diff options
Diffstat (limited to 'hypervideo_dl/extractor/bandcamp.py')
| -rw-r--r-- | hypervideo_dl/extractor/bandcamp.py | 23 |
1 files changed, 10 insertions, 13 deletions
diff --git a/hypervideo_dl/extractor/bandcamp.py b/hypervideo_dl/extractor/bandcamp.py index 745055e..de81e0d 100644 --- a/hypervideo_dl/extractor/bandcamp.py +++ b/hypervideo_dl/extractor/bandcamp.py @@ -1,6 +1,3 @@ -# coding: utf-8 -from __future__ import unicode_literals - import random import re import time @@ -8,23 +5,24 @@ import time from .common import InfoExtractor from ..compat import compat_str from ..utils import ( + KNOWN_EXTENSIONS, ExtractorError, float_or_none, int_or_none, - KNOWN_EXTENSIONS, parse_filesize, str_or_none, try_get, - update_url_query, unified_strdate, unified_timestamp, + update_url_query, url_or_none, urljoin, ) class BandcampIE(InfoExtractor): - _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)' + _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"'] _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', 'md5': 'c557841d5e50261777a6585648adf439', @@ -87,7 +85,7 @@ class BandcampIE(InfoExtractor): attr + ' data', group=2), video_id, fatal=fatal) def _real_extract(self, url): - title = self._match_id(url) + title, uploader = self._match_valid_url(url).group('id', 'uploader') webpage = self._download_webpage(url, title) tralbum = self._extract_data_attr(webpage, title) thumbnail = self._og_search_thumbnail(webpage) @@ -186,8 +184,6 @@ class BandcampIE(InfoExtractor): 'acodec': format_id.split('-')[0], }) - self._sort_formats(formats) - title = '%s - %s' % (artist, track) if artist else track if not duration: @@ -199,6 +195,8 @@ class BandcampIE(InfoExtractor): 'title': title, 'thumbnail': thumbnail, 'uploader': artist, + 'uploader_id': uploader, + 'uploader_url': f'https://{uploader}.bandcamp.com', 'timestamp': timestamp, 'release_timestamp': unified_timestamp(tralbum.get('album_release_date')), 'duration': duration, @@ -211,7 +209,7 @@ class BandcampIE(InfoExtractor): } -class BandcampAlbumIE(BandcampIE): +class BandcampAlbumIE(BandcampIE): # XXX: Do not subclass from concrete IE IE_NAME = 'Bandcamp:album' _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)' @@ -314,7 +312,7 @@ class BandcampAlbumIE(BandcampIE): } -class BandcampWeeklyIE(BandcampIE): +class BandcampWeeklyIE(BandcampIE): # XXX: Do not subclass from concrete IE IE_NAME = 'Bandcamp:weekly' _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)' _TESTS = [{ @@ -363,7 +361,6 @@ class BandcampWeeklyIE(BandcampIE): 'ext': ext, 'vcodec': 'none', }) - self._sort_formats(formats) title = show.get('audio_title') or 'Bandcamp Weekly' subtitle = show.get('subtitle') @@ -439,7 +436,7 @@ class BandcampUserIE(InfoExtractor): uploader = self._match_id(url) webpage = self._download_webpage(url, uploader) - discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\']([^"\']+)', webpage) + discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\'](?![^"\'/]*?/merch)([^"\']+)', webpage) or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage)) return self.playlist_from_matches( |