diff options
Diffstat (limited to 'youtube_dl/extractor/lrt.py')
| -rw-r--r-- | youtube_dl/extractor/lrt.py | 93 |
1 files changed, 52 insertions, 41 deletions
diff --git a/youtube_dl/extractor/lrt.py b/youtube_dl/extractor/lrt.py index 1072405b3..89d549858 100644 --- a/youtube_dl/extractor/lrt.py +++ b/youtube_dl/extractor/lrt.py @@ -1,64 +1,75 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( - int_or_none, - parse_duration, - remove_end, + clean_html, + merge_dicts, ) class LRTIE(InfoExtractor): IE_NAME = 'lrt.lt' - _VALID_URL = r'https?://(?:www\.)?lrt\.lt/mediateka/irasas/(?P<id>[0-9]+)' - _TEST = { - 'url': 'http://www.lrt.lt/mediateka/irasas/54391/', + _VALID_URL = r'https?://(?:www\.)?lrt\.lt(?P<path>/mediateka/irasas/(?P<id>[0-9]+))' + _TESTS = [{ + # m3u8 download + 'url': 'https://www.lrt.lt/mediateka/irasas/2000127261/greita-ir-gardu-sicilijos-ikvepta-klasikiniu-makaronu-su-baklazanais-vakariene', + 'md5': '85cb2bb530f31d91a9c65b479516ade4', 'info_dict': { - 'id': '54391', + 'id': '2000127261', 'ext': 'mp4', - 'title': 'Septynios Kauno dienos', - 'description': 'md5:24d84534c7dc76581e59f5689462411a', - 'duration': 1783, + 'title': 'Greita ir gardu: Sicilijos įkvėpta klasikinių makaronų su baklažanais vakarienė', + 'description': 'md5:ad7d985f51b0dc1489ba2d76d7ed47fa', + 'duration': 3035, + 'timestamp': 1604079000, + 'upload_date': '20201030', + }, + }, { + # direct mp3 download + 'url': 'http://www.lrt.lt/mediateka/irasas/1013074524/', + 'md5': '389da8ca3cad0f51d12bed0c844f6a0a', + 'info_dict': { + 'id': '1013074524', + 'ext': 'mp3', + 'title': 'Kita tema 2016-09-05 15:05', + 'description': 'md5:1b295a8fc7219ed0d543fc228c931fb5', + 'duration': 3008, 'view_count': int, 'like_count': int, }, - 'params': { - 'skip_download': True, # m3u8 download - }, - } + }] + + def _extract_js_var(self, webpage, var_name, default): + return self._search_regex( + r'%s\s*=\s*(["\'])((?:(?!\1).)+)\1' % var_name, + webpage, var_name.replace('_', ' '), default, group=2) def _real_extract(self, url): - video_id = self._match_id(url) + path, video_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, video_id) - title = remove_end(self._og_search_title(webpage), ' - LRT') - m3u8_url = self._search_regex( - r'file\s*:\s*(["\'])(?P<url>.+?)\1\s*\+\s*location\.hash\.substring\(1\)', - webpage, 'm3u8 url', group='url') - formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') - self._sort_formats(formats) + media_url = self._extract_js_var(webpage, 'main_url', path) + media = self._download_json(self._extract_js_var( + webpage, 'media_info_url', + 'https://www.lrt.lt/servisai/stream_url/vod/media_info/'), + video_id, query={'url': media_url}) + jw_data = self._parse_jwplayer_data( + media['playlist_item'], video_id, base_url=url) - thumbnail = self._og_search_thumbnail(webpage) - description = self._og_search_description(webpage) - duration = parse_duration(self._search_regex( - r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1', - webpage, 'duration', default=None, group='duration')) + json_ld_data = self._search_json_ld(webpage, video_id) - view_count = int_or_none(self._html_search_regex( - r'<div[^>]+class=(["\']).*?record-desc-seen.*?\1[^>]*>(?P<count>.+?)</div>', - webpage, 'view count', fatal=False, group='count')) - like_count = int_or_none(self._search_regex( - r'<span[^>]+id=(["\'])flikesCount.*?\1>(?P<count>\d+)<', - webpage, 'like count', fatal=False, group='count')) + tags = [] + for tag in (media.get('tags') or []): + tag_name = tag.get('name') + if not tag_name: + continue + tags.append(tag_name) - return { - 'id': video_id, - 'title': title, - 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, - 'duration': duration, - 'view_count': view_count, - 'like_count': like_count, + clean_info = { + 'description': clean_html(media.get('content')), + 'tags': tags, } + + return merge_dicts(clean_info, jw_data, json_ld_data) |