1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/lrt.py

70 lines
2 KiB
Python
Raw Normal View History

2014-09-29 23:26:16 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
determine_ext,
js_to_json,
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, # HLS download
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
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(
r"'duration':\s*'([^']+)',", webpage,
'duration', fatal=False, default=None))
formats = []
for js in re.findall(r'(?s)config:\s*(\{.*?\})', webpage):
data = json.loads(js_to_json(js))
if data['provider'] == 'rtmp':
formats.append({
'format_id': 'rtmp',
'ext': determine_ext(data['file']),
'url': data['streamer'],
'play_path': 'mp4:%s' % data['file'],
'preference': -1,
})
else:
formats.extend(
self._extract_m3u8_formats(data['file'], video_id, 'mp4'))
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'duration': duration,
}