jonas/overdrive-plex
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

op 2.0

Browse Source
This commit is contained in:
bender
2023-11-12 00:10:13 -05:00
parent d6410e4ab0
commit b1d02cff7b
27 changed files with 506 additions and 403 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Chapters_List/__init__.py
View File
Chapters_List/chapter_ms.py
+33
View File
@@ -0,0 +1,33 @@
'''Converts label durations to milliseconds for pydub to read'''
import os
import re
from datetime import datetime, timedelta
def duration_to_milliseconds(duration):
'''Conversion from Seconds to Milliseconds'''
hours, minutes, seconds = duration.split(':')
seconds = int(hours)*3600 + int(minutes)*60 + float(seconds)
return int(seconds * 1000)
def read_chapters_file(dirpath, filename):
'''Open the chapters file and read the contents.'''
with open(os.path.join(dirpath, filename), 'r') as f:
lines = f.readlines()
return lines
def new_file(dirpath, filename):
'''Create a new file with the same name but with "ms" added to the end.'''
lines = read_chapters_file(dirpath, filename)
new_filename = filename[:-4] + "_ms.txt"
with open(os.path.join(dirpath, new_filename), 'w') as new_file:
for line in lines:
duration, label = re.split(r"\s+", line.strip(), 1)
milliseconds = duration_to_milliseconds(duration)
new_file.write(f'{milliseconds} {label}\n')
def add_ms_to_chapters(directory):
'''Loop through all files in the directory tree and process the matching files.'''
for dirpath, _, filenames in os.walk(directory):
for filename in filenames:
if filename.startswith("overdrive_chapters") and filename.endswith(".txt"):
new_file(dirpath, filename)
Chapters_List/chapters.py
+29
View File
@@ -0,0 +1,29 @@
import sys
import os
parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, parent_dir)
from Chapters_List.extract_overdrive_chapters import extract_chapters
from Chapters_List.chapter_ms import add_ms_to_chapters
from XML_JSON.json_scripts import load_config
from Chapters_List.ms_durations import ms_to_durations
parent_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
config_path = os.path.join(parent_dir, 'config.json')
config = load_config(config_path)
queue = config['queue'] #Where your ODMs are downloaded to
annex = config['annex'] #Where the ODMs get unpackaged to
circulation = config['circulation'] #Where the chapterized mp3s get saved
bookshelf = config['bookshelf'] #Where the final audiobook gets dropped
def chapters_list():
extract_chapters(annex)
add_ms_to_chapters(annex)
ms_to_durations(annex)
print("Splitting audio files into chapters & adding metadata (this may take a moment)...")
if __name__ == '__main__':
chapters_list()
Chapters_List/extract_overdrive_chapters.py
+111
View File
@@ -0,0 +1,111 @@
#!/usr/bin/env python3
'''
Credit to ex-nerd
Recursively scans current or specified directory for all subdirectories
containing mp3 files. If these mp3 files contain overdrive chapter markers
(id3 tag), writes overdrive_chapters.txt to the same directory.
Usage:
extract_overdrive_chapters.py [optional directory path]
Use with build_m4b from https://github.com/ex-nerd/audiotools
Note: Due to overdrive low quality, there is no point in encoding aac files
with better than: 64kbps stereo, HE, optimize for voice
'''
import os, sys, re
import mutagen.id3 as id3
from mutagen.mp3 import MP3
from mutagen import File
from collections import OrderedDict
def timestr(secs):
(secs, ms) = str(secs).split(".")
ms = float(ms[0:3] + "." + ms[3:])
secs = int(secs)
hours = int(secs // 3600)
secs = secs % 3600
mins = int(secs // 60)
secs = secs % 60
return f"{hours:02}:{mins:02}:{secs:02}.{ms:03.0f}"
def load_mp3(total, dir, file):
path = os.path.join(dir, file)
audio = MP3(path)
# print(audio.info.length) # , audio.info.bitrate
m = id3.ID3(path)
data = m.get("TXXX:OverDrive MediaMarkers")
if not data:
print("Can't find TXXX data point for {0}".format(file))
print(m.keys())
return
info = data.text[0]
file_chapters = re.findall(
r"<Name>\s*([^>]+?)\s*</Name><Time>\s*([\d:.]+)\s*</Time>", info, re.MULTILINE
)
chapters = []
for chapter in file_chapters:
(name, length) = chapter
name = re.sub(r'^"(.+)"$', r"\1", name)
name = re.sub(r"^\*(.+)\*$", r"\1", name)
name = re.sub(
r"\s*\([^)]*\)$", "", name
)
'''ignore any sub-chapter markers from Overdrive'''
name = re.sub(
r"\s+\(?continued\)?$", "", name
)
'''ignore any sub-chapter markers from Overdrive'''
name = re.sub(
r"\s+-\s*$", "", name
)
'''ignore any sub-chapter markers from Overdrive'''
name = re.sub(
r"^Dis[kc]\s+\d+\W*$", "", name
)
'''ignore any disk markers from Overdrive'''
name = name.strip()
t_parts = list(length.split(":"))
t_parts.reverse()
seconds = total + float(t_parts[0])
if len(t_parts) > 1:
seconds += int(t_parts[1]) * 60
if len(t_parts) > 2:
seconds += int(t_parts[2]) * 60 * 60
chapters.append([name, seconds])
# print(name, seconds)
return (total + audio.info.length, chapters)
def visit(dirname, filenames):
print(dirname)
os.chdir(dirname)
'''Parse the files'''
total = 0
all_chapters = OrderedDict()
for file in sorted(filenames):
if file.endswith(".mp3"):
(total, chapters) = load_mp3(total, dirname, file)
# print(repr(chapters))
for chapter in chapters:
if chapter[0] in all_chapters.keys():
continue
all_chapters[chapter[0]] = chapter[1]
if len(all_chapters) > 0:
with open("overdrive_chapters.txt", "w") as file:
for name, length in all_chapters.items():
chapstr = f"{timestr(length)} {name}"
file.write(chapstr + "\n")
# print(repr(all_chapters))
def extract_chapters(path="."):
abs_path = os.path.abspath(path)
for dirname, dirs, files in os.walk(abs_path, topdown=True):
dirs[:] = [d for d in dirs if d not in {".git", ".direnv"}]
visit(dirname, files)
Chapters_List/ms_durations.py
+46
View File
@@ -0,0 +1,46 @@
'''Takes the contents of the Milliseconds durations/labels file and creates start/end times'''
import os
def create_durations(file, lines):
for i in range(len(lines)):
parts = lines[i].split(" ")
if i == len(lines) - 2:
'''If it's the second-to-last line, write the last line's number and 0'''
file.write(parts[0])
file.write("\t" + lines[i + 1].split(" ")[0])
file.write("0")
elif i != len(lines) - 1:
'''Otherwise, write the number from the next line to the file'''
file.write(parts[0])
file.write("\t" + lines[i + 1].split(" ")[0])
else:
'''If it's the last line, just write the number and 0'''
if parts[0] != "":
file.write(parts[0])
file.write("0")
'''Write the rest of the line to the file'''
file.write("\t" + " ".join(parts[1:]))
if i != len(lines) - 1 or (i == len(lines) - 1 and lines[i] != ""):
file.write("\n")
def bookmark_final_duration(file, lines):
if lines[-1] == "":
'''Ensures there's no empty line at the end of the txt'''
file.seek(file.tell()-1, os.SEEK_SET)
file.truncate()
def create_spans_txt(file, file_path):
if file == 'overdrive_chapters_ms.txt':
with open(file_path, "r") as file:
lines = file.read().split('\n')
new_file_path = file_path.replace('.txt', '_spans.txt')
with open(new_file_path, "w") as file:
create_durations(file, lines)
bookmark_final_duration(file, lines)
def ms_to_durations(directory):
for subdir, _, files in os.walk(directory):
for file in files:
'''Locates "overdrive_chapters_ms.txt"'''
file_path = os.path.join(subdir, file)
create_spans_txt(file, file_path)