prehistoric-systems/the-chomsky-index
1
0
Fork 0
mirror of https://github.com/jasons-gh/the-chomsky-index.git synced 2026-03-11 08:54:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Create base.py

Browse source
This commit is contained in:
Jason Lobo 2020-10-03 17:00:48 +01:00
parent 428eae73fd
commit 0f7ddc80ce
1 changed files with 42 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
base.py Normal file
View file

@ -0,0 +1,42 @@
import sources
import subprocess
from pathlib import Path
from unidecode import unidecode
# youtube-dl - download the subtitles as .vtt files
urls_yt = sources.urls_yt()
for url in urls_yt:
subprocess.run(['youtube-dl', '-i', '--skip-download', '--write-auto-sub', '-o%(title)s %(id)s', url])
# ffmpeg - convert them from .vtt to .srt
for file in [x for x in Path(__file__).parent.glob('**/*.vtt') if x.is_file()]:
subprocess.run('ffmpeg.exe -i "' + str(file.name) + '" -- "' + str(file.name[:-4]) + '".srt')
# unidecode - replace some characters if present
unidecoded_files = set()
for file in [x for x in Path(__file__).parent.glob('**/*.srt') if x.is_file()]:
with open(file, 'r', encoding='utf-8') as file_object:
data = file_object.read()
for line in data:
if line != unidecode(line):
data = data.replace(line, unidecode(line))
unidecoded_files.add(str(file.name))
with open(file, 'w', encoding='utf-8') as file_object:
file_object.write(data)
# information
print(str(len(urls_yt)) + ' subtitle files requested')
print(str(len([x for x in Path(__file__).parent.glob('**/*.vtt') if x.is_file()])) + ' .vtt subtitle files in this folder')
print(str(len([x for x in Path(__file__).parent.glob('**/*.srt') if x.is_file()])) + ' .srt subtitle files in this folder')
print(str(len(unidecoded_files)) + ' subtitle files unidecoded')