]>
Commit | Line | Data |
---|---|---|
3798eadc PH |
1 | from __future__ import unicode_literals |
2 | ||
45aef472 | 3 | import json |
0aacd2de | 4 | import random |
45aef472 | 5 | import re |
0aacd2de | 6 | import time |
45aef472 PH |
7 | |
8 | from .common import InfoExtractor | |
1cc79574 | 9 | from ..compat import ( |
cffa6aa1 | 10 | compat_str, |
09804265 | 11 | compat_urlparse, |
1cc79574 PH |
12 | ) |
13 | from ..utils import ( | |
45aef472 | 14 | ExtractorError, |
ba717dca S |
15 | float_or_none, |
16 | int_or_none, | |
6d923aab | 17 | KNOWN_EXTENSIONS, |
0aacd2de S |
18 | parse_filesize, |
19 | unescapeHTML, | |
20 | update_url_query, | |
62bafabc | 21 | unified_strdate, |
3052a30d | 22 | url_or_none, |
45aef472 PH |
23 | ) |
24 | ||
25 | ||
26 | class BandcampIE(InfoExtractor): | |
6d923aab | 27 | _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)' |
cffa6aa1 | 28 | _TESTS = [{ |
3798eadc | 29 | 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', |
3798eadc PH |
30 | 'md5': 'c557841d5e50261777a6585648adf439', |
31 | 'info_dict': { | |
d9bf4652 S |
32 | 'id': '1812978515', |
33 | 'ext': 'mp3', | |
34 | 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", | |
35 | 'duration': 9.8485, | |
6f5ac90c | 36 | }, |
3798eadc | 37 | '_skip': 'There is a limit of 200 free downloads / month for the test song' |
d9bf4652 S |
38 | }, { |
39 | 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', | |
0f63dc24 | 40 | 'md5': '0369ace6b939f0927e62c67a1a8d9fa7', |
d9bf4652 S |
41 | 'info_dict': { |
42 | 'id': '2650410135', | |
0f63dc24 TF |
43 | 'ext': 'aiff', |
44 | 'title': 'Ben Prunty - Lanius (Battle)', | |
45 | 'uploader': 'Ben Prunty', | |
d9bf4652 | 46 | }, |
14b7a24c PV |
47 | }, { |
48 | 'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire', | |
49 | 'info_dict': { | |
50 | 'id': '2584466013', | |
51 | 'ext': 'mp3', | |
52 | 'title': 'Hail to Fire', | |
53 | 'track_number': 5, | |
54 | }, | |
55 | 'params': { | |
56 | 'skip_download': True, | |
57 | }, | |
cffa6aa1 | 58 | }] |
45aef472 PH |
59 | |
60 | def _real_extract(self, url): | |
61 | mobj = re.match(self._VALID_URL, url) | |
62 | title = mobj.group('title') | |
63 | webpage = self._download_webpage(url, title) | |
8b4774dc | 64 | thumbnail = self._html_search_meta('og:image', webpage, default=None) |
45aef472 | 65 | m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage) |
79981f03 | 66 | if not m_download: |
cffa6aa1 | 67 | m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage) |
5ecd3c6a PH |
68 | if m_trackinfo: |
69 | json_code = m_trackinfo.group(1) | |
79981f03 | 70 | data = json.loads(json_code)[0] |
70346165 T |
71 | track_id = compat_str(data['id']) |
72 | ||
73 | if not data.get('file'): | |
74 | raise ExtractorError('Not streamable', video_id=track_id, expected=True) | |
5ecd3c6a | 75 | |
5ecd3c6a | 76 | formats = [] |
79981f03 | 77 | for format_id, format_url in data['file'].items(): |
2902d44f | 78 | ext, abr_str = format_id.split('-', 1) |
5ecd3c6a PH |
79 | formats.append({ |
80 | 'format_id': format_id, | |
1e52776a | 81 | 'url': self._proto_relative_url(format_url, 'http:'), |
79981f03 | 82 | 'ext': ext, |
5ecd3c6a | 83 | 'vcodec': 'none', |
79981f03 | 84 | 'acodec': ext, |
ba717dca | 85 | 'abr': int_or_none(abr_str), |
5ecd3c6a PH |
86 | }) |
87 | ||
88 | self._sort_formats(formats) | |
cffa6aa1 | 89 | |
d35dc6d3 | 90 | return { |
70346165 | 91 | 'id': track_id, |
79981f03 | 92 | 'title': data['title'], |
8b4774dc | 93 | 'thumbnail': thumbnail, |
cffa6aa1 | 94 | 'formats': formats, |
ba717dca | 95 | 'duration': float_or_none(data.get('duration')), |
14b7a24c | 96 | 'track_number': int_or_none(data.get('track_num')), |
d35dc6d3 | 97 | } |
5ecd3c6a | 98 | else: |
3798eadc | 99 | raise ExtractorError('No free songs found') |
45aef472 PH |
100 | |
101 | download_link = m_download.group(1) | |
d9bf4652 | 102 | video_id = self._search_regex( |
b524a001 | 103 | r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$', |
99c2398b | 104 | webpage, 'video id') |
45aef472 | 105 | |
0aacd2de S |
106 | download_webpage = self._download_webpage( |
107 | download_link, video_id, 'Downloading free downloads page') | |
108 | ||
109 | blob = self._parse_json( | |
110 | self._search_regex( | |
111 | r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage, | |
112 | 'blob', group='blob'), | |
113 | video_id, transform_source=unescapeHTML) | |
114 | ||
115 | info = blob['digital_items'][0] | |
116 | ||
117 | downloads = info['downloads'] | |
118 | track = info['title'] | |
119 | ||
120 | artist = info.get('artist') | |
121 | title = '%s - %s' % (artist, track) if artist else track | |
122 | ||
123 | download_formats = {} | |
124 | for f in blob['download_formats']: | |
125 | name, ext = f.get('name'), f.get('file_extension') | |
126 | if all(isinstance(x, compat_str) for x in (name, ext)): | |
127 | download_formats[name] = ext.strip('.') | |
128 | ||
129 | formats = [] | |
130 | for format_id, f in downloads.items(): | |
131 | format_url = f.get('url') | |
132 | if not format_url: | |
133 | continue | |
134 | # Stat URL generation algorithm is reverse engineered from | |
135 | # download_*_bundle_*.js | |
136 | stat_url = update_url_query( | |
137 | format_url.replace('/download/', '/statdownload/'), { | |
138 | '.rand': int(time.time() * 1000 * random.random()), | |
139 | }) | |
140 | format_id = f.get('encoding_name') or format_id | |
141 | stat = self._download_json( | |
142 | stat_url, video_id, 'Downloading %s JSON' % format_id, | |
143 | transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1], | |
144 | fatal=False) | |
145 | if not stat: | |
146 | continue | |
3052a30d S |
147 | retry_url = url_or_none(stat.get('retry_url')) |
148 | if not retry_url: | |
0aacd2de S |
149 | continue |
150 | formats.append({ | |
151 | 'url': self._proto_relative_url(retry_url, 'http:'), | |
152 | 'ext': download_formats.get(format_id), | |
153 | 'format_id': format_id, | |
154 | 'format_note': f.get('description'), | |
155 | 'filesize': parse_filesize(f.get('size_mb')), | |
156 | 'vcodec': 'none', | |
157 | }) | |
158 | self._sort_formats(formats) | |
45aef472 | 159 | |
5ecd3c6a PH |
160 | return { |
161 | 'id': video_id, | |
0aacd2de | 162 | 'title': title, |
8b4774dc | 163 | 'thumbnail': info.get('thumb_url') or thumbnail, |
f8b5ab8c | 164 | 'uploader': info.get('artist'), |
0aacd2de S |
165 | 'artist': artist, |
166 | 'track': track, | |
167 | 'formats': formats, | |
5ecd3c6a | 168 | } |
09804265 JMF |
169 | |
170 | ||
171 | class BandcampAlbumIE(InfoExtractor): | |
3798eadc | 172 | IE_NAME = 'Bandcamp:album' |
6d923aab | 173 | _VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^/?#&]+))?' |
09804265 | 174 | |
22a6f150 | 175 | _TESTS = [{ |
3798eadc PH |
176 | 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', |
177 | 'playlist': [ | |
d35dc6d3 | 178 | { |
3798eadc PH |
179 | 'md5': '39bc1eded3476e927c724321ddf116cf', |
180 | 'info_dict': { | |
13ba3a64 PH |
181 | 'id': '1353101989', |
182 | 'ext': 'mp3', | |
3798eadc | 183 | 'title': 'Intro', |
d35dc6d3 JMF |
184 | } |
185 | }, | |
186 | { | |
3798eadc PH |
187 | 'md5': '1a2c32e2691474643e912cc6cd4bffaa', |
188 | 'info_dict': { | |
13ba3a64 PH |
189 | 'id': '38097443', |
190 | 'ext': 'mp3', | |
3798eadc | 191 | 'title': 'Kero One - Keep It Alive (Blazo remix)', |
d35dc6d3 JMF |
192 | } |
193 | }, | |
194 | ], | |
13ba3a64 PH |
195 | 'info_dict': { |
196 | 'title': 'Jazz Format Mixtape vol.1', | |
72c1f8de PH |
197 | 'id': 'jazz-format-mixtape-vol-1', |
198 | 'uploader_id': 'blazo', | |
13ba3a64 | 199 | }, |
3798eadc PH |
200 | 'params': { |
201 | 'playlistend': 2 | |
d35dc6d3 | 202 | }, |
72c1f8de | 203 | 'skip': 'Bandcamp imposes download limits.' |
22a6f150 PH |
204 | }, { |
205 | 'url': 'http://nightbringer.bandcamp.com/album/hierophany-of-the-open-grave', | |
206 | 'info_dict': { | |
207 | 'title': 'Hierophany of the Open Grave', | |
72c1f8de PH |
208 | 'uploader_id': 'nightbringer', |
209 | 'id': 'hierophany-of-the-open-grave', | |
22a6f150 PH |
210 | }, |
211 | 'playlist_mincount': 9, | |
1fa17469 S |
212 | }, { |
213 | 'url': 'http://dotscale.bandcamp.com', | |
214 | 'info_dict': { | |
215 | 'title': 'Loom', | |
72c1f8de PH |
216 | 'id': 'dotscale', |
217 | 'uploader_id': 'dotscale', | |
1fa17469 S |
218 | }, |
219 | 'playlist_mincount': 7, | |
64fc49ab S |
220 | }, { |
221 | # with escaped quote in title | |
222 | 'url': 'https://jstrecords.bandcamp.com/album/entropy-ep', | |
223 | 'info_dict': { | |
224 | 'title': '"Entropy" EP', | |
225 | 'uploader_id': 'jstrecords', | |
226 | 'id': 'entropy-ep', | |
227 | }, | |
228 | 'playlist_mincount': 3, | |
019f4c03 YCH |
229 | }, { |
230 | # not all tracks have songs | |
231 | 'url': 'https://insulters.bandcamp.com/album/we-are-the-plague', | |
232 | 'info_dict': { | |
233 | 'id': 'we-are-the-plague', | |
234 | 'title': 'WE ARE THE PLAGUE', | |
235 | 'uploader_id': 'insulters', | |
236 | }, | |
237 | 'playlist_count': 2, | |
22a6f150 | 238 | }] |
d35dc6d3 | 239 | |
62bafabc AV |
240 | @classmethod |
241 | def suitable(cls, url): | |
6d923aab S |
242 | return (False |
243 | if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url) | |
244 | else super(BandcampAlbumIE, cls).suitable(url)) | |
62bafabc | 245 | |
09804265 JMF |
246 | def _real_extract(self, url): |
247 | mobj = re.match(self._VALID_URL, url) | |
72c1f8de PH |
248 | uploader_id = mobj.group('subdomain') |
249 | album_id = mobj.group('album_id') | |
250 | playlist_id = album_id or uploader_id | |
251 | webpage = self._download_webpage(url, playlist_id) | |
019f4c03 YCH |
252 | track_elements = re.findall( |
253 | r'(?s)<div[^>]*>(.*?<a[^>]+href="([^"]+?)"[^>]+itemprop="url"[^>]*>.*?)</div>', webpage) | |
254 | if not track_elements: | |
3798eadc | 255 | raise ExtractorError('The page doesn\'t contain any tracks') |
019f4c03 | 256 | # Only tracks with duration info have songs |
09804265 | 257 | entries = [ |
8239c679 LS |
258 | self.url_result( |
259 | compat_urlparse.urljoin(url, t_path), | |
260 | ie=BandcampIE.ie_key(), | |
261 | video_title=self._search_regex( | |
262 | r'<span\b[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', | |
263 | elem_content, 'track title', fatal=False)) | |
019f4c03 YCH |
264 | for elem_content, t_path in track_elements |
265 | if self._html_search_meta('duration', elem_content, default=None)] | |
266 | ||
64fc49ab S |
267 | title = self._html_search_regex( |
268 | r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"', | |
269 | webpage, 'title', fatal=False) | |
270 | if title: | |
271 | title = title.replace(r'\"', '"') | |
09804265 JMF |
272 | return { |
273 | '_type': 'playlist', | |
72c1f8de | 274 | 'uploader_id': uploader_id, |
b48f147d | 275 | 'id': playlist_id, |
09804265 JMF |
276 | 'title': title, |
277 | 'entries': entries, | |
278 | } | |
62bafabc AV |
279 | |
280 | ||
281 | class BandcampWeeklyIE(InfoExtractor): | |
6d923aab S |
282 | IE_NAME = 'Bandcamp:weekly' |
283 | _VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)' | |
62bafabc AV |
284 | _TESTS = [{ |
285 | 'url': 'https://bandcamp.com/?show=224', | |
286 | 'md5': 'b00df799c733cf7e0c567ed187dea0fd', | |
287 | 'info_dict': { | |
288 | 'id': '224', | |
289 | 'ext': 'opus', | |
6d923aab S |
290 | 'title': 'BC Weekly April 4th 2017 - Magic Moments', |
291 | 'description': 'md5:5d48150916e8e02d030623a48512c874', | |
292 | 'duration': 5829.77, | |
293 | 'release_date': '20170404', | |
294 | 'series': 'Bandcamp Weekly', | |
295 | 'episode': 'Magic Moments', | |
296 | 'episode_number': 208, | |
297 | 'episode_id': '224', | |
62bafabc AV |
298 | } |
299 | }, { | |
300 | 'url': 'https://bandcamp.com/?blah/blah@&show=228', | |
301 | 'only_matching': True | |
302 | }] | |
303 | ||
304 | def _real_extract(self, url): | |
305 | video_id = self._match_id(url) | |
306 | webpage = self._download_webpage(url, video_id) | |
307 | ||
308 | blob = self._parse_json( | |
309 | self._search_regex( | |
310 | r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage, | |
311 | 'blob', group='blob'), | |
312 | video_id, transform_source=unescapeHTML) | |
313 | ||
314 | show = blob['bcw_show'] | |
315 | ||
316 | # This is desired because any invalid show id redirects to `bandcamp.com` | |
317 | # which happens to expose the latest Bandcamp Weekly episode. | |
6d923aab | 318 | show_id = int_or_none(show.get('show_id')) or int_or_none(video_id) |
62bafabc | 319 | |
6d923aab S |
320 | formats = [] |
321 | for format_id, format_url in show['audio_stream'].items(): | |
3052a30d | 322 | if not url_or_none(format_url): |
6d923aab S |
323 | continue |
324 | for known_ext in KNOWN_EXTENSIONS: | |
325 | if known_ext in format_id: | |
326 | ext = known_ext | |
327 | break | |
328 | else: | |
329 | ext = None | |
330 | formats.append({ | |
331 | 'format_id': format_id, | |
332 | 'url': format_url, | |
333 | 'ext': ext, | |
334 | 'vcodec': 'none', | |
335 | }) | |
336 | self._sort_formats(formats) | |
62bafabc | 337 | |
6d923aab S |
338 | title = show.get('audio_title') or 'Bandcamp Weekly' |
339 | subtitle = show.get('subtitle') | |
340 | if subtitle: | |
341 | title += ' - %s' % subtitle | |
62bafabc | 342 | |
6d923aab S |
343 | episode_number = None |
344 | seq = blob.get('bcw_seq') | |
62bafabc | 345 | |
6d923aab S |
346 | if seq and isinstance(seq, list): |
347 | try: | |
348 | episode_number = next( | |
349 | int_or_none(e.get('episode_number')) | |
350 | for e in seq | |
351 | if isinstance(e, dict) and int_or_none(e.get('id')) == show_id) | |
352 | except StopIteration: | |
353 | pass | |
62bafabc AV |
354 | |
355 | return { | |
356 | 'id': video_id, | |
6d923aab S |
357 | 'title': title, |
358 | 'description': show.get('desc') or show.get('short_desc'), | |
62bafabc | 359 | 'duration': float_or_none(show.get('audio_duration')), |
62bafabc AV |
360 | 'is_live': False, |
361 | 'release_date': unified_strdate(show.get('published_date')), | |
362 | 'series': 'Bandcamp Weekly', | |
6d923aab S |
363 | 'episode': show.get('subtitle'), |
364 | 'episode_number': episode_number, | |
62bafabc AV |
365 | 'episode_id': compat_str(video_id), |
366 | 'formats': formats | |
367 | } |