]>
Commit | Line | Data |
---|---|---|
1 | from .common import InfoExtractor | |
2 | from ..utils import ( | |
3 | ExtractorError, | |
4 | traverse_obj, | |
5 | unified_strdate, | |
6 | ) | |
7 | ||
8 | ||
9 | class ProjectVeritasIE(InfoExtractor): | |
10 | _WORKING = False | |
11 | _VALID_URL = r'https?://(?:www\.)?projectveritas\.com/(?P<type>news|video)/(?P<id>[^/?#]+)' | |
12 | _TESTS = [{ | |
13 | 'url': 'https://www.projectveritas.com/news/exclusive-inside-the-new-york-and-new-jersey-hospitals-battling-coronavirus/', | |
14 | 'info_dict': { | |
15 | 'id': '51910aab-365a-5cf1-88f2-8eb1ca5fd3c6', | |
16 | 'ext': 'mp4', | |
17 | 'title': 'Exclusive: Inside The New York and New Jersey Hospitals Battling Coronavirus', | |
18 | 'upload_date': '20200327', | |
19 | 'thumbnail': 'md5:6076477fe50b03eb8708be9415e18e1c', | |
20 | } | |
21 | }, { | |
22 | 'url': 'https://www.projectveritas.com/video/ilhan-omar-connected-ballot-harvester-in-cash-for-ballots-scheme-car-is-full/', | |
23 | 'info_dict': { | |
24 | 'id': 'c5aab304-a56b-54b1-9f0b-03b77bc5f2f6', | |
25 | 'ext': 'mp4', | |
26 | 'title': 'Ilhan Omar connected Ballot Harvester in cash-for-ballots scheme: "Car is full" of absentee ballots', | |
27 | 'upload_date': '20200927', | |
28 | 'thumbnail': 'md5:194b8edf0e2ba64f25500ff4378369a4', | |
29 | } | |
30 | }] | |
31 | ||
32 | def _real_extract(self, url): | |
33 | id, type = self._match_valid_url(url).group('id', 'type') | |
34 | api_url = f'https://www.projectveritas.com/page-data/{type}/{id}/page-data.json' | |
35 | data_json = self._download_json(api_url, id)['result']['data'] | |
36 | main_data = traverse_obj(data_json, 'video', 'post') | |
37 | video_id = main_data['id'] | |
38 | thumbnail = traverse_obj(main_data, ('image', 'ogImage', 'src')) | |
39 | mux_asset = traverse_obj(main_data, | |
40 | 'muxAsset', ('body', 'json', 'content', ..., 'data', 'target', 'fields', 'muxAsset'), | |
41 | get_all=False, expected_type=dict) | |
42 | if not mux_asset: | |
43 | raise ExtractorError('No video on the provided url.', expected=True) | |
44 | playback_id = traverse_obj(mux_asset, 'playbackId', ('en-US', 'playbackId')) | |
45 | formats = self._extract_m3u8_formats(f'https://stream.mux.com/{playback_id}.m3u8', video_id) | |
46 | return { | |
47 | 'id': video_id, | |
48 | 'title': main_data['title'], | |
49 | 'upload_date': unified_strdate(main_data.get('date')), | |
50 | 'thumbnail': thumbnail.replace('//', ''), | |
51 | 'formats': formats, | |
52 | } |