mkv --split chapters:all input.mkv
比使用 JSON 和 sed
jq
来提取数据简单一点:
#!/usr/bin/env bash
# For systems where "bash" in not in "/bin/"
set -efu
videoFile="$1"
ffprobe -hide_banner
"$videoFile"
-print_format json
-show_chapters
-loglevel error |
jq -r '.chapters[] | [ .id, .start_time, .end_time | tostring ] | join(" ")' |
while read chapter start end; do
ffmpeg -nostdin
-ss "$start" -to "$end"
-i "$videoFile"
-map 0
-map_chapters -1
-c copy
-metadata title="$chapter"
"${videoFile%.*}-$chapter.${videoFile##*.}";
done
我使用 tostring jq
函数chapers[].id
因为它是一个整数。
我修改了哈利的脚本,使用章节名称作为文件名。它输出到具有输入文件名称(减去扩展名(的新目录中。它还在每个章节名称前面加上"1 - "、"2 - "等,以防有同名的章节。
#!/usr/bin/env python
import os
import re
import pprint
import sys
import subprocess as sp
from os.path import basename
from subprocess import *
from optparse import OptionParser
def parseChapters(filename):
chapters = []
command = [ "ffmpeg", '-i', filename]
output = ""
m = None
title = None
chapter_match = None
try:
# ffmpeg requires an output file and so it errors
# when it does not get one so we need to capture stderr,
# not stdout.
output = sp.check_output(command, stderr=sp.STDOUT, universal_newlines=True)
except CalledProcessError, e:
output = e.output
num = 1
for line in iter(output.splitlines()):
x = re.match(r".*title.*: (.*)", line)
print "x:"
pprint.pprint(x)
print "title:"
pprint.pprint(title)
if x == None:
m1 = re.match(r".*Chapter #(d+:d+): start (d+.d+), end (d+.d+).*", line)
title = None
else:
title = x.group(1)
if m1 != None:
chapter_match = m1
print "chapter_match:"
pprint.pprint(chapter_match)
if title != None and chapter_match != None:
m = chapter_match
pprint.pprint(title)
else:
m = None
if m != None:
chapters.append({ "name": `num` + " - " + title, "start": m.group(2), "end": m.group(3)})
num += 1
return chapters
def getChapters():
parser = OptionParser(usage="usage: %prog [options] filename", version="%prog 1.0")
parser.add_option("-f", "--file",dest="infile", help="Input File", metavar="FILE")
(options, args) = parser.parse_args()
if not options.infile:
parser.error('Filename required')
chapters = parseChapters(options.infile)
fbase, fext = os.path.splitext(options.infile)
path, file = os.path.split(options.infile)
newdir, fext = os.path.splitext( basename(options.infile) )
os.mkdir(path + "/" + newdir)
for chap in chapters:
chap['name'] = chap['name'].replace('/',':')
chap['name'] = chap['name'].replace("'","'")
print "start:" + chap['start']
chap['outfile'] = path + "/" + newdir + "/" + re.sub("[^-a-zA-Z0-9_.():' ]+", '', chap['name']) + fext
chap['origfile'] = options.infile
print chap['outfile']
return chapters
def convertChapters(chapters):
for chap in chapters:
print "start:" + chap['start']
print chap
command = [
"ffmpeg", '-i', chap['origfile'],
'-vcodec', 'copy',
'-acodec', 'copy',
'-ss', chap['start'],
'-to', chap['end'],
chap['outfile']]
output = ""
try:
# ffmpeg requires an output file and so it errors
# when it does not get one
output = sp.check_output(command, stderr=sp.STDOUT, universal_newlines=True)
except CalledProcessError, e:
output = e.output
raise RuntimeError("command '{}' return with error (code {}): {}".format(e.cmd, e.returncode, e.output))
if __name__ == '__main__':
chapters = getChapters()
convertChapters(chapters)
这花了很长时间才弄清楚,因为我绝对不是一个 Python 人。它也很不优雅,因为它正在逐行处理元数据,因此有很多箍需要跳过。(即,标题和章节数据通过元数据输出在单独的循环中找到(
但它有效,应该可以为您节省大量时间。它为我做到了!
前几天我试图自己拆分一本 .m4b 有声读物,偶然发现了这个线程和其他线程,但我找不到任何使用 batch-script 的示例。我不懂 python 或 bash,我根本不是批处理专家,但我试图阅读如何做到这一点,并提出了以下似乎有效的方法。
这会将按章节编号的 MP3 文件导出到与源文件相同的路径:
@echo off
setlocal enabledelayedexpansion
for /f "tokens=2,5,7,8 delims=," %%G in ('c:ffmpegbinffprobe -i %1 -print_format csv -show_chapters -loglevel error 2^> nul') do (
set padded=00%%G
"c:ffmpegbinffmpeg" -ss %%H -to %%I -i %1 -vn -c:a libmp3lame -b:a 32k -ac 1 -metadata title="%%J" -id3v2_version 3 -write_id3v1 1 -y "%~dpnx1-!padded:~-3!.mp3"
)
对于您的视频文件文件,我已将其更改为以下内容,以通过直接复制来处理视频和音频数据。我没有带有章节的视频文件,所以我无法测试它,但我希望它有效。
@echo off
setlocal enabledelayedexpansion
for /f "tokens=2,5,7,8 delims=," %%G in ('c:ffmpegbinffprobe -i %1 -print_format csv -show_chapters -loglevel error 2^> nul') do (
set padded=00%%G
"c:ffmpegbinffmpeg" -ss %%H -to %%I -i %1 -c:v copy -c:a copy -metadata title="%%J" -y "%~dpnx1-!padded:~-3!.mkv"
)
PowerShell版本
$filePath = 'C:InputVideo.mp4'
$file = Get-Item $filePath
$json = ConvertFrom-Json (ffprobe -i $filePath -print_format json -show_chapters -loglevel error | Out-String)
foreach($chapter in $json.chapters)
{
ffmpeg -loglevel error -i $filePath -c copy -ss $chapter.start_time -to $chapter.end_time "$($file.DirectoryName)$($chapter.id).$($file.Extension)"
}
我想要一些额外的东西,比如:
- 提取盖子
- 使用章节名称作为文件名 在
- 文件名前面加上前导零的计数器,因此字母顺序在每个软件中都可以正常工作
- 制作播放列表
- 修改元数据以包含章节名称
- 根据元数据将所有文件输出到新目录(年份作者 - 标题(
这是我的脚本(我使用了哈利的ffprobe json输出的提示(
#!/bin/bash
input="input.aax"
EXT2="m4a"
json=$(ffprobe -activation_bytes secret -i "$input" -loglevel error -print_format json -show_format -show_chapters)
title=$(echo $json | jq -r ".format.tags.title")
count=$(echo $json | jq ".chapters | length")
target=$(echo $json | jq -r ".format.tags | .date + " " + .artist + " - " + .title")
mkdir "$target"
ffmpeg -activation_bytes secret -i $input -vframes 1 -f image2 "$target/cover.jpg"
echo "[playlist]
NumberOfEntries=$count" > "$target/0_Playlist.pls"
for i in $(seq -w 1 $count);
do
j=$((10#$i))
n=$(($j-1))
start=$(echo $json | jq -r ".chapters[$n].start_time")
end=$(echo $json | jq -r ".chapters[$n].end_time")
name=$(echo $json | jq -r ".chapters[$n].tags.title")
ffmpeg -activation_bytes secret -i $input -vn -acodec -map_chapters -1 copy -ss $start -to $end -metadata title="$title $name" "$target/$i $name.$EXT2"
echo "File$j=$i $name.$EXT2" >> "$target/0_Playlist.pls"
done
in python
#!/usr/bin/env python3
import sys
import os
import subprocess
import shlex
def split_video(pathToInputVideo):
command="ffprobe -v quiet -print_format csv -show_chapters "
args=shlex.split(command)
args.append(pathToInputVideo)
output = subprocess.check_output(args, stderr=subprocess.STDOUT, universal_newlines=True)
cpt=0
for line in iter(output.splitlines()):
dec=line.split(",")
st_time=dec[4]
end_time=dec[6]
name=dec[7]
command="ffmpeg -i _VIDEO_ -ss _START_ -to _STOP_ -vcodec copy -acodec copy"
args=shlex.split(command)
args[args.index("_VIDEO_")]=pathToInputVideo
args[args.index("_START_")]=st_time
args[args.index("_STOP_")]=end_time
filename=os.path.basename(pathToInputVideo)
words=filename.split(".");
l=len(words)
ext=words[l-1]
cpt+=1
filename=" ".join(words[0:l-1])+" - "+str(cpt)+" - "+name+"."+ext
args.append(filename)
subprocess.call(args)
for video in sys.argv[1:]:
split_video(video)
NodeJS/JavaScript 中的朴素解决方案
const probe = function (fpath, debug) {
var self = this;
return new Promise((resolve, reject) => {
var loglevel = debug ? 'debug' : 'error';
const args = [
'-v', 'quiet',
'-loglevel', loglevel,
'-print_format', 'json',
'-show_chapters',
'-show_format',
'-show_streams',
'-i', fpath
];
const opts = {
cwd: self._options.tempDir
};
const cb = (error, stdout) => {
if (error)
return reject(error);
try {
const outputObj = JSON.parse(stdout);
return resolve(outputObj);
} catch (ex) {
self.logger.error("probe failed %s", ex);
return reject(ex);
}
};
console.log(args)
cp.execFile('ffprobe', args, opts, cb)
.on('error', reject);
});
}//probe
raw
对象的 json 输出将包含一个具有以下结构的 chapters
数组:
{
"chapters": [{
"id": 0,
"time_base": "1/1000",
"start": 0,
"start_time": "0.000000",
"end": 145000,
"end_time": "135.000000",
"tags": {
"title": "This is Chapter 1"
}
}]
}
了这个答案,使输出视频名称为"[计数]-[章节].xyz">
input="$1"
count=0
ffprobe
-print_format csv
-show_chapters
"$input" |
cut -d ',' -f '5,7,8' |
while IFS=, read start end chapter
do
ffmpeg
-nostdin
-ss "$start" -to "$end"
-i "$input"
-c copy
-map 0
-map_chapters -1
"${count}-$chapter.${input##*.}"
count=$((count+=1))
done