projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 22f5f5c6 AJ |
1 | # coding: utf-8 |
| 2 | from __future__ import unicode_literals | |
| 3 | ||
| 4 | import re | |
| 5 | from .common import InfoExtractor | |
| 6 | from ..utils import parse_duration, merge_dicts | |
| 7 | ||
| 8 | ||
| 9 | class MallTVIE(InfoExtractor): | |
| 10 | _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:.+/)?(?P<id>.+)(?:\?.*$|$)' | |
| 11 | _TESTS = [ | |
| 12 | { | |
| 13 | 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', | |
| 14 | 'md5': '9ced0de056534410837077e23bfba796', | |
| 15 | 'info_dict': { | |
| 16 | 'id': 't0zzt0', | |
| 17 | 'ext': 'mp4', | |
| 18 | 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', | |
| 19 | 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', | |
| 20 | 'upload_date': '20181007', | |
| 21 | 'timestamp': 1538870400 | |
| 22 | } | |
| 23 | }, | |
| 24 | { | |
| 25 | 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice', | |
| 26 | 'md5': '9ced0de056534410837077e23bfba796', | |
| 27 | 'only_matching': 1, | |
| 28 | 'info_dict': { | |
| 29 | 'id': 't0zzt0', | |
| 30 | 'ext': 'mp4', | |
| 31 | 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?', | |
| 32 | 'description': 'Pokud někdo hospodaří s penězmi daňových poplatníků, pak logicky chceme vědět, jak s nimi nakládá. Objem dotací pro neziskovky roste, ale opravdu jsou tyto organizace „pijavice", jak o nich hovoří And', | |
| 33 | 'upload_date': '20181007', | |
| 34 | 'timestamp': 1538870400 | |
| 35 | } | |
| 36 | } | |
| 37 | ] | |
| 38 | ||
| 39 | def _real_extract(self, url): | |
| 40 | display_id = self._match_id(url) | |
| 41 | webpage = self._download_webpage(url, display_id) | |
| 42 | src_id_regex = r'(?P<src><source src=([\"\'])?.+?/(?P<id>\w{6,}?)/index)(?P<after>\1?[^>]*?>)' | |
| 43 | video_id = self._search_regex(src_id_regex, webpage, 'ID', | |
| 44 | group='id') | |
| 45 | info = self._search_json_ld(webpage, video_id, default={}) | |
| 46 | html = re.sub(src_id_regex, r'\g<src>.m3u8\g<after>', webpage) | |
| 47 | media = self._parse_html5_media_entries(url, html, video_id) | |
| 48 | thumbnail = info.get('thumbnail', self._og_search_thumbnail(webpage)) | |
| 49 | duration = parse_duration(info.get('duration')) | |
| 50 | result = { | |
| 51 | 'id': video_id, | |
| 52 | 'title': info.get('title', self._og_search_title(webpage)), | |
| 53 | 'description': self._og_search_description(webpage) | |
| 54 | } | |
| 55 | result.update({'thumbnail': thumbnail}) | |
| 56 | result.update({'duration': duration}) | |
| 57 | ||
| 58 | return merge_dicts(media[0], info, result) |