projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 3f771f75 LL |
1 | # coding: utf-8 |
| 2 | ||
| 3 | from .common import InfoExtractor | |
| 4 | from ..utils import ( | |
| 5 | clean_html, | |
| 6 | traverse_obj, | |
| 7 | unescapeHTML, | |
| 8 | ) | |
| 9 | ||
| 10 | import itertools | |
| 11 | from urllib.parse import urlencode | |
| 12 | ||
| 13 | ||
| 14 | class RadioKapitalBaseIE(InfoExtractor): | |
| 15 | def _call_api(self, resource, video_id, note='Downloading JSON metadata', qs={}): | |
| 16 | return self._download_json( | |
| 17 | f'https://www.radiokapital.pl/wp-json/kapital/v1/{resource}?{urlencode(qs)}', | |
| 18 | video_id, note=note) | |
| 19 | ||
| 20 | def _parse_episode(self, data): | |
| 21 | release = '%s%s%s' % (data['published'][6:11], data['published'][3:6], data['published'][:3]) | |
| 22 | return { | |
| 23 | '_type': 'url_transparent', | |
| 24 | 'url': data['mixcloud_url'], | |
| 25 | 'ie_key': 'Mixcloud', | |
| 26 | 'title': unescapeHTML(data['title']), | |
| 27 | 'description': clean_html(data.get('content')), | |
| 28 | 'tags': traverse_obj(data, ('tags', ..., 'name')), | |
| 29 | 'release_date': release, | |
| 30 | 'series': traverse_obj(data, ('show', 'title')), | |
| 31 | } | |
| 32 | ||
| 33 | ||
| 34 | class RadioKapitalIE(RadioKapitalBaseIE): | |
| 35 | IE_NAME = 'radiokapital' | |
| 36 | _VALID_URL = r'https?://(?:www\.)?radiokapital\.pl/shows/[a-z\d-]+/(?P<id>[a-z\d-]+)' | |
| 37 | ||
| 38 | _TESTS = [{ | |
| 39 | 'url': 'https://radiokapital.pl/shows/tutaj-sa-smoki/5-its-okay-to-be-immaterial', | |
| 40 | 'info_dict': { | |
| 41 | 'id': 'radiokapital_radio-kapitał-tutaj-są-smoki-5-its-okay-to-be-immaterial-2021-05-20', | |
| 42 | 'ext': 'm4a', | |
| 43 | 'title': '#5: It’s okay to\xa0be\xa0immaterial', | |
| 44 | 'description': 'md5:2499da5fbfb0e88333b7d37ec8e9e4c4', | |
| 45 | 'uploader': 'Radio Kapitał', | |
| 46 | 'uploader_id': 'radiokapital', | |
| 47 | 'timestamp': 1621640164, | |
| 48 | 'upload_date': '20210521', | |
| 49 | }, | |
| 50 | }] | |
| 51 | ||
| 52 | def _real_extract(self, url): | |
| 53 | video_id = self._match_id(url) | |
| 54 | ||
| 55 | episode = self._call_api('episodes/%s' % video_id, video_id) | |
| 56 | return self._parse_episode(episode) | |
| 57 | ||
| 58 | ||
| 59 | class RadioKapitalShowIE(RadioKapitalBaseIE): | |
| 60 | IE_NAME = 'radiokapital:show' | |
| 61 | _VALID_URL = r'https?://(?:www\.)?radiokapital\.pl/shows/(?P<id>[a-z\d-]+)/?(?:$|[?#])' | |
| 62 | ||
| 63 | _TESTS = [{ | |
| 64 | 'url': 'https://radiokapital.pl/shows/wesz', | |
| 65 | 'info_dict': { | |
| 66 | 'id': '100', | |
| 67 | 'title': 'WĘSZ', | |
| 68 | 'description': 'md5:3a557a1e0f31af612b0dcc85b1e0ca5c', | |
| 69 | }, | |
| 70 | 'playlist_mincount': 17, | |
| 71 | }] | |
| 72 | ||
| 73 | def _get_episode_list(self, series_id, page_no): | |
| 74 | return self._call_api( | |
| 75 | 'episodes', series_id, | |
| 76 | f'Downloading episode list page #{page_no}', qs={ | |
| 77 | 'show': series_id, | |
| 78 | 'page': page_no, | |
| 79 | }) | |
| 80 | ||
| 81 | def _entries(self, series_id): | |
| 82 | for page_no in itertools.count(1): | |
| 83 | episode_list = self._get_episode_list(series_id, page_no) | |
| 84 | yield from (self._parse_episode(ep) for ep in episode_list['items']) | |
| 85 | if episode_list['next'] is None: | |
| 86 | break | |
| 87 | ||
| 88 | def _real_extract(self, url): | |
| 89 | series_id = self._match_id(url) | |
| 90 | ||
| 91 | show = self._call_api(f'shows/{series_id}', series_id, 'Downloading show metadata') | |
| 92 | entries = self._entries(series_id) | |
| 93 | return { | |
| 94 | '_type': 'playlist', | |
| 95 | 'entries': entries, | |
| 96 | 'id': str(show['id']), | |
| 97 | 'title': show.get('title'), | |
| 98 | 'description': clean_html(show.get('content')), | |
| 99 | } |