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