bandcamp-discover 0.2.3 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: fd867e30e047c7464a7601b9cfa5cd49a7d757f73b6b395546b39ac9fc681134
|
4
|
+
data.tar.gz: c99a4a5b6c5bd6efe32983d22f58971dd24d38849514ccff5c5b66bde8d119f9
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: ccbdc7e84878b732658a2d8f5732279fb650268bca8886ca0f21ddf6c070d9611ff4946f9a030a428fe708c1bd0a83f0939570e3370a583126e7adec1a541849
|
7
|
+
data.tar.gz: 051b67db17ce1acf900b088f440a8f52e92e3fe7475c3b6713c02b15d0a2f2b5c9e944d8fda52aaa8fd40c5bc083d6cb7d9f7a9824196d2e550ebbb6475c5fbe
|
@@ -8,9 +8,15 @@ module BandcampDiscover
|
|
8
8
|
super do |page|
|
9
9
|
page.goto(@url)
|
10
10
|
|
11
|
+
title = page.query_selector("meta[name=title]")[:content]
|
12
|
+
|
11
13
|
# querying all tags in the bottom and returning their text node
|
12
14
|
tags = page.query_selector_all("a.tag")
|
13
|
-
tags.map
|
15
|
+
tags.map!(&:inner_text)
|
16
|
+
|
17
|
+
player = page.query_selector("meta[property='og:video']")[:content]
|
18
|
+
|
19
|
+
[@url, title, tags, player]
|
14
20
|
end
|
15
21
|
end
|
16
22
|
end
|
@@ -18,7 +18,7 @@ module BandcampDiscover
|
|
18
18
|
|
19
19
|
if force || Analyzer.new(bio_text&.inner_html).label?
|
20
20
|
return Sync do
|
21
|
-
music_tags = Scrapers::Music.new(url: "#{@url}/music", browser: @browser, max_tasks: @max_tasks).scrape
|
21
|
+
albums, music_tags = Scrapers::Music.new(url: "#{@url}/music", browser: @browser, max_tasks: @max_tasks).scrape
|
22
22
|
|
23
23
|
puts "done scraping #{@url}"
|
24
24
|
|
@@ -27,7 +27,8 @@ module BandcampDiscover
|
|
27
27
|
name: name,
|
28
28
|
location: location,
|
29
29
|
bio: bio_text.inner_text,
|
30
|
-
tags_with_weights: music_tags&.compact
|
30
|
+
tags_with_weights: music_tags&.compact,
|
31
|
+
albums: albums
|
31
32
|
}
|
32
33
|
end
|
33
34
|
else
|
@@ -21,20 +21,24 @@ module BandcampDiscover
|
|
21
21
|
|
22
22
|
semaphore = Async::Semaphore.new(@max_tasks)
|
23
23
|
|
24
|
-
|
24
|
+
albums = album_links.take(20).map do |album_link|
|
25
25
|
semaphore.async do
|
26
26
|
url = album_link[:href].start_with?("https://") ? album_link[:href] : "#{@base_url}#{album_link[:href]}"
|
27
27
|
puts "starting to scrape #{url}"
|
28
28
|
|
29
|
-
|
29
|
+
album = Scrapers::Album.new(url: url, browser: @browser).scrape
|
30
30
|
|
31
31
|
puts "done scraping #{url}"
|
32
32
|
|
33
|
-
|
33
|
+
album
|
34
34
|
end
|
35
35
|
end.map(&:wait)
|
36
36
|
|
37
|
-
|
37
|
+
albums.map! do |album_url, album_title, album_tags, album_player|
|
38
|
+
{ url: album_url, title: album_title, tags: album_tags, player_url: album_player }
|
39
|
+
end
|
40
|
+
|
41
|
+
[albums, normalize_tally(albums.map { _1[:tags] }.flatten.tally)]
|
38
42
|
end
|
39
43
|
end
|
40
44
|
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bandcamp-discover
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.3.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Julian RUbisch
|
8
8
|
bindir: bin
|
9
9
|
cert_chain: []
|
10
|
-
date: 2025-08-
|
10
|
+
date: 2025-08-19 00:00:00.000000000 Z
|
11
11
|
dependencies:
|
12
12
|
- !ruby/object:Gem::Dependency
|
13
13
|
name: rake
|