youtube-dl/youtube_dl/extractor/lrt.py

49 lines
1.5 KiB
Python
Raw Normal View History

2014-09-29 23:26:16 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
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 10:24:46 +00:00
'description': 'md5:24d84534c7dc76581e59f5689462411a',
2014-09-29 23:26:16 +00:00
'duration': 1783,
},
'params': {
'skip_download': True, # m3u8 download
2014-09-29 23:26:16 +00:00
},
}
def _real_extract(self, url):
2014-10-27 01:27:49 +00:00
video_id = self._match_id(url)
2014-09-29 23:26:16 +00:00
webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' - LRT')
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
duration = parse_duration(self._search_regex(
2015-11-28 21:14:38 +00:00
r"var record_len = '([0-9]+:[0-9]+:[0-9]+)';", webpage, 'record_len', fatal=False, default=None))
2014-09-29 23:26:16 +00:00
link = self._search_regex(r'file: "(.*)" \+ location\.hash\.substring\(1\)', webpage, 'link to m3u8')
formats = self._extract_m3u8_formats(link, video_id, "mp4")
2014-09-29 23:26:16 +00:00
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'duration': duration,
}