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