1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-11-23 06:42:53 +08:00
youtube-dl/youtube_dl/extractor/lrt.py

65 lines
2.2 KiB
Python
Raw Normal View History

2014-09-30 07:26:16 +08:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
2015-12-27 14:26:48 +08:00
int_or_none,
2014-09-30 07:26:16 +08:00
parse_duration,
remove_end,
)
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/',
'info_dict': {
'id': '54391',
'ext': 'mp4',
'title': 'Septynios Kauno dienos',
2014-10-25 18:24:46 +08:00
'description': 'md5:24d84534c7dc76581e59f5689462411a',
2014-09-30 07:26:16 +08:00
'duration': 1783,
2015-12-27 14:26:48 +08:00
'view_count': int,
'like_count': int,
2014-09-30 07:26:16 +08:00
},
'params': {
'skip_download': True, # m3u8 download
2014-09-30 07:26:16 +08:00
},
}
def _real_extract(self, url):
2014-10-27 09:27:49 +08:00
video_id = self._match_id(url)
2014-09-30 07:26:16 +08:00
webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' - LRT')
2015-12-27 14:16:55 +08:00
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)
2015-12-27 14:16:55 +08:00
2014-09-30 07:26:16 +08:00
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
duration = parse_duration(self._search_regex(
2015-12-27 14:16:55 +08:00
r'var\s+record_len\s*=\s*(["\'])(?P<duration>[0-9]+:[0-9]+:[0-9]+)\1',
webpage, 'duration', default=None, group='duration'))
2014-09-30 07:26:16 +08:00
2015-12-27 14:26:48 +08:00
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'))
2014-09-30 07:26:16 +08:00
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'duration': duration,
2015-12-27 14:26:48 +08:00
'view_count': view_count,
'like_count': like_count,
2014-09-30 07:26:16 +08:00
}