projects / yt-dlp.git / blame
| Commit | Line | Data |
|---|---|---|
| 4dc19c09 NJ |
1 | # coding: utf-8 |
| 2 | from __future__ import unicode_literals | |
| 3 | ||
| 2512b174 S |
4 | import re |
| 5 | ||
| 4dc19c09 NJ |
6 | from .common import InfoExtractor |
| 7 | from ..utils import ( | |
| 8bdd16b4 | 8 | clean_html, |
| 9 | merge_dicts, | |
| 4dc19c09 NJ |
10 | ) |
| 11 | ||
| 12 | ||
| 13 | class LRTIE(InfoExtractor): | |
| 14 | IE_NAME = 'lrt.lt' | |
| 8bdd16b4 | 15 | _VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))' |
| 2512b174 S |
16 | _TESTS = [{ |
| 17 | # m3u8 download | |
| 8bdd16b4 | 18 | 'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene', |
| 19 | 'md5': '85cb2bb530f31d91a9c65b479516ade4', | |
| 4dc19c09 | 20 | 'info_dict': { |
| 8bdd16b4 | 21 | 'id': '2000127261', |
| 4dc19c09 | 22 | 'ext': 'mp4', |
| 8bdd16b4 | 23 | 'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė', |
| 24 | 'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa', | |
| 25 | 'duration': 3035, | |
| 26 | 'timestamp': 1604079000, | |
| 27 | 'upload_date': '20201030', | |
| 4dc19c09 | 28 | }, |
| 2512b174 S |
29 | }, { |
| 30 | # direct mp3 download | |
| 31 | 'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/', | |
| 32 | 'md5': '389da8ca3cad0f51d12bed0c844f6a0a', | |
| 33 | 'info_dict': { | |
| 34 | 'id': '1013074524', | |
| 35 | 'ext': 'mp3', | |
| 36 | 'title': 'Kita tema 2016-09-05 15:05', | |
| 37 | 'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5', | |
| 38 | 'duration': 3008, | |
| 39 | 'view_count': int, | |
| 40 | 'like_count': int, | |
| 4dc19c09 | 41 | }, |
| 2512b174 | 42 | }] |
| 4dc19c09 | 43 | |
| 8bdd16b4 | 44 | def _extract_js_var(self, webpage, var_name, default): |
| 45 | return self._search_regex( | |
| 46 | r'%s\s*=\s*(["\'])((?:(?!\1).)+)\1' % var_name, | |
| 47 | webpage, var_name.replace('_', ' '), default, group=2) | |
| 48 | ||
| 4dc19c09 | 49 | def _real_extract(self, url): |
| 8bdd16b4 | 50 | path, video_id = re.match(self._VALID_URL, url).groups() |
| 4dc19c09 NJ |
51 | webpage = self._download_webpage(url, video_id) |
| 52 | ||
| 8bdd16b4 | 53 | media_url = self._extract_js_var(webpage, 'main_url', path) |
| 54 | media = self._download_json(self._extract_js_var( | |
| 55 | webpage, 'media_info_url', | |
| 56 | 'https://www.lrt.lt/servisai/stream_url/vod/media_info/'), | |
| 57 | video_id, query={'url': media_url}) | |
| 58 | jw_data = self._parse_jwplayer_data( | |
| 59 | media['playlist_item'], video_id, base_url=url) | |
| f7e1d82d | 60 | |
| 8bdd16b4 | 61 | json_ld_data = self._search_json_ld(webpage, video_id) |
| 4dc19c09 | 62 | |
| 8bdd16b4 | 63 | tags = [] |
| 64 | for tag in (media.get('tags') or []): | |
| 65 | tag_name = tag.get('name') | |
| 66 | if not tag_name: | |
| 67 | continue | |
| 68 | tags.append(tag_name) | |
| 15aad84d | 69 | |
| 8bdd16b4 | 70 | clean_info = { |
| 71 | 'description': clean_html(media.get('content')), | |
| 72 | 'tags': tags, | |
| 4dc19c09 | 73 | } |
| 8bdd16b4 | 74 | |
| 75 | return merge_dicts(clean_info, jw_data, json_ld_data) |