Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 20:16:06 +08:00
Code Issues Releases Wiki Activity

[bandcamp] Extract more metadata

Browse Source
This commit is contained in:
rr- 2017-08-30 12:01:19 +02:00
parent 53647dfd0a
commit 471f398772
2 changed files with 65 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
test/helper.py
View File

@ -186,7 +186,7 @@ def expect_info_dict(self, got_dict, expected_dict):
# Are checkable fields missing from the test case definition? # Are checkable fields missing from the test case definition?
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value)) test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in got_dict.items() for key, value in got_dict.items()
if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit')) if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location', 'age_limit', 'album', 'artist', 'track', 'track_number', 'release_year', 'release_date'))
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys()) missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
if missing_keys: if missing_keys:
def _repr(v): def _repr(v):

80
youtube_dl/extractor/bandcamp.py
View File

@ -30,8 +30,11 @@ class BandcampIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1812978515', 'id': '1812978515',
'ext': 'mp3', 'ext': 'mp3',
'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", 'track': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
'title': "youtube-dl \\ - youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
'duration': 9.8485, 'duration': 9.8485,
'uploader': 'youtube-dl \\',
'artist': 'youtube-dl \\',
}, },
'_skip': 'There is a limit of 200 free downloads / month for the test song' '_skip': 'There is a limit of 200 free downloads / month for the test song'
}, { }, {
@ -40,8 +43,29 @@ class BandcampIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '2650410135', 'id': '2650410135',
'ext': 'aiff', 'ext': 'aiff',
'title': 'Ben Prunty - Lanius (Battle)', 'album': 'FTL: Advanced Edition Soundtrack',
'artist': 'Ben Prunty',
'uploader': 'Ben Prunty', 'uploader': 'Ben Prunty',
'release_date': '20140403',
'release_year': 2014,
'track_number': 1,
'track': 'Lanius (Battle)',
'title': 'Ben Prunty - Lanius (Battle)',
},
}, {
'url': 'https://billbaxter.bandcamp.com/track/drone-city-pt-3-3',
'md5': 'e8e24365cb38ff841b4e5df014f988ed',
'info_dict': {
'id': '3755531036',
'ext': 'mp3',
'album': 'Drone City',
'artist': 'The ambient drones of Bill Baxter',
'uploader': 'The ambient drones of Bill Baxter',
'release_date': '20160326',
'release_year': 2016,
'track_number': 3,
'track': 'Drone City, Pt. 3',
'title': 'The ambient drones of Bill Baxter - Drone City, Pt. 3',
}, },
}] }]
@ -51,11 +75,25 @@ class BandcampIE(InfoExtractor):
webpage = self._download_webpage(url, title) webpage = self._download_webpage(url, title)
thumbnail = self._html_search_meta('og:image', webpage, default=None) thumbnail = self._html_search_meta('og:image', webpage, default=None)
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
json_code = m_trackinfo.group(1) if m_trackinfo else None
data = json.loads(json_code)[0] if json_code else None
match = re.search(r'album_title\s*:\s*"([^"]+)"', webpage)
album_title = match.group(1) if match else None
match = re.search(r'artist\s*:\s*"([^"]+)"', webpage)
artist = match.group(1) if match else None
match = re.search(r'album_release_date\s*:\s*"([^"]+)"', webpage)
release_date = unified_strdate(match.group(1)) if match else None
release_year = int(release_date[0:4]) if release_date else None
track = data['title'] if data else None
title = '%s - %s' % (artist, track) if artist else track
if not m_download: if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) if data:
if m_trackinfo:
json_code = m_trackinfo.group(1)
data = json.loads(json_code)[0]
track_id = compat_str(data['id']) track_id = compat_str(data['id'])
if not data.get('file'): if not data.get('file'):
@ -77,7 +115,15 @@ class BandcampIE(InfoExtractor):
return { return {
'id': track_id, 'id': track_id,
'title': data['title'], 'album': album_title,
'uploader': artist,
'artist': artist,
'track_id': track_id,
'track_number': data.get('track_num'),
'release_date': release_date,
'release_year': release_year,
'track': track,
'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'formats': formats, 'formats': formats,
'duration': float_or_none(data.get('duration')), 'duration': float_or_none(data.get('duration')),
@ -99,13 +145,9 @@ class BandcampIE(InfoExtractor):
'blob', group='blob'), 'blob', group='blob'),
video_id, transform_source=unescapeHTML) video_id, transform_source=unescapeHTML)
info = blob['digital_items'][0] digital_items = blob['digital_items'][0]
downloads = info['downloads'] downloads = digital_items['downloads']
track = info['title']
artist = info.get('artist')
title = '%s - %s' % (artist, track) if artist else track
download_formats = {} download_formats = {}
for f in blob['download_formats']: for f in blob['download_formats']:
@ -146,10 +188,16 @@ class BandcampIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'title': title, 'album': album_title,
'thumbnail': info.get('thumb_url') or thumbnail, 'uploader': artist,
'uploader': info.get('artist'),
'artist': artist, 'artist': artist,
'track_id': video_id,
'track_number': data.get('track_num'),
'release_date': release_date,
'release_year': release_year,
'track': track,
'title': title,
'thumbnail': digital_items.get('thumb_url') or thumbnail,
'track': track, 'track': track,
'formats': formats, 'formats': formats,
} }