]>
Commit | Line | Data |
---|---|---|
1dd6d9ca | 1 | import itertools |
c9ce57d9 | 2 | import urllib.parse |
1dd6d9ca | 3 | |
a00d73c8 | 4 | from .common import InfoExtractor |
d6c2c2bc | 5 | from .sproutvideo import VidsIoIE |
65af1839 | 6 | from .vimeo import VimeoIE |
3d2623a8 | 7 | from ..networking.exceptions import HTTPError |
c9d891f1 | 8 | from ..utils import ( |
11de6fec | 9 | KNOWN_EXTENSIONS, |
10 | ExtractorError, | |
c9d891f1 RA |
11 | clean_html, |
12 | determine_ext, | |
13 | int_or_none, | |
b77c3949 | 14 | mimetype2ext, |
c9d891f1 | 15 | parse_iso8601, |
d6c2c2bc | 16 | smuggle_url, |
b77c3949 | 17 | str_or_none, |
4f08e586 | 18 | traverse_obj, |
1dd6d9ca | 19 | url_or_none, |
11de6fec | 20 | urljoin, |
c9d891f1 | 21 | ) |
a00d73c8 EJ |
22 | |
23 | ||
4f08e586 | 24 | class PatreonBaseIE(InfoExtractor): |
25 | USER_AGENT = 'Patreon/7.6.28 (Android; Android 11; Scale/2.10)' | |
26 | ||
27 | def _call_api(self, ep, item_id, query=None, headers=None, fatal=True, note=None): | |
28 | if headers is None: | |
29 | headers = {} | |
30 | if 'User-Agent' not in headers: | |
31 | headers['User-Agent'] = self.USER_AGENT | |
32 | if query: | |
33 | query.update({'json-api-version': 1.0}) | |
34 | ||
35 | try: | |
36 | return self._download_json( | |
37 | f'https://www.patreon.com/api/{ep}', | |
add96eb9 | 38 | item_id, note=note if note else 'Downloading API JSON', |
4f08e586 | 39 | query=query, fatal=fatal, headers=headers) |
40 | except ExtractorError as e: | |
3d2623a8 | 41 | if not isinstance(e.cause, HTTPError) or mimetype2ext(e.cause.response.headers.get('Content-Type')) != 'json': |
4f08e586 | 42 | raise |
3d2623a8 | 43 | err_json = self._parse_json(self._webpage_read_content(e.cause.response, None, item_id), item_id, fatal=False) |
4f08e586 | 44 | err_message = traverse_obj(err_json, ('errors', ..., 'detail'), get_all=False) |
45 | if err_message: | |
46 | raise ExtractorError(f'Patreon said: {err_message}', expected=True) | |
47 | raise | |
48 | ||
49 | ||
50 | class PatreonIE(PatreonBaseIE): | |
c9d891f1 RA |
51 | _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?:creation\?hid=|posts/(?:[\w-]+-)?)(?P<id>\d+)' |
52 | _TESTS = [{ | |
53 | 'url': 'http://www.patreon.com/creation?hid=743933', | |
54 | 'md5': 'e25505eec1053a6e6813b8ed369875cc', | |
55 | 'info_dict': { | |
56 | 'id': '743933', | |
57 | 'ext': 'mp3', | |
58 | 'title': 'Episode 166: David Smalley of Dogma Debate', | |
4f08e586 | 59 | 'description': 'md5:34d207dd29aa90e24f1b3f58841b81c7', |
c9d891f1 RA |
60 | 'uploader': 'Cognitive Dissonance Podcast', |
61 | 'thumbnail': 're:^https?://.*$', | |
62 | 'timestamp': 1406473987, | |
63 | 'upload_date': '20140727', | |
b77c3949 | 64 | 'uploader_id': '87145', |
4f08e586 | 65 | 'like_count': int, |
66 | 'comment_count': int, | |
67 | 'uploader_url': 'https://www.patreon.com/dissonancepod', | |
68 | 'channel_id': '80642', | |
69 | 'channel_url': 'https://www.patreon.com/dissonancepod', | |
70 | 'channel_follower_count': int, | |
c9d891f1 RA |
71 | }, |
72 | }, { | |
73 | 'url': 'http://www.patreon.com/creation?hid=754133', | |
74 | 'md5': '3eb09345bf44bf60451b8b0b81759d0a', | |
75 | 'info_dict': { | |
76 | 'id': '754133', | |
77 | 'ext': 'mp3', | |
78 | 'title': 'CD 167 Extra', | |
79 | 'uploader': 'Cognitive Dissonance Podcast', | |
80 | 'thumbnail': 're:^https?://.*$', | |
4f08e586 | 81 | 'like_count': int, |
82 | 'comment_count': int, | |
83 | 'uploader_url': 'https://www.patreon.com/dissonancepod', | |
a00d73c8 | 84 | }, |
c9d891f1 RA |
85 | 'skip': 'Patron-only content', |
86 | }, { | |
87 | 'url': 'https://www.patreon.com/creation?hid=1682498', | |
88 | 'info_dict': { | |
89 | 'id': 'SU4fj_aEMVw', | |
90 | 'ext': 'mp4', | |
91 | 'title': 'I\'m on Patreon!', | |
92 | 'uploader': 'TraciJHines', | |
93 | 'thumbnail': 're:^https?://.*$', | |
94 | 'upload_date': '20150211', | |
4f08e586 | 95 | 'description': 'md5:8af6425f50bd46fbf29f3db0fc3a8364', |
36b240f9 | 96 | 'uploader_id': '@TraciHinesMusic', |
4f08e586 | 97 | 'categories': ['Entertainment'], |
98 | 'duration': 282, | |
99 | 'view_count': int, | |
100 | 'tags': 'count:39', | |
101 | 'age_limit': 0, | |
102 | 'channel': 'TraciJHines', | |
103 | 'channel_url': 'https://www.youtube.com/channel/UCGLim4T2loE5rwCMdpCIPVg', | |
104 | 'live_status': 'not_live', | |
105 | 'like_count': int, | |
106 | 'channel_id': 'UCGLim4T2loE5rwCMdpCIPVg', | |
107 | 'availability': 'public', | |
108 | 'channel_follower_count': int, | |
109 | 'playable_in_embed': True, | |
36b240f9 | 110 | 'uploader_url': 'https://www.youtube.com/@TraciHinesMusic', |
4f08e586 | 111 | 'comment_count': int, |
36b240f9 JV |
112 | 'channel_is_verified': True, |
113 | 'chapters': 'count:4', | |
6994e706 | 114 | }, |
c9d891f1 RA |
115 | 'params': { |
116 | 'noplaylist': True, | |
117 | 'skip_download': True, | |
add96eb9 | 118 | }, |
c9d891f1 RA |
119 | }, { |
120 | 'url': 'https://www.patreon.com/posts/episode-166-of-743933', | |
121 | 'only_matching': True, | |
122 | }, { | |
123 | 'url': 'https://www.patreon.com/posts/743933', | |
124 | 'only_matching': True, | |
65af1839 | 125 | }, { |
126 | 'url': 'https://www.patreon.com/posts/kitchen-as-seen-51706779', | |
127 | 'md5': '96656690071f6d64895866008484251b', | |
128 | 'info_dict': { | |
129 | 'id': '555089736', | |
130 | 'ext': 'mp4', | |
131 | 'title': 'KITCHEN AS SEEN ON DEEZ NUTS EXTENDED!', | |
132 | 'uploader': 'Cold Ones', | |
133 | 'thumbnail': 're:^https?://.*$', | |
134 | 'upload_date': '20210526', | |
135 | 'description': 'md5:557a409bd79d3898689419094934ba79', | |
136 | 'uploader_id': '14936315', | |
137 | }, | |
add96eb9 | 138 | 'skip': 'Patron-only content', |
4f08e586 | 139 | }, { |
140 | # m3u8 video (https://github.com/yt-dlp/yt-dlp/issues/2277) | |
141 | 'url': 'https://www.patreon.com/posts/video-sketchbook-32452882', | |
142 | 'info_dict': { | |
143 | 'id': '32452882', | |
144 | 'ext': 'mp4', | |
145 | 'comment_count': int, | |
146 | 'uploader_id': '4301314', | |
147 | 'like_count': int, | |
148 | 'timestamp': 1576696962, | |
149 | 'upload_date': '20191218', | |
150 | 'thumbnail': r're:^https?://.*$', | |
151 | 'uploader_url': 'https://www.patreon.com/loish', | |
152 | 'description': 'md5:e2693e97ee299c8ece47ffdb67e7d9d2', | |
153 | 'title': 'VIDEO // sketchbook flipthrough', | |
154 | 'uploader': 'Loish ', | |
155 | 'tags': ['sketchbook', 'video'], | |
156 | 'channel_id': '1641751', | |
157 | 'channel_url': 'https://www.patreon.com/loish', | |
158 | 'channel_follower_count': int, | |
add96eb9 | 159 | }, |
cea4b857 | 160 | }, { |
161 | # bad videos under media (if media is included). Real one is under post_file | |
162 | 'url': 'https://www.patreon.com/posts/premium-access-70282931', | |
163 | 'info_dict': { | |
164 | 'id': '70282931', | |
165 | 'ext': 'mp4', | |
166 | 'title': '[Premium Access + Uncut] The Office - 2x6 The Fight - Group Reaction', | |
167 | 'channel_url': 'https://www.patreon.com/thenormies', | |
168 | 'channel_id': '573397', | |
169 | 'uploader_id': '2929435', | |
170 | 'uploader': 'The Normies', | |
171 | 'description': 'md5:79c9fd8778e2cef84049a94c058a5e23', | |
172 | 'comment_count': int, | |
173 | 'upload_date': '20220809', | |
174 | 'thumbnail': r're:^https?://.*$', | |
175 | 'channel_follower_count': int, | |
176 | 'like_count': int, | |
177 | 'timestamp': 1660052820, | |
178 | 'tags': ['The Office', 'early access', 'uncut'], | |
179 | 'uploader_url': 'https://www.patreon.com/thenormies', | |
180 | }, | |
181 | 'skip': 'Patron-only content', | |
36b240f9 JV |
182 | }, { |
183 | # dead vimeo and embed URLs, need to extract post_file | |
184 | 'url': 'https://www.patreon.com/posts/hunter-x-hunter-34007913', | |
185 | 'info_dict': { | |
186 | 'id': '34007913', | |
187 | 'ext': 'mp4', | |
188 | 'title': 'Hunter x Hunter | Kurapika DESTROYS Uvogin!!!', | |
189 | 'like_count': int, | |
190 | 'uploader': 'YaBoyRoshi', | |
191 | 'timestamp': 1581636833, | |
192 | 'channel_url': 'https://www.patreon.com/yaboyroshi', | |
193 | 'thumbnail': r're:^https?://.*$', | |
194 | 'tags': ['Hunter x Hunter'], | |
195 | 'uploader_id': '14264111', | |
196 | 'comment_count': int, | |
197 | 'channel_follower_count': int, | |
198 | 'description': 'Kurapika is a walking cheat code!', | |
199 | 'upload_date': '20200213', | |
200 | 'channel_id': '2147162', | |
201 | 'uploader_url': 'https://www.patreon.com/yaboyroshi', | |
202 | }, | |
c9ce57d9 | 203 | }, { |
204 | # NSFW vimeo embed URL | |
205 | 'url': 'https://www.patreon.com/posts/4k-spiderman-4k-96414599', | |
206 | 'info_dict': { | |
207 | 'id': '902250943', | |
208 | 'ext': 'mp4', | |
209 | 'title': '❤️(4K) Spiderman Girl Yeonhwa’s Gift ❤️(4K) 스파이더맨걸 연화의 선물', | |
210 | 'description': '❤️(4K) Spiderman Girl Yeonhwa’s Gift \n❤️(4K) 스파이더맨걸 연화의 선물', | |
211 | 'uploader': 'Npickyeonhwa', | |
212 | 'uploader_id': '90574422', | |
213 | 'uploader_url': 'https://www.patreon.com/Yeonhwa726', | |
214 | 'channel_id': '10237902', | |
215 | 'channel_url': 'https://www.patreon.com/Yeonhwa726', | |
216 | 'duration': 70, | |
217 | 'timestamp': 1705150153, | |
218 | 'upload_date': '20240113', | |
219 | 'comment_count': int, | |
220 | 'like_count': int, | |
221 | 'thumbnail': r're:^https?://.+', | |
222 | }, | |
223 | 'params': {'skip_download': 'm3u8'}, | |
036e0d92 | 224 | }, { |
225 | # multiple attachments/embeds | |
226 | 'url': 'https://www.patreon.com/posts/holy-wars-solos-100601977', | |
227 | 'playlist_count': 3, | |
228 | 'info_dict': { | |
229 | 'id': '100601977', | |
230 | 'title': '"Holy Wars" (Megadeth) Solos Transcription & Lesson/Analysis', | |
231 | 'description': 'md5:d099ab976edfce6de2a65c2b169a88d3', | |
232 | 'uploader': 'Bradley Hall', | |
233 | 'uploader_id': '24401883', | |
234 | 'uploader_url': 'https://www.patreon.com/bradleyhallguitar', | |
235 | 'channel_id': '3193932', | |
236 | 'channel_url': 'https://www.patreon.com/bradleyhallguitar', | |
237 | 'channel_follower_count': int, | |
238 | 'timestamp': 1710777855, | |
239 | 'upload_date': '20240318', | |
240 | 'like_count': int, | |
241 | 'comment_count': int, | |
242 | 'thumbnail': r're:^https?://.+', | |
243 | }, | |
244 | 'skip': 'Patron-only content', | |
4f08e586 | 245 | }] |
036e0d92 | 246 | _RETURN_TYPE = 'video' |
a00d73c8 EJ |
247 | |
248 | def _real_extract(self, url): | |
77070040 | 249 | video_id = self._match_id(url) |
4f08e586 | 250 | post = self._call_api( |
251 | f'posts/{video_id}', video_id, query={ | |
b77c3949 | 252 | 'fields[media]': 'download_url,mimetype,size_bytes', |
4f08e586 | 253 | 'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title,current_user_can_view', |
b77c3949 | 254 | 'fields[user]': 'full_name,url', |
4f08e586 | 255 | 'fields[post_tag]': 'value', |
256 | 'fields[campaign]': 'url,name,patron_count', | |
b77c3949 | 257 | 'json-api-use-default-includes': 'false', |
cea4b857 | 258 | 'include': 'audio,user,user_defined_tags,campaign,attachments_media', |
b77c3949 | 259 | }) |
c9d891f1 | 260 | attributes = post['data']['attributes'] |
036e0d92 | 261 | info = traverse_obj(attributes, { |
262 | 'title': ('title', {str.strip}), | |
263 | 'description': ('content', {clean_html}), | |
264 | 'thumbnail': ('image', ('large_url', 'url'), {url_or_none}, any), | |
265 | 'timestamp': ('published_at', {parse_iso8601}), | |
266 | 'like_count': ('like_count', {int_or_none}), | |
267 | 'comment_count': ('comment_count', {int_or_none}), | |
268 | }) | |
c9d891f1 | 269 | |
036e0d92 | 270 | entries = [] |
271 | idx = 0 | |
272 | for include in traverse_obj(post, ('included', lambda _, v: v['type'])): | |
273 | include_type = include['type'] | |
274 | if include_type == 'media': | |
275 | media_attributes = traverse_obj(include, ('attributes', {dict})) or {} | |
276 | download_url = url_or_none(media_attributes.get('download_url')) | |
b77c3949 | 277 | ext = mimetype2ext(media_attributes.get('mimetype')) |
cea4b857 | 278 | |
279 | # if size_bytes is None, this media file is likely unavailable | |
280 | # See: https://github.com/yt-dlp/yt-dlp/issues/4608 | |
281 | size_bytes = int_or_none(media_attributes.get('size_bytes')) | |
282 | if download_url and ext in KNOWN_EXTENSIONS and size_bytes is not None: | |
036e0d92 | 283 | idx += 1 |
284 | entries.append({ | |
285 | 'id': f'{video_id}-{idx}', | |
b77c3949 | 286 | 'ext': ext, |
cea4b857 | 287 | 'filesize': size_bytes, |
b77c3949 | 288 | 'url': download_url, |
c9d891f1 RA |
289 | }) |
290 | ||
036e0d92 | 291 | elif include_type == 'user': |
292 | info.update(traverse_obj(include, { | |
293 | 'uploader': ('attributes', 'full_name', {str}), | |
294 | 'uploader_id': ('id', {str_or_none}), | |
295 | 'uploader_url': ('attributes', 'url', {url_or_none}), | |
296 | })) | |
65af1839 | 297 | |
036e0d92 | 298 | elif include_type == 'post_tag': |
299 | if post_tag := traverse_obj(include, ('attributes', 'value', {str})): | |
300 | info.setdefault('tags', []).append(post_tag) | |
301 | ||
302 | elif include_type == 'campaign': | |
303 | info.update(traverse_obj(include, { | |
304 | 'channel': ('attributes', 'title', {str}), | |
305 | 'channel_id': ('id', {str_or_none}), | |
306 | 'channel_url': ('attributes', 'url', {url_or_none}), | |
307 | 'channel_follower_count': ('attributes', 'patron_count', {int_or_none}), | |
308 | })) | |
19a35285 | 309 | |
d6c2c2bc | 310 | # all-lowercase 'referer' so we can smuggle it to Generic, SproutVideo, Vimeo |
311 | headers = {'referer': 'https://patreon.com/'} | |
312 | ||
4f08e586 | 313 | # handle Vimeo embeds |
c9ce57d9 | 314 | if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo': |
315 | v_url = urllib.parse.unquote(self._html_search_regex( | |
316 | r'(https(?:%3A%2F%2F|://)player\.vimeo\.com.+app_id(?:=|%3D)+\d+)', | |
317 | traverse_obj(attributes, ('embed', 'html', {str})), 'vimeo url', fatal=False) or '') | |
318 | if url_or_none(v_url) and self._request_webpage( | |
d6c2c2bc | 319 | v_url, video_id, 'Checking Vimeo embed URL', headers=headers, fatal=False, errnote=False): |
036e0d92 | 320 | entries.append(self.url_result( |
c9ce57d9 | 321 | VimeoIE._smuggle_referrer(v_url, 'https://patreon.com/'), |
036e0d92 | 322 | VimeoIE, url_transparent=True)) |
4f08e586 | 323 | |
c9ce57d9 | 324 | embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none})) |
d6c2c2bc | 325 | if embed_url and (urlh := self._request_webpage( |
326 | embed_url, video_id, 'Checking embed URL', headers=headers, | |
327 | fatal=False, errnote=False, expected_status=403)): | |
328 | # Password-protected vids.io embeds return 403 errors w/o --video-password or session cookie | |
329 | if urlh.status != 403 or VidsIoIE.suitable(embed_url): | |
330 | entries.append(self.url_result(smuggle_url(embed_url, headers))) | |
4f08e586 | 331 | |
036e0d92 | 332 | post_file = traverse_obj(attributes, ('post_file', {dict})) |
4f08e586 | 333 | if post_file: |
334 | name = post_file.get('name') | |
335 | ext = determine_ext(name) | |
b77c3949 | 336 | if ext in KNOWN_EXTENSIONS: |
036e0d92 | 337 | entries.append({ |
338 | 'id': video_id, | |
b77c3949 RA |
339 | 'ext': ext, |
340 | 'url': post_file['url'], | |
036e0d92 | 341 | }) |
f0e8bc7c | 342 | elif name == 'video' or determine_ext(post_file.get('url')) == 'm3u8': |
4f08e586 | 343 | formats, subtitles = self._extract_m3u8_formats_and_subtitles(post_file['url'], video_id) |
036e0d92 | 344 | entries.append({ |
345 | 'id': video_id, | |
4f08e586 | 346 | 'formats': formats, |
347 | 'subtitles': subtitles, | |
036e0d92 | 348 | }) |
c9d891f1 | 349 | |
036e0d92 | 350 | can_view_post = traverse_obj(attributes, 'current_user_can_view') |
351 | comments = None | |
352 | if can_view_post and info.get('comment_count'): | |
353 | comments = self.extract_comments(video_id) | |
354 | ||
355 | if not entries and can_view_post is False: | |
4f08e586 | 356 | self.raise_no_formats('You do not have access to this post', video_id=video_id, expected=True) |
036e0d92 | 357 | elif not entries: |
4f08e586 | 358 | self.raise_no_formats('No supported media found in this post', video_id=video_id, expected=True) |
036e0d92 | 359 | elif len(entries) == 1: |
360 | info.update(entries[0]) | |
361 | else: | |
362 | for entry in entries: | |
363 | entry.update(info) | |
364 | return self.playlist_result(entries, video_id, **info, __post_extractor=comments) | |
365 | ||
366 | info['id'] = video_id | |
367 | info['__post_extractor'] = comments | |
c9d891f1 | 368 | return info |
1dd6d9ca | 369 | |
4f08e586 | 370 | def _get_comments(self, post_id): |
371 | cursor = None | |
372 | count = 0 | |
373 | params = { | |
374 | 'page[count]': 50, | |
375 | 'include': 'parent.commenter.campaign,parent.post.user,parent.post.campaign.creator,parent.replies.parent,parent.replies.commenter.campaign,parent.replies.post.user,parent.replies.post.campaign.creator,commenter.campaign,post.user,post.campaign.creator,replies.parent,replies.commenter.campaign,replies.post.user,replies.post.campaign.creator,on_behalf_of_campaign', | |
376 | 'fields[comment]': 'body,created,is_by_creator', | |
377 | 'fields[user]': 'image_url,full_name,url', | |
378 | 'filter[flair]': 'image_tiny_url,name', | |
379 | 'sort': '-created', | |
380 | 'json-api-version': 1.0, | |
381 | 'json-api-use-default-includes': 'false', | |
382 | } | |
383 | ||
384 | for page in itertools.count(1): | |
385 | ||
386 | params.update({'page[cursor]': cursor} if cursor else {}) | |
387 | response = self._call_api( | |
add96eb9 | 388 | f'posts/{post_id}/comments', post_id, query=params, note=f'Downloading comments page {page}') |
4f08e586 | 389 | |
390 | cursor = None | |
6839ae1f | 391 | for comment in traverse_obj(response, (('data', ('included', lambda _, v: v['type'] == 'comment')), ...)): |
4f08e586 | 392 | count += 1 |
393 | comment_id = comment.get('id') | |
394 | attributes = comment.get('attributes') or {} | |
395 | if comment_id is None: | |
396 | continue | |
397 | author_id = traverse_obj(comment, ('relationships', 'commenter', 'data', 'id')) | |
398 | author_info = traverse_obj( | |
399 | response, ('included', lambda _, v: v['id'] == author_id and v['type'] == 'user', 'attributes'), | |
400 | get_all=False, expected_type=dict, default={}) | |
401 | ||
402 | yield { | |
403 | 'id': comment_id, | |
404 | 'text': attributes.get('body'), | |
405 | 'timestamp': parse_iso8601(attributes.get('created')), | |
406 | 'parent': traverse_obj(comment, ('relationships', 'parent', 'data', 'id'), default='root'), | |
407 | 'author_is_uploader': attributes.get('is_by_creator'), | |
408 | 'author_id': author_id, | |
409 | 'author': author_info.get('full_name'), | |
410 | 'author_thumbnail': author_info.get('image_url'), | |
411 | } | |
412 | ||
413 | if count < traverse_obj(response, ('meta', 'count')): | |
414 | cursor = traverse_obj(response, ('data', -1, 'id')) | |
415 | ||
416 | if cursor is None: | |
417 | break | |
1dd6d9ca | 418 | |
1dd6d9ca | 419 | |
4f08e586 | 420 | class PatreonCampaignIE(PatreonBaseIE): |
1dd6d9ca | 421 | |
4f08e586 | 422 | _VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P<campaign_id>\d+))|(?P<vanity>[-\w]+))' |
1dd6d9ca | 423 | _TESTS = [{ |
424 | 'url': 'https://www.patreon.com/dissonancepod/', | |
425 | 'info_dict': { | |
4f08e586 | 426 | 'title': 'Cognitive Dissonance Podcast', |
427 | 'channel_url': 'https://www.patreon.com/dissonancepod', | |
428 | 'id': '80642', | |
429 | 'description': 'md5:eb2fa8b83da7ab887adeac34da6b7af7', | |
430 | 'channel_id': '80642', | |
431 | 'channel': 'Cognitive Dissonance Podcast', | |
432 | 'age_limit': 0, | |
433 | 'channel_follower_count': int, | |
434 | 'uploader_id': '87145', | |
435 | 'uploader_url': 'https://www.patreon.com/dissonancepod', | |
436 | 'uploader': 'Cognitive Dissonance Podcast', | |
437 | 'thumbnail': r're:^https?://.*$', | |
1dd6d9ca | 438 | }, |
439 | 'playlist_mincount': 68, | |
4f08e586 | 440 | }, { |
441 | 'url': 'https://www.patreon.com/m/4767637/posts', | |
442 | 'info_dict': { | |
443 | 'title': 'Not Just Bikes', | |
444 | 'channel_follower_count': int, | |
445 | 'id': '4767637', | |
446 | 'channel_id': '4767637', | |
447 | 'channel_url': 'https://www.patreon.com/notjustbikes', | |
448 | 'description': 'md5:595c6e7dca76ae615b1d38c298a287a1', | |
449 | 'age_limit': 0, | |
450 | 'channel': 'Not Just Bikes', | |
451 | 'uploader_url': 'https://www.patreon.com/notjustbikes', | |
452 | 'uploader': 'Not Just Bikes', | |
453 | 'uploader_id': '37306634', | |
454 | 'thumbnail': r're:^https?://.*$', | |
455 | }, | |
add96eb9 | 456 | 'playlist_mincount': 71, |
1dd6d9ca | 457 | }, { |
458 | 'url': 'https://www.patreon.com/dissonancepod/posts', | |
add96eb9 | 459 | 'only_matching': True, |
4f08e586 | 460 | }, { |
461 | 'url': 'https://www.patreon.com/m/5932659', | |
add96eb9 | 462 | 'only_matching': True, |
4f08e586 | 463 | }] |
1dd6d9ca | 464 | |
465 | @classmethod | |
466 | def suitable(cls, url): | |
add96eb9 | 467 | return False if PatreonIE.suitable(url) else super().suitable(url) |
1dd6d9ca | 468 | |
4f08e586 | 469 | def _entries(self, campaign_id): |
1dd6d9ca | 470 | cursor = None |
471 | params = { | |
4f08e586 | 472 | 'fields[post]': 'patreon_url,url', |
1dd6d9ca | 473 | 'filter[campaign_id]': campaign_id, |
474 | 'filter[is_draft]': 'false', | |
475 | 'sort': '-published_at', | |
1dd6d9ca | 476 | 'json-api-use-default-includes': 'false', |
477 | } | |
478 | ||
479 | for page in itertools.count(1): | |
480 | ||
481 | params.update({'page[cursor]': cursor} if cursor else {}) | |
add96eb9 | 482 | posts_json = self._call_api('posts', campaign_id, query=params, note=f'Downloading posts page {page}') |
1dd6d9ca | 483 | |
4f08e586 | 484 | cursor = traverse_obj(posts_json, ('meta', 'pagination', 'cursors', 'next')) |
11de6fec | 485 | for post_url in traverse_obj(posts_json, ('data', ..., 'attributes', 'patreon_url')): |
486 | yield self.url_result(urljoin('https://www.patreon.com/', post_url), PatreonIE) | |
1dd6d9ca | 487 | |
488 | if cursor is None: | |
489 | break | |
490 | ||
491 | def _real_extract(self, url): | |
492 | ||
4f08e586 | 493 | campaign_id, vanity = self._match_valid_url(url).group('campaign_id', 'vanity') |
494 | if campaign_id is None: | |
495 | webpage = self._download_webpage(url, vanity, headers={'User-Agent': self.USER_AGENT}) | |
2e5a47da | 496 | campaign_id = self._search_nextjs_data( |
497 | webpage, vanity)['props']['pageProps']['bootstrapEnvelope']['pageBootstrap']['campaign']['data']['id'] | |
4f08e586 | 498 | |
499 | params = { | |
500 | 'json-api-use-default-includes': 'false', | |
501 | 'fields[user]': 'full_name,url', | |
502 | 'fields[campaign]': 'name,summary,url,patron_count,creation_count,is_nsfw,avatar_photo_url', | |
add96eb9 | 503 | 'include': 'creator', |
4f08e586 | 504 | } |
505 | ||
506 | campaign_response = self._call_api( | |
507 | f'campaigns/{campaign_id}', campaign_id, | |
508 | note='Downloading campaign info', fatal=False, | |
509 | query=params) or {} | |
510 | ||
511 | campaign_info = campaign_response.get('data') or {} | |
512 | channel_name = traverse_obj(campaign_info, ('attributes', 'name')) | |
513 | user_info = traverse_obj( | |
514 | campaign_response, ('included', lambda _, v: v['type'] == 'user'), | |
515 | default={}, expected_type=dict, get_all=False) | |
516 | ||
517 | return { | |
518 | '_type': 'playlist', | |
519 | 'id': campaign_id, | |
520 | 'title': channel_name, | |
521 | 'entries': self._entries(campaign_id), | |
522 | 'description': clean_html(traverse_obj(campaign_info, ('attributes', 'summary'))), | |
523 | 'channel_url': traverse_obj(campaign_info, ('attributes', 'url')), | |
524 | 'channel_follower_count': int_or_none(traverse_obj(campaign_info, ('attributes', 'patron_count'))), | |
525 | 'channel_id': campaign_id, | |
526 | 'channel': channel_name, | |
527 | 'uploader_url': traverse_obj(user_info, ('attributes', 'url')), | |
528 | 'uploader_id': str_or_none(user_info.get('id')), | |
529 | 'uploader': traverse_obj(user_info, ('attributes', 'full_name')), | |
530 | 'playlist_count': traverse_obj(campaign_info, ('attributes', 'creation_count')), | |
531 | 'age_limit': 18 if traverse_obj(campaign_info, ('attributes', 'is_nsfw')) else 0, | |
532 | 'thumbnail': url_or_none(traverse_obj(campaign_info, ('attributes', 'avatar_photo_url'))), | |
533 | } |