MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-28 07:36:52 +01:00
Code Issues Projects Releases Wiki Activity

[bandcamp] fix test song uploader name, cleanup remanings " and \ in data, including album titles

Browse Source
This commit is contained in:
Gilles Pietri 2020-09-28 19:42:56 +02:00
parent 37f625598c
commit 75a83afe3b
1 changed files with 15 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/bandcamp.py
View File

@ -33,9 +33,9 @@ class BandcampIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1812978515', 'id': '1812978515',
'ext': 'mp3', 'ext': 'mp3',
'title': "youtube-dl \\ - youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
'duration': 9.8485, 'duration': 9.8485,
'uploader': 'youtube-dl \\', 'uploader': "youtube-dl \"'/\\\u00e4\u21ad",
'timestamp': 1354224127, 'timestamp': 1354224127,
'upload_date': '20121129', 'upload_date': '20121129',
}, },
@ -43,7 +43,7 @@ class BandcampIE(InfoExtractor):
}, { }, {
# free download # free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle', 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'md5': '853e35bf34aa1d6fe2615ae612564b36', 'md5': '5d92af55811e47f38962a54c30b07ef0',
'info_dict': { 'info_dict': {
'id': '2650410135', 'id': '2650410135',
'ext': 'aiff', 'ext': 'aiff',
@ -94,11 +94,12 @@ def _real_extract(self, url):
duration = None duration = None
formats = [] formats = []
trackinfo_block = self._search_regex( trackinfo_block = self._html_search_regex(
r'trackinfo(?:["\']|"):\[\s*({.+?})\s*\],(?:["\']|")', r'trackinfo(?:["\']|"):\[\s*({.+?})\s*\],(?:["\']|")',
webpage, 'track info', default='{}') webpage, 'track info', default='{}')
unescaped_json = unescapeHTML(trackinfo_block)
track_info = self._parse_json(unescaped_json, title) track_info = self._parse_json(trackinfo_block, title)
if track_info: if track_info:
file_ = track_info.get('file') file_ = track_info.get('file')
if isinstance(file_, dict): if isinstance(file_, dict):
@ -120,9 +121,10 @@ def _real_extract(self, url):
duration = float_or_none(track_info.get('duration')) duration = float_or_none(track_info.get('duration'))
def extract(key): def extract(key):
return self._search_regex( data = self._html_search_regex(
r',(["\']|&quot;)%s\1:\1(?P<value>(?:(?!\1).)+)\1' % key, r',(["\']|&quot;)%s\1:\1(?P<value>(?:\\\1|((?!\1).))+)\1' % key,
webpage, key, default=None, group='value') webpage, key, default=None, group='value')
return data.replace(r'\"', '"').replace('\\\\', '\\') if data else data
artist = extract('artist') artist = extract('artist')
album = extract('album_title') album = extract('album_title')
@ -319,10 +321,12 @@ def _real_extract(self, url):
if self._html_search_meta('duration', elem_content, default=None)] if self._html_search_meta('duration', elem_content, default=None)]
title = self._html_search_regex( title = self._html_search_regex(
r'album_title\s*(?:&quot;|["\']):\s*(?:&quot;|["\'])((?:\\.|[^"\\])+?)(?:&quot;|["\'])', r'album_title\s*(?:&quot;|["\']):\s*(&quot;|["\'])(?P<album>(?:\\\1|((?!\1).))+)\1',
webpage, 'title', fatal=False) webpage, 'title', fatal=False, group='album')
if title: if title:
title = unescapeHTML(title) title = title.replace(r'\"', '"')
return { return {
'_type': 'playlist', '_type': 'playlist',
'uploader_id': uploader_id, 'uploader_id': uploader_id,