Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-25 09:54:32 +01:00
Code Issues Releases Wiki Activity

[bandcamp] fix regexp for JSON matching on bandcamp

Browse Source
This commit is contained in:
Lyz 2020-09-24 11:08:04 +02:00
commit 0f371d9166
No known key found for this signature in database
GPG Key ID: 6C7D7C1612CDE02F
1 changed files with 360 additions and 307 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

667
youtube_dl/extractor/bandcamp.py
View File

@ -4,86 +4,80 @@ import random
import re import re
import time import time
from ..compat import compat_str, compat_urlparse
from ..utils import (KNOWN_EXTENSIONS, ExtractorError, float_or_none,
int_or_none, parse_filesize, str_or_none, try_get,
unescapeHTML, unified_strdate, unified_timestamp,
update_url_query, url_or_none)
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
str_or_none,
try_get,
unescapeHTML,
update_url_query,
unified_strdate,
unified_timestamp,
url_or_none,
)
class BandcampIE(InfoExtractor): class BandcampIE(InfoExtractor):
_VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<title>[^/?#&]+)' _VALID_URL = r"https?://[^/]+\.bandcamp\.com/track/(?P<title>[^/?#&]+)"
_TESTS = [{ _TESTS = [
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', {
'md5': 'c557841d5e50261777a6585648adf439', "url": "http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
'info_dict': { "md5": "c557841d5e50261777a6585648adf439",
'id': '1812978515', "info_dict": {
'ext': 'mp3', "id": "1812978515",
'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", "ext": "mp3",
'duration': 9.8485, "title": (
"youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song"
" \"'/\\\u00e4\u21ad"
),
"duration": 9.8485,
},
"_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' {
}, { # free download
# free download "url": "http://benprunty.bandcamp.com/track/lanius-battle",
'url': 'http://benprunty.bandcamp.com/track/lanius-battle', "md5": "853e35bf34aa1d6fe2615ae612564b36",
'md5': '853e35bf34aa1d6fe2615ae612564b36', "info_dict": {
'info_dict': { "id": "2650410135",
'id': '2650410135', "ext": "aiff",
'ext': 'aiff', "title": "Ben Prunty - Lanius (Battle)",
'title': 'Ben Prunty - Lanius (Battle)', "thumbnail": r"re:^https?://.*\.jpg$",
'thumbnail': r're:^https?://.*\.jpg$', "uploader": "Ben Prunty",
'uploader': 'Ben Prunty', "timestamp": 1396508491,
'timestamp': 1396508491, "upload_date": "20140403",
'upload_date': '20140403', "release_date": "20140403",
'release_date': '20140403', "duration": 260.877,
'duration': 260.877, "track": "Lanius (Battle)",
'track': 'Lanius (Battle)', "track_number": 1,
'track_number': 1, "track_id": "2650410135",
'track_id': '2650410135', "artist": "Ben Prunty",
'artist': 'Ben Prunty', "album": "FTL: Advanced Edition Soundtrack",
'album': 'FTL: Advanced Edition Soundtrack', },
}, },
}, { {
# no free download, mp3 128 # no free download, mp3 128
'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire', "url": "https://relapsealumni.bandcamp.com/track/hail-to-fire",
'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7', "md5": "fec12ff55e804bb7f7ebeb77a800c8b7",
'info_dict': { "info_dict": {
'id': '2584466013', "id": "2584466013",
'ext': 'mp3', "ext": "mp3",
'title': 'Mastodon - Hail to Fire', "title": "Mastodon - Hail to Fire",
'thumbnail': r're:^https?://.*\.jpg$', "thumbnail": r"re:^https?://.*\.jpg$",
'uploader': 'Mastodon', "uploader": "Mastodon",
'timestamp': 1322005399, "timestamp": 1322005399,
'upload_date': '20111122', "upload_date": "20111122",
'release_date': '20040207', "release_date": "20040207",
'duration': 120.79, "duration": 120.79,
'track': 'Hail to Fire', "track": "Hail to Fire",
'track_number': 5, "track_number": 5,
'track_id': '2584466013', "track_id": "2584466013",
'artist': 'Mastodon', "artist": "Mastodon",
'album': 'Call of the Mastodon', "album": "Call of the Mastodon",
},
}, },
}] ]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
title = mobj.group('title') title = mobj.group("title")
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)
track_id = None track_id = None
track = None track = None
@ -91,212 +85,250 @@ class BandcampIE(InfoExtractor):
duration = None duration = None
formats = [] formats = []
track_info = self._parse_json( trackinfo_block = self._search_regex(
self._search_regex( r"trackinfo&quot;:\[\s*({.+?})\s*\],&quot;",
r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n', webpage,
webpage, 'track info', default='{}'), title) "track info",
default="{}",
)
quoted_json = trackinfo_block.replace("&quot;", '"')
track_info = self._parse_json(quoted_json, 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):
for format_id, format_url in file_.items(): for format_id, format_url in file_.items():
if not url_or_none(format_url): if not url_or_none(format_url):
continue continue
ext, abr_str = format_id.split('-', 1) ext, abr_str = format_id.split("-", 1)
formats.append({ formats.append(
'format_id': format_id, {
'url': self._proto_relative_url(format_url, 'http:'), "format_id": format_id,
'ext': ext, "url": self._proto_relative_url(format_url, "http:"),
'vcodec': 'none', "ext": ext,
'acodec': ext, "vcodec": "none",
'abr': int_or_none(abr_str), "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')) track = track_info.get("title")
duration = float_or_none(track_info.get('duration')) 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"))
# r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key, # r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key,
def extract(key): def extract(key):
return self._search_regex( return self._search_regex(
r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>.+)\1' % key, r",&quot;%s&quot;:(&quot;)(?P<value>(?:(?!&quot;).)+)&quot;" % key,
webpage, key, default=None, group='value') webpage,
key,
default=None,
group="value",
)
artist = extract('artist') artist = extract("artist")
album = extract('album_title') album = extract("album_title")
timestamp = unified_timestamp( timestamp = unified_timestamp(
extract('publish_date') or extract('album_publish_date')) extract("publish_date") or extract("album_publish_date")
release_date = unified_strdate(extract('album_release_date')) )
release_date = unified_strdate(extract("album_release_date"))
download_link = self._search_regex( download_link = self._search_regex(
r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
'download link', default=None, group='url') webpage,
"download link",
default=None,
group="url",
)
if download_link: if download_link:
track_id = self._search_regex( track_id = self._search_regex(
r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', r"(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$",
webpage, 'track id') webpage,
"track id",
)
download_webpage = self._download_webpage( download_webpage = self._download_webpage(
download_link, track_id, 'Downloading free downloads page') download_link, track_id, "Downloading free downloads page"
)
blob = self._parse_json( blob = self._parse_json(
self._search_regex( self._search_regex(
r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, r'data-blob=(["\'])(?P<blob>{.+?})\1',
'blob', group='blob'), download_webpage,
track_id, transform_source=unescapeHTML) "blob",
group="blob",
),
track_id,
transform_source=unescapeHTML,
)
info = try_get( info = try_get(
blob, (lambda x: x['digital_items'][0], blob,
lambda x: x['download_items'][0]), dict) (lambda x: x["digital_items"][0], lambda x: x["download_items"][0]),
dict,
)
if info: if info:
downloads = info.get('downloads') downloads = info.get("downloads")
if isinstance(downloads, dict): if isinstance(downloads, dict):
if not track: if not track:
track = info.get('title') track = info.get("title")
if not artist: if not artist:
artist = info.get('artist') artist = info.get("artist")
if not thumbnail: if not thumbnail:
thumbnail = info.get('thumb_url') thumbnail = info.get("thumb_url")
download_formats = {} download_formats = {}
download_formats_list = blob.get('download_formats') download_formats_list = blob.get("download_formats")
if isinstance(download_formats_list, list): if isinstance(download_formats_list, list):
for f in blob['download_formats']: for f in blob["download_formats"]:
name, ext = f.get('name'), f.get('file_extension') name, ext = f.get("name"), f.get("file_extension")
if all(isinstance(x, compat_str) for x in (name, ext)): if all(isinstance(x, compat_str) for x in (name, ext)):
download_formats[name] = ext.strip('.') download_formats[name] = ext.strip(".")
for format_id, f in downloads.items(): for format_id, f in downloads.items():
format_url = f.get('url') format_url = f.get("url")
if not format_url: if not format_url:
continue continue
# Stat URL generation algorithm is reverse engineered from # Stat URL generation algorithm is reverse engineered from
# download_*_bundle_*.js # download_*_bundle_*.js
stat_url = update_url_query( stat_url = update_url_query(
format_url.replace('/download/', '/statdownload/'), { format_url.replace("/download/", "/statdownload/"),
'.rand': int(time.time() * 1000 * random.random()), {".rand": int(time.time() * 1000 * random.random())},
}) )
format_id = f.get('encoding_name') or format_id format_id = f.get("encoding_name") or format_id
stat = self._download_json( stat = self._download_json(
stat_url, track_id, 'Downloading %s JSON' % format_id, stat_url,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1], track_id,
fatal=False) "Downloading %s JSON" % format_id,
transform_source=lambda s: s[
s.index("{") : s.rindex("}") + 1
],
fatal=False,
)
if not stat: if not stat:
continue continue
retry_url = url_or_none(stat.get('retry_url')) retry_url = url_or_none(stat.get("retry_url"))
if not retry_url: if not retry_url:
continue continue
formats.append({ formats.append(
'url': self._proto_relative_url(retry_url, 'http:'), {
'ext': download_formats.get(format_id), "url": self._proto_relative_url(retry_url, "http:"),
'format_id': format_id, "ext": download_formats.get(format_id),
'format_note': f.get('description'), "format_id": format_id,
'filesize': parse_filesize(f.get('size_mb')), "format_note": f.get("description"),
'vcodec': 'none', "filesize": parse_filesize(f.get("size_mb")),
}) "vcodec": "none",
}
)
self._sort_formats(formats) self._sort_formats(formats)
title = '%s - %s' % (artist, track) if artist else track title = "%s - %s" % (artist, track) if artist else track
if not duration: if not duration:
duration = float_or_none(self._html_search_meta( duration = float_or_none(
'duration', webpage, default=None)) self._html_search_meta("duration", webpage, default=None)
)
return { return {
'id': track_id, "id": track_id,
'title': title, "title": title,
'thumbnail': thumbnail, "thumbnail": thumbnail,
'uploader': artist, "uploader": artist,
'timestamp': timestamp, "timestamp": timestamp,
'release_date': release_date, "release_date": release_date,
'duration': duration, "duration": duration,
'track': track, "track": track,
'track_number': track_number, "track_number": track_number,
'track_id': track_id, "track_id": track_id,
'artist': artist, "artist": artist,
'album': album, "album": album,
'formats': formats, "formats": formats,
} }
class BandcampAlbumIE(InfoExtractor): class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album' IE_NAME = "Bandcamp:album"
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<album_id>[^/?#&]+)' _VALID_URL = r"https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<album_id>[^/?#&]+)"
_TESTS = [{ _TESTS = [
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', {
'playlist': [ "url": "http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1",
{ "playlist": [
'md5': '39bc1eded3476e927c724321ddf116cf', {
'info_dict': { "md5": "39bc1eded3476e927c724321ddf116cf",
'id': '1353101989', "info_dict": {"id": "1353101989", "ext": "mp3", "title": "Intro",},
'ext': 'mp3', },
'title': 'Intro', {
} "md5": "1a2c32e2691474643e912cc6cd4bffaa",
"info_dict": {
"id": "38097443",
"ext": "mp3",
"title": "Kero One - Keep It Alive (Blazo remix)",
},
},
],
"info_dict": {
"title": "Jazz Format Mixtape vol.1",
"id": "jazz-format-mixtape-vol-1",
"uploader_id": "blazo",
}, },
{ "params": {"playlistend": 2},
'md5': '1a2c32e2691474643e912cc6cd4bffaa', "skip": "Bandcamp imposes download limits.",
'info_dict': { },
'id': '38097443', {
'ext': 'mp3', "url": (
'title': 'Kero One - Keep It Alive (Blazo remix)', "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,
'info_dict': {
'title': 'Jazz Format Mixtape vol.1',
'id': 'jazz-format-mixtape-vol-1',
'uploader_id': 'blazo',
}, },
'params': { {
'playlistend': 2 # with escaped quote in title
"url": "https://jstrecords.bandcamp.com/album/entropy-ep",
"info_dict": {
"title": '"Entropy" EP',
"uploader_id": "jstrecords",
"id": "entropy-ep",
},
"playlist_mincount": 3,
}, },
'skip': 'Bandcamp imposes download limits.' {
}, { # not all tracks have songs
'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', "url": "https://insulters.bandcamp.com/album/we-are-the-plague",
'info_dict': { "info_dict": {
'title': 'Hierophany of the Open Grave', "id": "we-are-the-plague",
'uploader_id': 'nightbringer', "title": "WE ARE THE PLAGUE",
'id': 'hierophany-of-the-open-grave', "uploader_id": "insulters",
},
"playlist_count": 2,
}, },
'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',
},
'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',
},
'playlist_count': 2,
}]
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return (False return (
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url) False
else super(BandcampAlbumIE, cls).suitable(url)) if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
else super(BandcampAlbumIE, cls).suitable(url)
)
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
uploader_id = mobj.group('subdomain') uploader_id = mobj.group("subdomain")
album_id = mobj.group('album_id') album_id = mobj.group("album_id")
playlist_id = album_id or uploader_id playlist_id = album_id or uploader_id
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
track_elements = re.findall( track_elements = re.findall(
r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage) r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>',
webpage,
)
if not track_elements: if not track_elements:
raise ExtractorError('The page doesn\'t contain any tracks') raise ExtractorError("The page doesn't contain any tracks")
# Only tracks with duration info have songs # Only tracks with duration info have songs
entries = [ entries = [
self.url_result( self.url_result(
@ -304,46 +336,51 @@ class BandcampAlbumIE(InfoExtractor):
ie=BandcampIE.ie_key(), ie=BandcampIE.ie_key(),
video_title=self._search_regex( video_title=self._search_regex(
r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)',
elem_content, 'track title', fatal=False)) elem_content,
"track title",
fatal=False,
),
)
for elem_content, t_path in track_elements for elem_content, t_path in track_elements
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*:\s*"((?:\\.|[^"\\])+?)"', r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"', webpage, "title", fatal=False
webpage, 'title', fatal=False) )
if title: if title:
title = title.replace(r'\"', '"') title = title.replace(r"\"", '"')
return { return {
'_type': 'playlist', "_type": "playlist",
'uploader_id': uploader_id, "uploader_id": uploader_id,
'id': playlist_id, "id": playlist_id,
'title': title, "title": title,
'entries': entries, "entries": entries,
} }
class BandcampWeeklyIE(InfoExtractor): class BandcampWeeklyIE(InfoExtractor):
IE_NAME = 'Bandcamp:weekly' IE_NAME = "Bandcamp:weekly"
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)' _VALID_URL = r"https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)"
_TESTS = [{ _TESTS = [
'url': 'https://bandcamp.com/?show=224', {
'md5': 'b00df799c733cf7e0c567ed187dea0fd', "url": "https://bandcamp.com/?show=224",
'info_dict': { "md5": "b00df799c733cf7e0c567ed187dea0fd",
'id': '224', "info_dict": {
'ext': 'opus', "id": "224",
'title': 'BC Weekly April 4th 2017 - Magic Moments', "ext": "opus",
'description': 'md5:5d48150916e8e02d030623a48512c874', "title": "BC Weekly April 4th 2017 - Magic Moments",
'duration': 5829.77, "description": "md5:5d48150916e8e02d030623a48512c874",
'release_date': '20170404', "duration": 5829.77,
'series': 'Bandcamp Weekly', "release_date": "20170404",
'episode': 'Magic Moments', "series": "Bandcamp Weekly",
'episode_number': 208, "episode": "Magic Moments",
'episode_id': '224', "episode_number": 208,
} "episode_id": "224",
}, { },
'url': 'https://bandcamp.com/?blah/blah@&show=228', },
'only_matching': True {"url": "https://bandcamp.com/?blah/blah@&show=228", "only_matching": True},
}] ]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -351,18 +388,20 @@ class BandcampWeeklyIE(InfoExtractor):
blob = self._parse_json( blob = self._parse_json(
self._search_regex( self._search_regex(
r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage, r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage, "blob", group="blob"
'blob', group='blob'), ),
video_id, transform_source=unescapeHTML) video_id,
transform_source=unescapeHTML,
)
show = blob['bcw_show'] show = blob["bcw_show"]
# This is desired because any invalid show id redirects to `bandcamp.com` # This is desired because any invalid show id redirects to `bandcamp.com`
# which happens to expose the latest Bandcamp Weekly episode. # which happens to expose the latest Bandcamp Weekly episode.
show_id = int_or_none(show.get('show_id')) or int_or_none(video_id) show_id = int_or_none(show.get("show_id")) or int_or_none(video_id)
formats = [] formats = []
for format_id, format_url in show['audio_stream'].items(): for format_id, format_url in show["audio_stream"].items():
if not url_or_none(format_url): if not url_or_none(format_url):
continue continue
for known_ext in KNOWN_EXTENSIONS: for known_ext in KNOWN_EXTENSIONS:
@ -371,81 +410,86 @@ class BandcampWeeklyIE(InfoExtractor):
break break
else: else:
ext = None ext = None
formats.append({ formats.append(
'format_id': format_id, {
'url': format_url, "format_id": format_id,
'ext': ext, "url": format_url,
'vcodec': 'none', "ext": ext,
}) "vcodec": "none",
}
)
self._sort_formats(formats) self._sort_formats(formats)
title = show.get('audio_title') or 'Bandcamp Weekly' title = show.get("audio_title") or "Bandcamp Weekly"
subtitle = show.get('subtitle') subtitle = show.get("subtitle")
if subtitle: if subtitle:
title += ' - %s' % subtitle title += " - %s" % subtitle
episode_number = None episode_number = None
seq = blob.get('bcw_seq') seq = blob.get("bcw_seq")
if seq and isinstance(seq, list): if seq and isinstance(seq, list):
try: try:
episode_number = next( episode_number = next(
int_or_none(e.get('episode_number')) int_or_none(e.get("episode_number"))
for e in seq for e in seq
if isinstance(e, dict) and int_or_none(e.get('id')) == show_id) if isinstance(e, dict) and int_or_none(e.get("id")) == show_id
)
except StopIteration: except StopIteration:
pass pass
return { return {
'id': video_id, "id": video_id,
'title': title, "title": title,
'description': show.get('desc') or show.get('short_desc'), "description": show.get("desc") or show.get("short_desc"),
'duration': float_or_none(show.get('audio_duration')), "duration": float_or_none(show.get("audio_duration")),
'is_live': False, "is_live": False,
'release_date': unified_strdate(show.get('published_date')), "release_date": unified_strdate(show.get("published_date")),
'series': 'Bandcamp Weekly', "series": "Bandcamp Weekly",
'episode': show.get('subtitle'), "episode": show.get("subtitle"),
'episode_number': episode_number, "episode_number": episode_number,
'episode_id': compat_str(video_id), "episode_id": compat_str(video_id),
'formats': formats "formats": formats,
} }
class BandcampUserIE(InfoExtractor): class BandcampUserIE(InfoExtractor):
IE_NAME = 'Bandcamp:user' IE_NAME = "Bandcamp:user"
_VALID_URL = r'https?://(?:(?P<id>[^.]+)\.)?bandcamp\.com' _VALID_URL = r"https?://(?:(?P<id>[^.]+)\.)?bandcamp\.com"
_TESTS = [{ _TESTS = [
'url': 'https://adrianvonziegler.bandcamp.com', {
'info_dict': { "url": "https://adrianvonziegler.bandcamp.com",
'id': 'adrianvonziegler', "info_dict": {
'title': 'Discography of adrianvonziegler', "id": "adrianvonziegler",
"title": "Discography of adrianvonziegler",
},
"playlist_mincount": 23,
}, },
'playlist_mincount': 23, {
}, { "url": "http://dotscale.bandcamp.com",
'url': 'http://dotscale.bandcamp.com', "info_dict": {"id": "dotscale", "title": "Discography of dotscale",},
'info_dict': { "playlist_count": 1,
'id': 'dotscale',
'title': 'Discography of dotscale',
}, },
'playlist_count': 1, {
}, { "url": "https://nightcallofficial.bandcamp.com",
'url': 'https://nightcallofficial.bandcamp.com', "info_dict": {
'info_dict': { "id": "nightcallofficial",
'id': 'nightcallofficial', "title": "Discography of nightcallofficial",
'title': 'Discography of nightcallofficial', },
"playlist_count": 4,
}, },
'playlist_count': 4,
},
] ]
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return (False if BandcampAlbumIE.suitable(url) return (
or BandcampIE.suitable(url) False
or BandcampWeeklyIE.suitable(url) if BandcampAlbumIE.suitable(url)
else super(BandcampUserIE, cls).suitable(url)) or BandcampIE.suitable(url)
or BandcampWeeklyIE.suitable(url)
else super(BandcampUserIE, cls).suitable(url)
)
def _real_extract(self, url): def _real_extract(self, url):
uploader = self._match_id(url) uploader = self._match_id(url)
@ -455,41 +499,50 @@ class BandcampUserIE(InfoExtractor):
# Bandcamp User type 1 page # Bandcamp User type 1 page
discography_data = re.findall( discography_data = re.findall(
r'<li data-item-id="([^"]+)[^>]+>\s*<a href="(/[^/]+/[^/"]+)">', r'<li data-item-id="([^"]+)[^>]+>\s*<a href="(/[^/]+/[^/"]+)">',
webpage, re.MULTILINE) webpage,
re.MULTILINE,
)
if len(discography_data) > 0: if len(discography_data) > 0:
for match in discography_data: for match in discography_data:
element_id = match[0] element_id = match[0]
element_url = match[1] element_url = match[1]
if element_url.split('/')[1] == 'album': if element_url.split("/")[1] == "album":
ie = BandcampAlbumIE.ie_key() ie = BandcampAlbumIE.ie_key()
else: else:
ie = BandcampIE.ie_key() ie = BandcampIE.ie_key()
entries.append(self.url_result( entries.append(
compat_urlparse.urljoin(url, element_url), self.url_result(
ie=ie, compat_urlparse.urljoin(url, element_url),
video_id=element_id, ie=ie,
video_title=element_url.split('/')[2])) video_id=element_id,
video_title=element_url.split("/")[2],
)
)
else: else:
# Bandcamp user type 2 page # Bandcamp user type 2 page
discography_data = re.findall( discography_data = re.findall(
r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage) r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage
)
for element in discography_data: for element in discography_data:
if re.match('/album/+', element): if re.match("/album/+", element):
ie = BandcampAlbumIE.ie_key() ie = BandcampAlbumIE.ie_key()
else: else:
ie = BandcampIE.ie_key() ie = BandcampIE.ie_key()
entries.append(self.url_result( entries.append(
compat_urlparse.urljoin(url, element), self.url_result(
ie=ie, compat_urlparse.urljoin(url, element),
video_title=element)) ie=ie,
video_title=element,
)
)
return { return {
'_type': 'playlist', "_type": "playlist",
'id': uploader, "id": uploader,
'title': 'Discography of %s' % uploader, "title": "Discography of %s" % uploader,
'entries': entries, "entries": entries,
} }