]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | from __future__ import unicode_literals | |
3 | ||
4 | from .common import InfoExtractor | |
5 | from ..utils import ( | |
6 | bool_or_none, | |
7 | ExtractorError, | |
8 | dict_get, | |
9 | float_or_none, | |
10 | int_or_none, | |
11 | str_or_none, | |
12 | traverse_obj, | |
13 | try_get, | |
14 | url_or_none, | |
15 | urljoin, | |
16 | ) | |
17 | ||
18 | ||
19 | class GettrBaseIE(InfoExtractor): | |
20 | _BASE_REGEX = r'https?://(www\.)?gettr\.com/' | |
21 | _MEDIA_BASE_URL = 'https://media.gettr.com/' | |
22 | ||
23 | def _call_api(self, path, video_id, *args, **kwargs): | |
24 | return self._download_json(urljoin('https://api.gettr.com/u/', path), video_id, *args, **kwargs)['result'] | |
25 | ||
26 | ||
27 | class GettrIE(GettrBaseIE): | |
28 | _VALID_URL = GettrBaseIE._BASE_REGEX + r'post/(?P<id>[a-z0-9]+)' | |
29 | ||
30 | _TESTS = [{ | |
31 | 'url': 'https://www.gettr.com/post/pcf6uv838f', | |
32 | 'info_dict': { | |
33 | 'id': 'pcf6uv838f', | |
34 | 'title': 'md5:9086a646bbd06c41c4fe8e52b3c93454', | |
35 | 'description': 'md5:be0577f1e4caadc06de4a002da2bf287', | |
36 | 'ext': 'mp4', | |
37 | 'uploader': 'EpochTV', | |
38 | 'uploader_id': 'epochtv', | |
39 | 'upload_date': '20210927', | |
40 | 'thumbnail': r're:^https?://.+/out\.jpg', | |
41 | 'timestamp': 1632782451.058, | |
42 | 'duration': 58.5585, | |
43 | 'tags': ['hornofafrica', 'explorations'], | |
44 | } | |
45 | }, { | |
46 | 'url': 'https://gettr.com/post/p4iahp', | |
47 | 'info_dict': { | |
48 | 'id': 'p4iahp', | |
49 | 'title': 'md5:b03c07883db6fbc1aab88877a6c3b149', | |
50 | 'description': 'md5:741b7419d991c403196ed2ea7749a39d', | |
51 | 'ext': 'mp4', | |
52 | 'uploader': 'Neues Forum Freiheit', | |
53 | 'uploader_id': 'nf_freiheit', | |
54 | 'upload_date': '20210718', | |
55 | 'thumbnail': r're:^https?://.+/out\.jpg', | |
56 | 'timestamp': 1626594455.017, | |
57 | 'duration': 23, | |
58 | 'tags': 'count:12', | |
59 | } | |
60 | }, { | |
61 | # quote post | |
62 | 'url': 'https://gettr.com/post/pxn5b743a9', | |
63 | 'only_matching': True, | |
64 | }, { | |
65 | # quote with video | |
66 | 'url': 'https://gettr.com/post/pxtiiz5ca2', | |
67 | 'only_matching': True, | |
68 | }, { | |
69 | # streaming embed | |
70 | 'url': 'https://gettr.com/post/pxlu8p3b13', | |
71 | 'only_matching': True, | |
72 | }, { | |
73 | # youtube embed | |
74 | 'url': 'https://gettr.com/post/pv6wp9e24c', | |
75 | 'only_matching': True, | |
76 | 'add_ie': ['Youtube'], | |
77 | }] | |
78 | ||
79 | def _real_extract(self, url): | |
80 | post_id = self._match_id(url) | |
81 | webpage = self._download_webpage(url, post_id) | |
82 | api_data = self._call_api('post/%s?incl="poststats|userinfo"' % post_id, post_id) | |
83 | ||
84 | post_data = api_data.get('data') | |
85 | user_data = try_get(api_data, lambda x: x['aux']['uinf'][post_data['uid']], dict) or {} | |
86 | ||
87 | vid = post_data.get('vid') | |
88 | ovid = post_data.get('ovid') | |
89 | ||
90 | if post_data.get('p_type') == 'stream': | |
91 | return self.url_result(f'https://gettr.com/streaming/{post_id}', ie='GettrStreaming', video_id=post_id) | |
92 | ||
93 | if not (ovid or vid): | |
94 | embed_url = url_or_none(post_data.get('prevsrc')) | |
95 | shared_post_id = traverse_obj(api_data, ('aux', 'shrdpst', '_id'), ('data', 'rpstIds', 0), expected_type=str) | |
96 | ||
97 | if embed_url: | |
98 | return self.url_result(embed_url) | |
99 | elif shared_post_id: | |
100 | return self.url_result(f'https://gettr.com/post/{shared_post_id}', ie='Gettr', video_id=shared_post_id) | |
101 | else: | |
102 | raise ExtractorError('There\'s no video in this post.') | |
103 | ||
104 | title = description = str_or_none( | |
105 | post_data.get('txt') or self._og_search_description(webpage)) | |
106 | ||
107 | uploader = str_or_none( | |
108 | user_data.get('nickname') | |
109 | or self._search_regex(r'^(.+?) on GETTR', self._og_search_title(webpage, default=''), 'uploader', fatal=False)) | |
110 | ||
111 | if uploader: | |
112 | title = '%s - %s' % (uploader, title) | |
113 | ||
114 | formats, subtitles = self._extract_m3u8_formats_and_subtitles( | |
115 | urljoin(self._MEDIA_BASE_URL, vid), post_id, 'mp4', | |
116 | entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if vid else ([], {}) | |
117 | ||
118 | if ovid: | |
119 | formats.append({ | |
120 | 'url': urljoin(self._MEDIA_BASE_URL, ovid), | |
121 | 'format_id': 'ovid', | |
122 | 'ext': 'mp4', | |
123 | 'width': int_or_none(post_data.get('vid_wid')), | |
124 | 'height': int_or_none(post_data.get('vid_hgt')), | |
125 | }) | |
126 | ||
127 | self._sort_formats(formats) | |
128 | ||
129 | return { | |
130 | 'id': post_id, | |
131 | 'title': title, | |
132 | 'description': description, | |
133 | 'formats': formats, | |
134 | 'subtitles': subtitles, | |
135 | 'uploader': uploader, | |
136 | 'uploader_id': str_or_none( | |
137 | dict_get(user_data, ['_id', 'username']) | |
138 | or post_data.get('uid')), | |
139 | 'thumbnail': url_or_none( | |
140 | urljoin(self._MEDIA_BASE_URL, post_data.get('main')) | |
141 | or self._html_search_meta(['og:image', 'image'], webpage, 'thumbnail', fatal=False)), | |
142 | 'timestamp': float_or_none(dict_get(post_data, ['cdate', 'udate']), scale=1000), | |
143 | 'duration': float_or_none(post_data.get('vid_dur')), | |
144 | 'tags': post_data.get('htgs'), | |
145 | } | |
146 | ||
147 | ||
148 | class GettrStreamingIE(GettrBaseIE): | |
149 | _VALID_URL = GettrBaseIE._BASE_REGEX + r'streaming/(?P<id>[a-z0-9]+)' | |
150 | ||
151 | _TESTS = [{ | |
152 | 'url': 'https://gettr.com/streaming/psoiulc122', | |
153 | 'info_dict': { | |
154 | 'id': 'psoiulc122', | |
155 | 'ext': 'mp4', | |
156 | 'description': 'md5:56bca4b8f48f1743d9fd03d49c723017', | |
157 | 'view_count': int, | |
158 | 'uploader': 'Corona Investigative Committee', | |
159 | 'uploader_id': 'coronacommittee', | |
160 | 'duration': 5180.184, | |
161 | 'thumbnail': r're:^https?://.+', | |
162 | 'title': 'Day 1: Opening Session of the Grand Jury Proceeding', | |
163 | 'timestamp': 1644080997.164, | |
164 | 'upload_date': '20220205', | |
165 | } | |
166 | }, { | |
167 | 'url': 'https://gettr.com/streaming/psfmeefcc1', | |
168 | 'info_dict': { | |
169 | 'id': 'psfmeefcc1', | |
170 | 'ext': 'mp4', | |
171 | 'title': 'Session 90: "The Virus Of Power"', | |
172 | 'view_count': int, | |
173 | 'uploader_id': 'coronacommittee', | |
174 | 'description': 'md5:98986acdf656aa836bf36f9c9704c65b', | |
175 | 'uploader': 'Corona Investigative Committee', | |
176 | 'thumbnail': r're:^https?://.+', | |
177 | 'duration': 21872.507, | |
178 | 'timestamp': 1643976662.858, | |
179 | 'upload_date': '20220204', | |
180 | } | |
181 | }] | |
182 | ||
183 | def _real_extract(self, url): | |
184 | video_id = self._match_id(url) | |
185 | video_info = self._call_api('live/join/%s' % video_id, video_id, data={}) | |
186 | ||
187 | live_info = video_info['broadcast'] | |
188 | live_url = url_or_none(live_info.get('url')) | |
189 | ||
190 | formats, subtitles = self._extract_m3u8_formats_and_subtitles( | |
191 | live_url, video_id, ext='mp4', | |
192 | entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if live_url else ([], {}) | |
193 | ||
194 | thumbnails = [{ | |
195 | 'url': urljoin(self._MEDIA_BASE_URL, thumbnail), | |
196 | } for thumbnail in try_get(video_info, lambda x: x['postData']['imgs'], list) or []] | |
197 | ||
198 | self._sort_formats(formats) | |
199 | ||
200 | return { | |
201 | 'id': video_id, | |
202 | 'title': try_get(video_info, lambda x: x['postData']['ttl'], str), | |
203 | 'description': try_get(video_info, lambda x: x['postData']['dsc'], str), | |
204 | 'formats': formats, | |
205 | 'subtitles': subtitles, | |
206 | 'thumbnails': thumbnails, | |
207 | 'uploader': try_get(video_info, lambda x: x['liveHostInfo']['nickname'], str), | |
208 | 'uploader_id': try_get(video_info, lambda x: x['liveHostInfo']['_id'], str), | |
209 | 'view_count': int_or_none(live_info.get('viewsCount')), | |
210 | 'timestamp': float_or_none(live_info.get('startAt'), scale=1000), | |
211 | 'duration': float_or_none(live_info.get('duration'), scale=1000), | |
212 | 'is_live': bool_or_none(live_info.get('isLive')), | |
213 | } |