def handle(self, *args, **options):
for file in sorted(
glob.glob(
'/var/www/vhosts/tmi-archive.com/mp3/import2/clean/*.mp3')
):
title = file.split('/')[-1].replace('.mp3',
'').replace('-', ' ').replace(
'_', ' ')
title = f'Imported - {title}'
existing = Talk.objects.filter(title=title).count()
if existing > 0:
continue
id_ = uuid.uuid4()
id_ = base64.b32encode(
id_.bytes).decode("utf-8").rstrip("=\n")[:12]
new_file_dir = '/var/www/vhosts/tmi-archive.com/mp3.tmi-archive.com'
new_file_name = f"tmi-archive-{id_}.mp3"
shutil.copy(file, new_file_dir + '/' + new_file_name)
talk = Talk(title=title,
updated_by_id=1,
created_by_id=1,
original_file_name=file.split('/')[-1],
audio_filename=new_file_name,
audio_cleaned=new_file_name,
audio_original=new_file_name)
talk.auto_add_user_data = False
talk.save()
print(title, talk.id)
def handle(self, *args, **options):
df = pd.read_json('./_other/scraper/articles-selenium.json')
audio_path = '/home/script/_tmp/dhamma'
for i, row in df.iloc[3:].iterrows():
title = row.title
existing = Talk.objects.filter(title=title).count()
if existing > 0:
continue
print(title)
content = BeautifulSoup(row.article, "html.parser").find('div', {'class': 'entry-content'})
content = str(content).replace('<div class="entry-content">', '')[:-6]
content = BeautifulSoup(content, "html.parser")
for div in content.find_all("div", {'class': 'powerpress_player'}):
div.decompose()
for div in content.find_all("p", {'class': 'powerpress_links'}):
div.decompose()
content = str(content)
talk = Talk(
title=title,
description=content,
updated_by_id=1,
created_by_id=1
)
talk.auto_add_user_data = False
talk.save()
if row.audio_link is not None:
from django.core.files import File
file_name = row.audio_link.replace('?_=1', '').split('/')[-1]
orig_audio = '{}/mp3/{}'.format(audio_path, file_name)
if os.path.exists(orig_audio):
orig_audio = File(open(orig_audio, 'rb'))
talk.audio_original.save('new', orig_audio)
clean_audio = '{}/mp3-cleaned/{}'.format(audio_path, file_name)
if os.path.exists(clean_audio):
clean_audio = File(open(clean_audio, 'rb'))
talk.audio_cleaned.save('new', clean_audio)