[yt-dlp.git] / yt_dlp / extractor / bandcamp.py

import random
import re
import time

from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
    KNOWN_EXTENSIONS,
    ExtractorError,
    float_or_none,
    int_or_none,
    parse_filesize,
    str_or_none,
    try_get,
    unified_strdate,
    unified_timestamp,
    update_url_query,
    url_or_none,
    urljoin,
)


class BandcampIE(InfoExtractor):
    _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',
        'info_dict': {
            'id': '1812978515',
            'ext': 'mp3',
            'title': "youtube-dl  \"'/\\ä↭ - youtube-dl  \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭",
            'duration': 9.8485,
            'uploader': 'youtube-dl  "\'/\\ä↭',
            'upload_date': '20121129',
            'timestamp': 1354224127,
        },
        '_skip': 'There is a limit of 200 free downloads / month for the test song'
    }, {
        # free download
        'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
        'info_dict': {
            'id': '2650410135',
            'ext': 'aiff',
            'title': 'Ben Prunty - Lanius (Battle)',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Ben Prunty',
            'timestamp': 1396508491,
            'upload_date': '20140403',
            'release_timestamp': 1396483200,
            'release_date': '20140403',
            'duration': 260.877,
            'track': 'Lanius (Battle)',
            'track_number': 1,
            'track_id': '2650410135',
            'artist': 'Ben Prunty',
            'album': 'FTL: Advanced Edition Soundtrack',
        },
    }, {
        # no free download, mp3 128
        'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
        'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
        'info_dict': {
            'id': '2584466013',
            'ext': 'mp3',
            'title': 'Mastodon - Hail to Fire',
            'thumbnail': r're:^https?://.*\.jpg$',
            'uploader': 'Mastodon',
            'timestamp': 1322005399,
            'upload_date': '20111122',
            'release_timestamp': 1076112000,
            'release_date': '20040207',
            'duration': 120.79,
            'track': 'Hail to Fire',
            'track_number': 5,
            'track_id': '2584466013',
            'artist': 'Mastodon',
            'album': 'Call of the Mastodon',
        },
    }]

    def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
        return self._parse_json(self._html_search_regex(
            r'data-%s=(["\'])({.+?})\1' % attr, webpage,
            attr + ' data', group=2), video_id, fatal=fatal)

    def _real_extract(self, 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)

        track_id = None
        track = None
        track_number = None
        duration = None

        formats = []
        track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict)
        if track_info:
            file_ = track_info.get('file')
            if isinstance(file_, dict):
                for format_id, format_url in file_.items():
                    if not url_or_none(format_url):
                        continue
                    ext, abr_str = format_id.split('-', 1)
                    formats.append({
                        'format_id': format_id,
                        'url': self._proto_relative_url(format_url, 'http:'),
                        'ext': ext,
                        'vcodec': 'none',
                        'acodec': ext,
                        'abr': int_or_none(abr_str),
                    })
            track = track_info.get('title')
            track_id = str_or_none(
                track_info.get('track_id') or track_info.get('id'))
            track_number = int_or_none(track_info.get('track_num'))
            duration = float_or_none(track_info.get('duration'))

        embed = self._extract_data_attr(webpage, title, 'embed', False)
        current = tralbum.get('current') or {}
        artist = embed.get('artist') or current.get('artist') or tralbum.get('artist')
        timestamp = unified_timestamp(
            current.get('publish_date') or tralbum.get('album_publish_date'))

        download_link = tralbum.get('freeDownloadPage')
        if download_link:
            track_id = compat_str(tralbum['id'])

            download_webpage = self._download_webpage(
                download_link, track_id, 'Downloading free downloads page')

            blob = self._extract_data_attr(download_webpage, track_id, 'blob')

            info = try_get(
                blob, (lambda x: x['digital_items'][0],
                       lambda x: x['download_items'][0]), dict)
            if info:
                downloads = info.get('downloads')
                if isinstance(downloads, dict):
                    if not track:
                        track = info.get('title')
                    if not artist:
                        artist = info.get('artist')
                    if not thumbnail:
                        thumbnail = info.get('thumb_url')

                    download_formats = {}
                    download_formats_list = blob.get('download_formats')
                    if isinstance(download_formats_list, list):
                        for f in blob['download_formats']:
                            name, ext = f.get('name'), f.get('file_extension')
                            if all(isinstance(x, compat_str) for x in (name, ext)):
                                download_formats[name] = ext.strip('.')

                    for format_id, f in downloads.items():
                        format_url = f.get('url')
                        if not format_url:
                            continue
                        # Stat URL generation algorithm is reverse engineered from
                        # download_*_bundle_*.js
                        stat_url = update_url_query(
                            format_url.replace('/download/', '/statdownload/'), {
                                '.rand': int(time.time() * 1000 * random.random()),
                            })
                        format_id = f.get('encoding_name') or format_id
                        stat = self._download_json(
                            stat_url, track_id, 'Downloading %s JSON' % format_id,
                            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
                            fatal=False)
                        if not stat:
                            continue
                        retry_url = url_or_none(stat.get('retry_url'))
                        if not retry_url:
                            continue
                        formats.append({
                            'url': self._proto_relative_url(retry_url, 'http:'),
                            'ext': download_formats.get(format_id),
                            'format_id': format_id,
                            'format_note': f.get('description'),
                            'filesize': parse_filesize(f.get('size_mb')),
                            'vcodec': 'none',
                            'acodec': format_id.split('-')[0],
                        })

        self._sort_formats(formats)

        title = '%s - %s' % (artist, track) if artist else track

        if not duration:
            duration = float_or_none(self._html_search_meta(
                'duration', webpage, default=None))

        return {
            'id': track_id,
            '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,
            'track': track,
            'track_number': track_number,
            'track_id': track_id,
            'artist': artist,
            'album': embed.get('album_title'),
            'formats': formats,
        }


class BandcampAlbumIE(BandcampIE):
    IE_NAME = 'Bandcamp:album'
    _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'

    _TESTS = [{
        'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
        'playlist': [
            {
                'md5': '39bc1eded3476e927c724321ddf116cf',
                'info_dict': {
                    'id': '1353101989',
                    'ext': 'mp3',
                    'title': 'Blazo - Intro',
                    'timestamp': 1311756226,
                    'upload_date': '20110727',
                    'uploader': 'Blazo',
                }
            },
            {
                'md5': '1a2c32e2691474643e912cc6cd4bffaa',
                'info_dict': {
                    'id': '38097443',
                    'ext': 'mp3',
                    'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
                    'timestamp': 1311757238,
                    'upload_date': '20110727',
                    'uploader': 'Blazo',
                }
            },
        ],
        'info_dict': {
            'title': 'Jazz Format Mixtape vol.1',
            'id': 'jazz-format-mixtape-vol-1',
            'uploader_id': 'blazo',
        },
        'params': {
            'playlistend': 2
        },
        'skip': 'Bandcamp imposes download limits.'
    }, {
        'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
        'info_dict': {
            'title': 'Hierophany of the Open Grave',
            'uploader_id': 'nightbringer',
            'id': 'hierophany-of-the-open-grave',
        },
        'playlist_mincount': 9,
    }, {
        # with escaped quote in title
        'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
        'info_dict': {
            'title': '"Entropy" EP',
            'uploader_id': 'jstrecords',
            'id': 'entropy-ep',
            'description': 'md5:0ff22959c943622972596062f2f366a5',
        },
        'playlist_mincount': 3,
    }, {
        # not all tracks have songs
        'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
        'info_dict': {
            'id': 'we-are-the-plague',
            'title': 'WE ARE THE PLAGUE',
            'uploader_id': 'insulters',
            'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
        },
        'playlist_count': 2,
    }]

    @classmethod
    def suitable(cls, url):
        return (False
                if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
                else super(BandcampAlbumIE, cls).suitable(url))

    def _real_extract(self, url):
        uploader_id, album_id = self._match_valid_url(url).groups()
        playlist_id = album_id or uploader_id
        webpage = self._download_webpage(url, playlist_id)
        tralbum = self._extract_data_attr(webpage, playlist_id)
        track_info = tralbum.get('trackinfo')
        if not track_info:
            raise ExtractorError('The page doesn\'t contain any tracks')
        # Only tracks with duration info have songs
        entries = [
            self.url_result(
                urljoin(url, t['title_link']), BandcampIE.ie_key(),
                str_or_none(t.get('track_id') or t.get('id')), t.get('title'))
            for t in track_info
            if t.get('duration')]

        current = tralbum.get('current') or {}

        return {
            '_type': 'playlist',
            'uploader_id': uploader_id,
            'id': playlist_id,
            'title': current.get('title'),
            'description': current.get('about'),
            'entries': entries,
        }


class BandcampWeeklyIE(BandcampIE):
    IE_NAME = 'Bandcamp:weekly'
    _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
    _TESTS = [{
        'url': 'https://bandcamp.com/?show=224',
        'md5': 'b00df799c733cf7e0c567ed187dea0fd',
        'info_dict': {
            'id': '224',
            'ext': 'opus',
            'title': 'BC Weekly April 4th 2017 - Magic Moments',
            'description': 'md5:5d48150916e8e02d030623a48512c874',
            'duration': 5829.77,
            'release_date': '20170404',
            'series': 'Bandcamp Weekly',
            'episode': 'Magic Moments',
            'episode_id': '224',
        },
        'params': {
            'format': 'opus-lo',
        },
    }, {
        'url': 'https://bandcamp.com/?blah/blah@&show=228',
        'only_matching': True
    }]

    def _real_extract(self, url):
        show_id = self._match_id(url)
        webpage = self._download_webpage(url, show_id)

        blob = self._extract_data_attr(webpage, show_id, 'blob')

        show = blob['bcw_data'][show_id]

        formats = []
        for format_id, format_url in show['audio_stream'].items():
            if not url_or_none(format_url):
                continue
            for known_ext in KNOWN_EXTENSIONS:
                if known_ext in format_id:
                    ext = known_ext
                    break
            else:
                ext = None
            formats.append({
                'format_id': format_id,
                'url': format_url,
                'ext': ext,
                'vcodec': 'none',
            })
        self._sort_formats(formats)

        title = show.get('audio_title') or 'Bandcamp Weekly'
        subtitle = show.get('subtitle')
        if subtitle:
            title += ' - %s' % subtitle

        return {
            'id': show_id,
            'title': title,
            'description': show.get('desc') or show.get('short_desc'),
            'duration': float_or_none(show.get('audio_duration')),
            'is_live': False,
            'release_date': unified_strdate(show.get('published_date')),
            'series': 'Bandcamp Weekly',
            'episode': show.get('subtitle'),
            'episode_id': show_id,
            'formats': formats
        }


class BandcampUserIE(InfoExtractor):
    IE_NAME = 'Bandcamp:user'
    _VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)'

    _TESTS = [{
        # Type 1 Bandcamp user page.
        'url': 'https://adrianvonziegler.bandcamp.com',
        'info_dict': {
            'id': 'adrianvonziegler',
            'title': 'Discography of adrianvonziegler',
        },
        'playlist_mincount': 23,
    }, {
        # Bandcamp user page with only one album
        'url': 'http://dotscale.bandcamp.com',
        'info_dict': {
            'id': 'dotscale',
            'title': 'Discography of dotscale'
        },
        'playlist_count': 1,
    }, {
        # Type 2 Bandcamp user page.
        'url': 'https://nightcallofficial.bandcamp.com',
        'info_dict': {
            'id': 'nightcallofficial',
            'title': 'Discography of nightcallofficial',
        },
        'playlist_count': 4,
    }, {
        'url': 'https://steviasphere.bandcamp.com/music',
        'playlist_mincount': 47,
        'info_dict': {
            'id': 'steviasphere',
            'title': 'Discography of steviasphere',
        },
    }, {
        'url': 'https://coldworldofficial.bandcamp.com/music',
        'playlist_mincount': 10,
        'info_dict': {
            'id': 'coldworldofficial',
            'title': 'Discography of coldworldofficial',
        },
    }, {
        'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
        'playlist_mincount': 399,
        'info_dict': {
            'id': 'nuclearwarnowproductions',
            'title': 'Discography of nuclearwarnowproductions',
        },
    }]

    def _real_extract(self, url):
        uploader = self._match_id(url)
        webpage = self._download_webpage(url, uploader)

        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(
            discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
Commit	Line	Data
0aacd2de	1	import random
45aef472	2	import re
0aacd2de	3	import time
45aef472 PH	4
45aef472 PH	5	from .common import InfoExtractor
8bdd16b4	6	from ..compat import compat_str
1cc79574	7	from ..utils import (
304ad45a	8	KNOWN_EXTENSIONS,
45aef472	9	ExtractorError,
ba717dca S	10	float_or_none,
ba717dca S	11	int_or_none,
0aacd2de	12	parse_filesize,
4991e16c S	13	str_or_none,
4991e16c S	14	try_get,
62bafabc	15	unified_strdate,
4991e16c	16	unified_timestamp,
304ad45a	17	update_url_query,
3052a30d	18	url_or_none,
8bdd16b4	19	urljoin,
45aef472 PH	20	)
	21
	22
8bdd16b4	23	class BandcampIE(InfoExtractor):
2c475e48	24	_VALID_URL = r'https?://(?P<uploader>[^/]+)\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
bfd973ec	25	_EMBED_REGEX = [r'<meta property="og:url"[^>]?content="(?P<url>.?bandcamp\.com.*?)"']
cffa6aa1	26	_TESTS = [{
3467b3e2	27	'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
3798eadc PH	28	'md5': 'c557841d5e50261777a6585648adf439',
3798eadc PH	29	'info_dict': {
d9bf4652 S	30	'id': '1812978515',
d9bf4652 S	31	'ext': 'mp3',
8bdd16b4	32	'title': "youtube-dl \"'/\\ä↭ - youtube-dl \"'/\\ä↭ - youtube-dl test song \"'/\\ä↭",
d9bf4652	33	'duration': 9.8485,
8bdd16b4	34	'uploader': 'youtube-dl "\'/\\ä↭',
3a379e5e	35	'upload_date': '20121129',
8bdd16b4	36	'timestamp': 1354224127,
6f5ac90c	37	},
3798eadc	38	'_skip': 'There is a limit of 200 free downloads / month for the test song'
d9bf4652	39	}, {
4991e16c	40	# free download
d9bf4652	41	'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
d9bf4652 S	42	'info_dict': {
d9bf4652 S	43	'id': '2650410135',
0f63dc24 TF	44	'ext': 'aiff',
0f63dc24 TF	45	'title': 'Ben Prunty - Lanius (Battle)',
4991e16c	46	'thumbnail': r're:^https?://.*\.jpg$',
0f63dc24	47	'uploader': 'Ben Prunty',
4991e16c S	48	'timestamp': 1396508491,
4991e16c S	49	'upload_date': '20140403',
10db0d2f	50	'release_timestamp': 1396483200,
4991e16c S	51	'release_date': '20140403',
	52	'duration': 260.877,
	53	'track': 'Lanius (Battle)',
	54	'track_number': 1,
	55	'track_id': '2650410135',
	56	'artist': 'Ben Prunty',
	57	'album': 'FTL: Advanced Edition Soundtrack',
d9bf4652	58	},
14b7a24c	59	}, {
4991e16c	60	# no free download, mp3 128
14b7a24c	61	'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
4991e16c	62	'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
14b7a24c PV	63	'info_dict': {
	64	'id': '2584466013',
	65	'ext': 'mp3',
4991e16c S	66	'title': 'Mastodon - Hail to Fire',
	67	'thumbnail': r're:^https?://.*\.jpg$',
	68	'uploader': 'Mastodon',
	69	'timestamp': 1322005399,
	70	'upload_date': '20111122',
10db0d2f	71	'release_timestamp': 1076112000,
4991e16c S	72	'release_date': '20040207',
	73	'duration': 120.79,
	74	'track': 'Hail to Fire',
14b7a24c	75	'track_number': 5,
4991e16c S	76	'track_id': '2584466013',
	77	'artist': 'Mastodon',
	78	'album': 'Call of the Mastodon',
14b7a24c	79	},
cffa6aa1	80	}]
45aef472	81
8bdd16b4	82	def _extract_data_attr(self, webpage, video_id, attr='tralbum', fatal=True):
	83	return self._parse_json(self._html_search_regex(
	84	r'data-%s=(["\'])({.+?})\1' % attr, webpage,
	85	attr + ' data', group=2), video_id, fatal=fatal)
	86
45aef472	87	def _real_extract(self, url):
2c475e48	88	title, uploader = self._match_valid_url(url).group('id', 'uploader')
45aef472	89	webpage = self._download_webpage(url, title)
8bdd16b4	90	tralbum = self._extract_data_attr(webpage, title)
	91	thumbnail = self._og_search_thumbnail(webpage)
	92
	93	track_id = None
	94	track = None
	95	track_number = None
	96	duration = None
	97
	98	formats = []
	99	track_info = try_get(tralbum, lambda x: x['trackinfo'][0], dict)
	100	if track_info:
	101	file_ = track_info.get('file')
	102	if isinstance(file_, dict):
	103	for format_id, format_url in file_.items():
	104	if not url_or_none(format_url):
	105	continue
	106	ext, abr_str = format_id.split('-', 1)
	107	formats.append({
	108	'format_id': format_id,
	109	'url': self._proto_relative_url(format_url, 'http:'),
	110	'ext': ext,
	111	'vcodec': 'none',
	112	'acodec': ext,
	113	'abr': int_or_none(abr_str),
	114	})
	115	track = track_info.get('title')
	116	track_id = str_or_none(
	117	track_info.get('track_id') or track_info.get('id'))
	118	track_number = int_or_none(track_info.get('track_num'))
	119	duration = float_or_none(track_info.get('duration'))
	120
	121	embed = self._extract_data_attr(webpage, title, 'embed', False)
	122	current = tralbum.get('current') or {}
	123	artist = embed.get('artist') or current.get('artist') or tralbum.get('artist')
	124	timestamp = unified_timestamp(
	125	current.get('publish_date') or tralbum.get('album_publish_date'))
	126
	127	download_link = tralbum.get('freeDownloadPage')
4991e16c	128	if download_link:
8bdd16b4	129	track_id = compat_str(tralbum['id'])
4991e16c S	130
	131	download_webpage = self._download_webpage(
	132	download_link, track_id, 'Downloading free downloads page')
	133
8bdd16b4	134	blob = self._extract_data_attr(download_webpage, track_id, 'blob')
4991e16c S	135
	136	info = try_get(
	137	blob, (lambda x: x['digital_items'][0],
	138	lambda x: x['download_items'][0]), dict)
	139	if info:
	140	downloads = info.get('downloads')
	141	if isinstance(downloads, dict):
8bdd16b4	142	if not track:
8bdd16b4	143	track = info.get('title')
4991e16c S	144	if not artist:
	145	artist = info.get('artist')
	146	if not thumbnail:
	147	thumbnail = info.get('thumb_url')
	148
	149	download_formats = {}
	150	download_formats_list = blob.get('download_formats')
	151	if isinstance(download_formats_list, list):
	152	for f in blob['download_formats']:
	153	name, ext = f.get('name'), f.get('file_extension')
	154	if all(isinstance(x, compat_str) for x in (name, ext)):
	155	download_formats[name] = ext.strip('.')
	156
	157	for format_id, f in downloads.items():
	158	format_url = f.get('url')
	159	if not format_url:
	160	continue
	161	# Stat URL generation algorithm is reverse engineered from
	162	# download__bundle_.js
	163	stat_url = update_url_query(
	164	format_url.replace('/download/', '/statdownload/'), {
	165	'.rand': int(time.time() * 1000 * random.random()),
	166	})
	167	format_id = f.get('encoding_name') or format_id
	168	stat = self._download_json(
	169	stat_url, track_id, 'Downloading %s JSON' % format_id,
	170	transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
	171	fatal=False)
	172	if not stat:
	173	continue
	174	retry_url = url_or_none(stat.get('retry_url'))
	175	if not retry_url:
	176	continue
8bdd16b4	177	formats.append({
4991e16c S	178	'url': self._proto_relative_url(retry_url, 'http:'),
	179	'ext': download_formats.get(format_id),
	180	'format_id': format_id,
	181	'format_note': f.get('description'),
	182	'filesize': parse_filesize(f.get('size_mb')),
	183	'vcodec': 'none',
933dbf5a	184	'acodec': format_id.split('-')[0],
4991e16c	185	})
5ecd3c6a	186
8bdd16b4	187	self._sort_formats(formats)
0aacd2de	188
8bdd16b4	189	title = '%s - %s' % (artist, track) if artist else track
	190
	191	if not duration:
	192	duration = float_or_none(self._html_search_meta(
	193	'duration', webpage, default=None))
45aef472	194
5ecd3c6a	195	return {
8bdd16b4	196	'id': track_id,
8bdd16b4	197	'title': title,
4991e16c	198	'thumbnail': thumbnail,
8bdd16b4	199	'uploader': artist,
2c475e48	200	'uploader_id': uploader,
2c475e48	201	'uploader_url': f'https://{uploader}.bandcamp.com',
4991e16c	202	'timestamp': timestamp,
10db0d2f	203	'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
8bdd16b4	204	'duration': duration,
	205	'track': track,
	206	'track_number': track_number,
	207	'track_id': track_id,
	208	'artist': artist,
	209	'album': embed.get('album_title'),
	210	'formats': formats,
5ecd3c6a	211	}
09804265 JMF	212
09804265 JMF	213
8bdd16b4	214	class BandcampAlbumIE(BandcampIE):
3798eadc	215	IE_NAME = 'Bandcamp:album'
85a0ad01	216	_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
09804265	217
22a6f150	218	_TESTS = [{
3798eadc PH	219	'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
3798eadc PH	220	'playlist': [
d35dc6d3	221	{
3798eadc PH	222	'md5': '39bc1eded3476e927c724321ddf116cf',
3798eadc PH	223	'info_dict': {
13ba3a64 PH	224	'id': '1353101989',
13ba3a64 PH	225	'ext': 'mp3',
8bdd16b4	226	'title': 'Blazo - Intro',
	227	'timestamp': 1311756226,
	228	'upload_date': '20110727',
	229	'uploader': 'Blazo',
d35dc6d3 JMF	230	}
	231	},
	232	{
3798eadc PH	233	'md5': '1a2c32e2691474643e912cc6cd4bffaa',
3798eadc PH	234	'info_dict': {
13ba3a64 PH	235	'id': '38097443',
13ba3a64 PH	236	'ext': 'mp3',
8bdd16b4	237	'title': 'Blazo - Kero One - Keep It Alive (Blazo remix)',
	238	'timestamp': 1311757238,
	239	'upload_date': '20110727',
	240	'uploader': 'Blazo',
d35dc6d3 JMF	241	}
	242	},
	243	],
13ba3a64 PH	244	'info_dict': {
13ba3a64 PH	245	'title': 'Jazz Format Mixtape vol.1',
72c1f8de PH	246	'id': 'jazz-format-mixtape-vol-1',
72c1f8de PH	247	'uploader_id': 'blazo',
13ba3a64	248	},
3798eadc PH	249	'params': {
3798eadc PH	250	'playlistend': 2
d35dc6d3	251	},
72c1f8de	252	'skip': 'Bandcamp imposes download limits.'
22a6f150 PH	253	}, {
	254	'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
	255	'info_dict': {
	256	'title': 'Hierophany of the Open Grave',
72c1f8de PH	257	'uploader_id': 'nightbringer',
72c1f8de PH	258	'id': 'hierophany-of-the-open-grave',
22a6f150 PH	259	},
22a6f150 PH	260	'playlist_mincount': 9,
64fc49ab S	261	}, {
	262	# with escaped quote in title
	263	'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
	264	'info_dict': {
	265	'title': '"Entropy" EP',
	266	'uploader_id': 'jstrecords',
	267	'id': 'entropy-ep',
8bdd16b4	268	'description': 'md5:0ff22959c943622972596062f2f366a5',
64fc49ab S	269	},
64fc49ab S	270	'playlist_mincount': 3,
019f4c03 YCH	271	}, {
	272	# not all tracks have songs
	273	'url': 'https://insulters.bandcamp.com/album/we-are-the-plague',
	274	'info_dict': {
	275	'id': 'we-are-the-plague',
	276	'title': 'WE ARE THE PLAGUE',
	277	'uploader_id': 'insulters',
8bdd16b4	278	'description': 'md5:b3cf845ee41b2b1141dc7bde9237255f',
019f4c03 YCH	279	},
019f4c03 YCH	280	'playlist_count': 2,
22a6f150	281	}]
d35dc6d3	282
62bafabc AV	283	@classmethod
62bafabc AV	284	def suitable(cls, url):
6d923aab S	285	return (False
	286	if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
	287	else super(BandcampAlbumIE, cls).suitable(url))
62bafabc	288
09804265	289	def _real_extract(self, url):
5ad28e7f	290	uploader_id, album_id = self._match_valid_url(url).groups()
72c1f8de PH	291	playlist_id = album_id or uploader_id
72c1f8de PH	292	webpage = self._download_webpage(url, playlist_id)
8bdd16b4	293	tralbum = self._extract_data_attr(webpage, playlist_id)
	294	track_info = tralbum.get('trackinfo')
	295	if not track_info:
	296	raise ExtractorError('The page doesn\'t contain any tracks')
019f4c03	297	# Only tracks with duration info have songs
09804265	298	entries = [
8239c679	299	self.url_result(
8bdd16b4	300	urljoin(url, t['title_link']), BandcampIE.ie_key(),
	301	str_or_none(t.get('track_id') or t.get('id')), t.get('title'))
	302	for t in track_info
	303	if t.get('duration')]
	304
	305	current = tralbum.get('current') or {}
3a379e5e	306
09804265 JMF	307	return {
09804265 JMF	308	'_type': 'playlist',
72c1f8de	309	'uploader_id': uploader_id,
b48f147d	310	'id': playlist_id,
8bdd16b4	311	'title': current.get('title'),
	312	'description': current.get('about'),
	313	'entries': entries,
09804265	314	}
62bafabc AV	315
62bafabc AV	316
8bdd16b4	317	class BandcampWeeklyIE(BandcampIE):
6d923aab S	318	IE_NAME = 'Bandcamp:weekly'
6d923aab S	319	_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
62bafabc AV	320	_TESTS = [{
	321	'url': 'https://bandcamp.com/?show=224',
	322	'md5': 'b00df799c733cf7e0c567ed187dea0fd',
	323	'info_dict': {
	324	'id': '224',
	325	'ext': 'opus',
6d923aab S	326	'title': 'BC Weekly April 4th 2017 - Magic Moments',
	327	'description': 'md5:5d48150916e8e02d030623a48512c874',
	328	'duration': 5829.77,
	329	'release_date': '20170404',
	330	'series': 'Bandcamp Weekly',
	331	'episode': 'Magic Moments',
6d923aab	332	'episode_id': '224',
8bdd16b4	333	},
	334	'params': {
	335	'format': 'opus-lo',
	336	},
62bafabc AV	337	}, {
	338	'url': 'https://bandcamp.com/?blah/blah@&show=228',
	339	'only_matching': True
	340	}]
	341
	342	def _real_extract(self, url):
8bdd16b4	343	show_id = self._match_id(url)
8bdd16b4	344	webpage = self._download_webpage(url, show_id)
62bafabc	345
8bdd16b4	346	blob = self._extract_data_attr(webpage, show_id, 'blob')
62bafabc	347
8bdd16b4	348	show = blob['bcw_data'][show_id]
62bafabc	349
6d923aab S	350	formats = []
6d923aab S	351	for format_id, format_url in show['audio_stream'].items():
3052a30d	352	if not url_or_none(format_url):
6d923aab S	353	continue
	354	for known_ext in KNOWN_EXTENSIONS:
	355	if known_ext in format_id:
	356	ext = known_ext
	357	break
	358	else:
	359	ext = None
	360	formats.append({
	361	'format_id': format_id,
	362	'url': format_url,
	363	'ext': ext,
	364	'vcodec': 'none',
	365	})
	366	self._sort_formats(formats)
62bafabc	367
6d923aab S	368	title = show.get('audio_title') or 'Bandcamp Weekly'
	369	subtitle = show.get('subtitle')
	370	if subtitle:
	371	title += ' - %s' % subtitle
62bafabc	372
62bafabc	373	return {
8bdd16b4	374	'id': show_id,
6d923aab S	375	'title': title,
6d923aab S	376	'description': show.get('desc') or show.get('short_desc'),
62bafabc	377	'duration': float_or_none(show.get('audio_duration')),
62bafabc AV	378	'is_live': False,
	379	'release_date': unified_strdate(show.get('published_date')),
	380	'series': 'Bandcamp Weekly',
6d923aab	381	'episode': show.get('subtitle'),
8bdd16b4	382	'episode_id': show_id,
62bafabc AV	383	'formats': formats
62bafabc AV	384	}
bc874548 A	385
bc874548 A	386
85a0ad01	387	class BandcampUserIE(InfoExtractor):
	388	IE_NAME = 'Bandcamp:user'
	389	_VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]\|$)'
	390
bc874548	391	_TESTS = [{
85a0ad01	392	# Type 1 Bandcamp user page.
	393	'url': 'https://adrianvonziegler.bandcamp.com',
	394	'info_dict': {
	395	'id': 'adrianvonziegler',
	396	'title': 'Discography of adrianvonziegler',
	397	},
	398	'playlist_mincount': 23,
	399	}, {
	400	# Bandcamp user page with only one album
	401	'url': 'http://dotscale.bandcamp.com',
	402	'info_dict': {
	403	'id': 'dotscale',
	404	'title': 'Discography of dotscale'
	405	},
	406	'playlist_count': 1,
	407	}, {
	408	# Type 2 Bandcamp user page.
	409	'url': 'https://nightcallofficial.bandcamp.com',
	410	'info_dict': {
	411	'id': 'nightcallofficial',
	412	'title': 'Discography of nightcallofficial',
	413	},
	414	'playlist_count': 4,
	415	}, {
bc874548 A	416	'url': 'https://steviasphere.bandcamp.com/music',
	417	'playlist_mincount': 47,
	418	'info_dict': {
	419	'id': 'steviasphere',
85a0ad01	420	'title': 'Discography of steviasphere',
bc874548 A	421	},
	422	}, {
	423	'url': 'https://coldworldofficial.bandcamp.com/music',
	424	'playlist_mincount': 10,
	425	'info_dict': {
	426	'id': 'coldworldofficial',
85a0ad01	427	'title': 'Discography of coldworldofficial',
bc874548 A	428	},
	429	}, {
	430	'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
	431	'playlist_mincount': 399,
	432	'info_dict': {
	433	'id': 'nuclearwarnowproductions',
85a0ad01	434	'title': 'Discography of nuclearwarnowproductions',
bc874548	435	},
85a0ad01	436	}]
bc874548 A	437
bc874548 A	438	def _real_extract(self, url):
85a0ad01	439	uploader = self._match_id(url)
	440	webpage = self._download_webpage(url, uploader)
	441
96b49af0	442	discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s<a href=["\'](?![^"\'/]?/merch)([^"\']+)', webpage)
85a0ad01	443	or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
	444
	445	return self.playlist_from_matches(
	446	discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))