blob: 935a2d88b8fa8da4d3a1ed2c119cac520d588fca (
plain)
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
|
import re
import logging
import requests
from bs4 import BeautifulSoup
from .common import Extractor
class bandcamp(Extractor):
pattern = re.compile(r'(http(?:s|):\/\/.*bandcamp.com)')
filename_template = "%(artist)s/%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s"
def __init__(self, reg, url):
super().__init__(reg, url)
def get_albums(self):
r = requests.get(self.root)
soup = BeautifulSoup(r.text, 'html.parser')
items = soup.select('a[href]')
for item in items:
if '/album' in item['href'] and \
not item['href'].startswith("http"):
url = self.root.rstrip('/') + item['href']
if url not in self._albums:
self._albums.append(url)
if not self._albums:
logging.warning(f"No albums found at {self.root} ????")
|
