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