1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/rtp.py

67 lines
2.2 KiB
Python
Raw Normal View History

2014-12-12 18:22:24 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2019-05-28 03:58:12 +00:00
from ..utils import (
determine_ext,
js_to_json,
)
2014-12-12 18:22:24 +00:00
class RTPIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtp\.pt/play/p(?P<program_id>[0-9]+)/(?P<id>[^/?#]+)/?'
_TESTS = [{
2014-12-12 18:22:24 +00:00
'url': 'http://www.rtp.pt/play/p405/e174042/paixoes-cruzadas',
'md5': 'e736ce0c665e459ddb818546220b4ef8',
2014-12-12 18:22:24 +00:00
'info_dict': {
2014-12-21 14:28:40 +00:00
'id': 'e174042',
2014-12-12 18:22:24 +00:00
'ext': 'mp3',
'title': 'Paixões Cruzadas',
'description': 'As paixões musicais de António Cartaxo e António Macedo',
'thumbnail': r're:^https?://.*\.jpg',
2014-12-12 18:22:24 +00:00
},
}, {
'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas',
'only_matching': True,
}]
2014-12-12 18:22:24 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(
'twitter:title', webpage, display_name='title', fatal=True)
2019-05-28 03:58:12 +00:00
config = self._parse_json(self._search_regex(
r'(?s)RTPPlayer\(({.+?})\);', webpage,
'player config'), video_id, js_to_json)
file_url = config['file']
ext = determine_ext(file_url)
if ext == 'm3u8':
file_key = config.get('fileKey')
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=file_key)
if file_key:
formats.append({
'url': 'https://cdn-ondemand.rtp.pt' + file_key,
'preference': 1,
})
self._sort_formats(formats)
else:
formats = [{
'url': file_url,
'ext': ext,
}]
if config.get('mediaType') == 'audio':
for f in formats:
f['vcodec'] = 'none'
2014-12-12 18:22:24 +00:00
return {
'id': video_id,
'title': title,
'formats': formats,
2019-05-28 03:58:12 +00:00
'description': self._html_search_meta(['description', 'twitter:description'], webpage),
'thumbnail': config.get('poster') or self._og_search_thumbnail(webpage),
2014-12-12 18:22:24 +00:00
}