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
|
From 435d62abe9c4b4de7634d6028812ebd28b31c882 Mon Sep 17 00:00:00 2001
From: Gilles Pietri <gilles@wolface.fr>
Date: Wed, 23 Sep 2020 23:09:00 +0200
Subject: [PATCH 1/8] [bandcamp] fix regexp for JSON matching on bandcamp
From https://github.com/ytdl-org/youtube-dl/pull/26684.
---
youtube_dl/extractor/bandcamp.py | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py
index f14b407dc..ad1812320 100644
--- a/youtube_dl/extractor/bandcamp.py
+++ b/youtube_dl/extractor/bandcamp.py
@@ -91,10 +91,11 @@ class BandcampIE(InfoExtractor):
duration = None
formats = []
- track_info = self._parse_json(
- self._search_regex(
- r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n',
- webpage, 'track info', default='{}'), title)
+ trackinfo_block = self._search_regex(
+ r'trackinfo":\[\s*({.+?})\s*\],"',
+ webpage, 'track info', default='{}')
+ quoted_json = trackinfo_block.replace('"', '"')
+ track_info = self._parse_json(quoted_json, title)
if track_info:
file_ = track_info.get('file')
if isinstance(file_, dict):
@@ -117,7 +118,7 @@ class BandcampIE(InfoExtractor):
def extract(key):
return self._search_regex(
- r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key,
+ r',"%s":(")(?P<value>(?:(?!").)+)"' % key,
webpage, key, default=None, group='value')
artist = extract('artist')
--
2.27.0
|