]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/bandcamp.py
Merge pull request #8061 from dstftw/introduce-chapter-and-series-fields
[yt-dlp.git] / youtube_dl / extractor / bandcamp.py
CommitLineData
3798eadc
PH
1from __future__ import unicode_literals
2
45aef472
PH
3import json
4import re
5
6from .common import InfoExtractor
1cc79574 7from ..compat import (
cffa6aa1 8 compat_str,
09804265 9 compat_urlparse,
1cc79574
PH
10)
11from ..utils import (
45aef472 12 ExtractorError,
ba717dca
S
13 float_or_none,
14 int_or_none,
45aef472
PH
15)
16
17
18class BandcampIE(InfoExtractor):
b48f147d 19 _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
cffa6aa1 20 _TESTS = [{
3798eadc 21 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
3798eadc
PH
22 'md5': 'c557841d5e50261777a6585648adf439',
23 'info_dict': {
d9bf4652
S
24 'id': '1812978515',
25 'ext': 'mp3',
26 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad",
27 'duration': 9.8485,
6f5ac90c 28 },
3798eadc 29 '_skip': 'There is a limit of 200 free downloads / month for the test song'
d9bf4652
S
30 }, {
31 'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
32 'md5': '2b68e5851514c20efdff2afc5603b8b4',
33 'info_dict': {
34 'id': '2650410135',
35 'ext': 'mp3',
36 'title': 'Lanius (Battle)',
37 'uploader': 'Ben Prunty Music',
38 },
cffa6aa1 39 }]
45aef472
PH
40
41 def _real_extract(self, url):
42 mobj = re.match(self._VALID_URL, url)
43 title = mobj.group('title')
44 webpage = self._download_webpage(url, title)
45aef472 45 m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
79981f03 46 if not m_download:
cffa6aa1 47 m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
5ecd3c6a
PH
48 if m_trackinfo:
49 json_code = m_trackinfo.group(1)
79981f03 50 data = json.loads(json_code)[0]
5ecd3c6a 51
5ecd3c6a 52 formats = []
79981f03 53 for format_id, format_url in data['file'].items():
2902d44f 54 ext, abr_str = format_id.split('-', 1)
5ecd3c6a
PH
55 formats.append({
56 'format_id': format_id,
1e52776a 57 'url': self._proto_relative_url(format_url, 'http:'),
79981f03 58 'ext': ext,
5ecd3c6a 59 'vcodec': 'none',
79981f03 60 'acodec': ext,
ba717dca 61 'abr': int_or_none(abr_str),
5ecd3c6a
PH
62 })
63
64 self._sort_formats(formats)
cffa6aa1 65
d35dc6d3 66 return {
79981f03 67 'id': compat_str(data['id']),
68 'title': data['title'],
cffa6aa1 69 'formats': formats,
ba717dca 70 'duration': float_or_none(data.get('duration')),
d35dc6d3 71 }
5ecd3c6a 72 else:
3798eadc 73 raise ExtractorError('No free songs found')
45aef472
PH
74
75 download_link = m_download.group(1)
d9bf4652 76 video_id = self._search_regex(
b524a001 77 r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
99c2398b 78 webpage, 'video id')
45aef472 79
79981f03 80 download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')
81 # We get the dictionary of the track from some javascript code
99c2398b
PH
82 all_info = self._parse_json(self._search_regex(
83 r'(?sm)items: (.*?),$', download_webpage, 'items'), video_id)
834bf069 84 info = all_info[0]
45aef472 85 # We pick mp3-320 for now, until format selection can be easily implemented.
3798eadc 86 mp3_info = info['downloads']['mp3-320']
45aef472 87 # If we try to use this url it says the link has expired
3798eadc 88 initial_url = mp3_info['url']
99c2398b
PH
89 m_url = re.match(
90 r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$',
91 initial_url)
5f6a1245 92 # We build the url we will use to get the final track url
45aef472 93 # This url is build in Bandcamp in the script download_bunde_*.js
5ecd3c6a 94 request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts'))
298f16f9 95 final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url')
45aef472 96 # If we could correctly generate the .rand field the url would be
5f6a1245 97 # in the "download_url" key
f648e682
S
98 final_url = self._proto_relative_url(self._search_regex(
99 r'"retry_url":"(.+?)"', final_url_webpage, 'final video URL'), 'http:')
45aef472 100
5ecd3c6a
PH
101 return {
102 'id': video_id,
3798eadc 103 'title': info['title'],
5ecd3c6a
PH
104 'ext': 'mp3',
105 'vcodec': 'none',
106 'url': final_url,
f8b5ab8c
PH
107 'thumbnail': info.get('thumb_url'),
108 'uploader': info.get('artist'),
5ecd3c6a 109 }
09804265
JMF
110
111
112class BandcampAlbumIE(InfoExtractor):
3798eadc 113 IE_NAME = 'Bandcamp:album'
72c1f8de 114 _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
09804265 115
22a6f150 116 _TESTS = [{
3798eadc
PH
117 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
118 'playlist': [
d35dc6d3 119 {
3798eadc
PH
120 'md5': '39bc1eded3476e927c724321ddf116cf',
121 'info_dict': {
13ba3a64
PH
122 'id': '1353101989',
123 'ext': 'mp3',
3798eadc 124 'title': 'Intro',
d35dc6d3
JMF
125 }
126 },
127 {
3798eadc
PH
128 'md5': '1a2c32e2691474643e912cc6cd4bffaa',
129 'info_dict': {
13ba3a64
PH
130 'id': '38097443',
131 'ext': 'mp3',
3798eadc 132 'title': 'Kero One - Keep It Alive (Blazo remix)',
d35dc6d3
JMF
133 }
134 },
135 ],
13ba3a64
PH
136 'info_dict': {
137 'title': 'Jazz Format Mixtape vol.1',
72c1f8de
PH
138 'id': 'jazz-format-mixtape-vol-1',
139 'uploader_id': 'blazo',
13ba3a64 140 },
3798eadc
PH
141 'params': {
142 'playlistend': 2
d35dc6d3 143 },
72c1f8de 144 'skip': 'Bandcamp imposes download limits.'
22a6f150
PH
145 }, {
146 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave',
147 'info_dict': {
148 'title': 'Hierophany of the Open Grave',
72c1f8de
PH
149 'uploader_id': 'nightbringer',
150 'id': 'hierophany-of-the-open-grave',
22a6f150
PH
151 },
152 'playlist_mincount': 9,
1fa17469
S
153 }, {
154 'url': 'http://dotscale.bandcamp.com',
155 'info_dict': {
156 'title': 'Loom',
72c1f8de
PH
157 'id': 'dotscale',
158 'uploader_id': 'dotscale',
1fa17469
S
159 },
160 'playlist_mincount': 7,
22a6f150 161 }]
d35dc6d3 162
09804265
JMF
163 def _real_extract(self, url):
164 mobj = re.match(self._VALID_URL, url)
72c1f8de
PH
165 uploader_id = mobj.group('subdomain')
166 album_id = mobj.group('album_id')
167 playlist_id = album_id or uploader_id
168 webpage = self._download_webpage(url, playlist_id)
09804265
JMF
169 tracks_paths = re.findall(r'<a href="(.*?)" itemprop="url">', webpage)
170 if not tracks_paths:
3798eadc 171 raise ExtractorError('The page doesn\'t contain any tracks')
09804265
JMF
172 entries = [
173 self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
174 for t_path in tracks_paths]
cce81f19
PH
175 title = self._search_regex(
176 r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
09804265
JMF
177 return {
178 '_type': 'playlist',
72c1f8de 179 'uploader_id': uploader_id,
b48f147d 180 'id': playlist_id,
09804265
JMF
181 'title': title,
182 'entries': entries,
183 }