1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
|
import os
import re
from pathlib import Path
from sh import youtube_dl, ErrorReturnCode_1
from utils import read_file, write_file
class Extractor():
def __init__(self, reg, url):
self.root = None
if not reg:
r = re.search(r'(^http(?:s|):(?:\/\/.*?\/|\/\/.*))', url)
if r:
self.root = r.group(1)
if not self.root:
self.root = reg.group(1)
self._albums = []
self.root_path = self._root_path()
self._update_cache(self.root)
def _root_path(self):
file_path = os.path.abspath(__file__)
folder_path = Path(file_path).parent
root_path = Path(folder_path).parent
return root_path
def _update_cache(self, url):
urls_cache = []
cache_file = Path(self.root_path, '.urls_cache.txt')
urls_cache = read_file(cache_file)
for url in urls_cache:
if url.startswith(self.root):
return
write_file(cache_file, self.root + "," + self.__class__.__name__)
def _yt_wrapper(self, url, output):
try:
for line in youtube_dl(
url, audio_format="mp3",
add_metadata=True,
o=output + self.filename_template,
ignore_errors=True,
_iter=True):
print(line.strip())
except ErrorReturnCode_1:
pass
def download_albums(self, output):
for album in self._albums:
print("Parsing " + album + "...")
self._yt_wrapper(album, output)
|
