]>
Commit | Line | Data |
---|---|---|
85187609 | 1 | from .common import InfoExtractor |
2 | from ..utils import ( | |
82b51767 | 3 | bool_or_none, |
85187609 | 4 | ExtractorError, |
5 | dict_get, | |
6 | float_or_none, | |
7 | int_or_none, | |
85187609 | 8 | str_or_none, |
b90dbe6c | 9 | traverse_obj, |
85187609 | 10 | try_get, |
11 | url_or_none, | |
12 | urljoin, | |
13 | ) | |
14 | ||
15 | ||
82b51767 | 16 | class GettrBaseIE(InfoExtractor): |
17 | _BASE_REGEX = r'https?://(www\.)?gettr\.com/' | |
85187609 | 18 | _MEDIA_BASE_URL = 'https://media.gettr.com/' |
19 | ||
82b51767 | 20 | def _call_api(self, path, video_id, *args, **kwargs): |
21 | return self._download_json(urljoin('https://api.gettr.com/u/', path), video_id, *args, **kwargs)['result'] | |
22 | ||
23 | ||
24 | class GettrIE(GettrBaseIE): | |
25 | _VALID_URL = GettrBaseIE._BASE_REGEX + r'post/(?P<id>[a-z0-9]+)' | |
26 | ||
85187609 | 27 | _TESTS = [{ |
28 | 'url': 'https://www.gettr.com/post/pcf6uv838f', | |
29 | 'info_dict': { | |
30 | 'id': 'pcf6uv838f', | |
31 | 'title': 'md5:9086a646bbd06c41c4fe8e52b3c93454', | |
32 | 'description': 'md5:be0577f1e4caadc06de4a002da2bf287', | |
33 | 'ext': 'mp4', | |
34 | 'uploader': 'EpochTV', | |
35 | 'uploader_id': 'epochtv', | |
b90dbe6c | 36 | 'upload_date': '20210927', |
85187609 | 37 | 'thumbnail': r're:^https?://.+/out\.jpg', |
b90dbe6c | 38 | 'timestamp': 1632782451.058, |
85187609 | 39 | 'duration': 58.5585, |
971c4847 | 40 | 'tags': ['hornofafrica', 'explorations'], |
85187609 | 41 | } |
42 | }, { | |
43 | 'url': 'https://gettr.com/post/p4iahp', | |
44 | 'info_dict': { | |
45 | 'id': 'p4iahp', | |
46 | 'title': 'md5:b03c07883db6fbc1aab88877a6c3b149', | |
47 | 'description': 'md5:741b7419d991c403196ed2ea7749a39d', | |
48 | 'ext': 'mp4', | |
49 | 'uploader': 'Neues Forum Freiheit', | |
50 | 'uploader_id': 'nf_freiheit', | |
b90dbe6c | 51 | 'upload_date': '20210718', |
85187609 | 52 | 'thumbnail': r're:^https?://.+/out\.jpg', |
b90dbe6c | 53 | 'timestamp': 1626594455.017, |
85187609 | 54 | 'duration': 23, |
971c4847 | 55 | 'tags': 'count:12', |
85187609 | 56 | } |
b90dbe6c | 57 | }, { |
58 | # quote post | |
59 | 'url': 'https://gettr.com/post/pxn5b743a9', | |
60 | 'only_matching': True, | |
61 | }, { | |
62 | # quote with video | |
63 | 'url': 'https://gettr.com/post/pxtiiz5ca2', | |
64 | 'only_matching': True, | |
65 | }, { | |
66 | # streaming embed | |
67 | 'url': 'https://gettr.com/post/pxlu8p3b13', | |
68 | 'only_matching': True, | |
69 | }, { | |
70 | # youtube embed | |
71 | 'url': 'https://gettr.com/post/pv6wp9e24c', | |
72 | 'only_matching': True, | |
73 | 'add_ie': ['Youtube'], | |
85187609 | 74 | }] |
75 | ||
76 | def _real_extract(self, url): | |
77 | post_id = self._match_id(url) | |
78 | webpage = self._download_webpage(url, post_id) | |
82b51767 | 79 | api_data = self._call_api('post/%s?incl="poststats|userinfo"' % post_id, post_id) |
85187609 | 80 | |
82b51767 | 81 | post_data = api_data.get('data') |
b90dbe6c | 82 | user_data = try_get(api_data, lambda x: x['aux']['uinf'][post_data['uid']], dict) or {} |
85187609 | 83 | |
b90dbe6c | 84 | vid = post_data.get('vid') |
85 | ovid = post_data.get('ovid') | |
86 | ||
87 | if post_data.get('p_type') == 'stream': | |
88 | return self.url_result(f'https://gettr.com/streaming/{post_id}', ie='GettrStreaming', video_id=post_id) | |
89 | ||
90 | if not (ovid or vid): | |
91 | embed_url = url_or_none(post_data.get('prevsrc')) | |
92 | shared_post_id = traverse_obj(api_data, ('aux', 'shrdpst', '_id'), ('data', 'rpstIds', 0), expected_type=str) | |
93 | ||
94 | if embed_url: | |
95 | return self.url_result(embed_url) | |
96 | elif shared_post_id: | |
97 | return self.url_result(f'https://gettr.com/post/{shared_post_id}', ie='Gettr', video_id=shared_post_id) | |
98 | else: | |
99 | raise ExtractorError('There\'s no video in this post.') | |
85187609 | 100 | |
101 | title = description = str_or_none( | |
102 | post_data.get('txt') or self._og_search_description(webpage)) | |
103 | ||
104 | uploader = str_or_none( | |
105 | user_data.get('nickname') | |
b90dbe6c | 106 | or self._search_regex(r'^(.+?) on GETTR', self._og_search_title(webpage, default=''), 'uploader', fatal=False)) |
107 | ||
85187609 | 108 | if uploader: |
109 | title = '%s - %s' % (uploader, title) | |
110 | ||
b90dbe6c | 111 | formats, subtitles = self._extract_m3u8_formats_and_subtitles( |
85187609 | 112 | urljoin(self._MEDIA_BASE_URL, vid), post_id, 'mp4', |
b90dbe6c | 113 | entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if vid else ([], {}) |
85187609 | 114 | |
115 | if ovid: | |
116 | formats.append({ | |
117 | 'url': urljoin(self._MEDIA_BASE_URL, ovid), | |
118 | 'format_id': 'ovid', | |
119 | 'ext': 'mp4', | |
120 | 'width': int_or_none(post_data.get('vid_wid')), | |
121 | 'height': int_or_none(post_data.get('vid_hgt')), | |
85187609 | 122 | }) |
123 | ||
124 | self._sort_formats(formats) | |
125 | ||
126 | return { | |
127 | 'id': post_id, | |
128 | 'title': title, | |
129 | 'description': description, | |
b90dbe6c | 130 | 'formats': formats, |
131 | 'subtitles': subtitles, | |
132 | 'uploader': uploader, | |
85187609 | 133 | 'uploader_id': str_or_none( |
134 | dict_get(user_data, ['_id', 'username']) | |
135 | or post_data.get('uid')), | |
b90dbe6c | 136 | 'thumbnail': url_or_none( |
137 | urljoin(self._MEDIA_BASE_URL, post_data.get('main')) | |
138 | or self._html_search_meta(['og:image', 'image'], webpage, 'thumbnail', fatal=False)), | |
139 | 'timestamp': float_or_none(dict_get(post_data, ['cdate', 'udate']), scale=1000), | |
85187609 | 140 | 'duration': float_or_none(post_data.get('vid_dur')), |
141 | 'tags': post_data.get('htgs'), | |
142 | } | |
82b51767 | 143 | |
144 | ||
145 | class GettrStreamingIE(GettrBaseIE): | |
146 | _VALID_URL = GettrBaseIE._BASE_REGEX + r'streaming/(?P<id>[a-z0-9]+)' | |
147 | ||
148 | _TESTS = [{ | |
149 | 'url': 'https://gettr.com/streaming/psoiulc122', | |
150 | 'info_dict': { | |
151 | 'id': 'psoiulc122', | |
152 | 'ext': 'mp4', | |
153 | 'description': 'md5:56bca4b8f48f1743d9fd03d49c723017', | |
154 | 'view_count': int, | |
155 | 'uploader': 'Corona Investigative Committee', | |
156 | 'uploader_id': 'coronacommittee', | |
157 | 'duration': 5180.184, | |
158 | 'thumbnail': r're:^https?://.+', | |
159 | 'title': 'Day 1: Opening Session of the Grand Jury Proceeding', | |
160 | 'timestamp': 1644080997.164, | |
161 | 'upload_date': '20220205', | |
162 | } | |
163 | }, { | |
164 | 'url': 'https://gettr.com/streaming/psfmeefcc1', | |
165 | 'info_dict': { | |
166 | 'id': 'psfmeefcc1', | |
167 | 'ext': 'mp4', | |
168 | 'title': 'Session 90: "The Virus Of Power"', | |
169 | 'view_count': int, | |
170 | 'uploader_id': 'coronacommittee', | |
171 | 'description': 'md5:98986acdf656aa836bf36f9c9704c65b', | |
172 | 'uploader': 'Corona Investigative Committee', | |
173 | 'thumbnail': r're:^https?://.+', | |
174 | 'duration': 21872.507, | |
175 | 'timestamp': 1643976662.858, | |
176 | 'upload_date': '20220204', | |
177 | } | |
178 | }] | |
179 | ||
180 | def _real_extract(self, url): | |
181 | video_id = self._match_id(url) | |
182 | video_info = self._call_api('live/join/%s' % video_id, video_id, data={}) | |
183 | ||
184 | live_info = video_info['broadcast'] | |
185 | live_url = url_or_none(live_info.get('url')) | |
186 | ||
187 | formats, subtitles = self._extract_m3u8_formats_and_subtitles( | |
188 | live_url, video_id, ext='mp4', | |
189 | entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if live_url else ([], {}) | |
190 | ||
191 | thumbnails = [{ | |
192 | 'url': urljoin(self._MEDIA_BASE_URL, thumbnail), | |
b90dbe6c | 193 | } for thumbnail in try_get(video_info, lambda x: x['postData']['imgs'], list) or []] |
82b51767 | 194 | |
195 | self._sort_formats(formats) | |
196 | ||
197 | return { | |
198 | 'id': video_id, | |
b90dbe6c | 199 | 'title': try_get(video_info, lambda x: x['postData']['ttl'], str), |
200 | 'description': try_get(video_info, lambda x: x['postData']['dsc'], str), | |
82b51767 | 201 | 'formats': formats, |
202 | 'subtitles': subtitles, | |
203 | 'thumbnails': thumbnails, | |
b90dbe6c | 204 | 'uploader': try_get(video_info, lambda x: x['liveHostInfo']['nickname'], str), |
205 | 'uploader_id': try_get(video_info, lambda x: x['liveHostInfo']['_id'], str), | |
82b51767 | 206 | 'view_count': int_or_none(live_info.get('viewsCount')), |
207 | 'timestamp': float_or_none(live_info.get('startAt'), scale=1000), | |
208 | 'duration': float_or_none(live_info.get('duration'), scale=1000), | |
209 | 'is_live': bool_or_none(live_info.get('isLive')), | |
210 | } |