1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-01-24 00:45:38 +08:00

video archives + reuse jwplayer parsing of yt-dl

This commit is contained in:
Robert Trebula 2018-01-04 22:29:27 +01:00
parent 2b17340fb9
commit 0b0d2bb8e8

View File

@ -5,31 +5,34 @@ from .common import InfoExtractor
class RtvsExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rtvs\.sk/.*/archiv/[0-9]*/(?P<id>[0-9]+)'
_TEST = {
_TESTS = [{
# radio archive
'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
'info_dict': {
'id': '414872',
'ext': 'mp3',
'title': u'Ostrov pokladov 1 časť',
'title': u'Ostrov pokladov 1 časť.mp3',
}
}, {
# tv archive
'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
'md5': '85e2c55cf988403b70cac24f5c086dc6',
'info_dict': {
'id': '63118',
'ext': 'mp4',
'title': u'Amaro Džives - Náš deň',
'description': u'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist_url = self._search_regex(r'"playlist": "(https?:.*)&', webpage, 'playlist_url')
self.to_screen("Playlist URL: " + playlist_url)
self.to_screen("%s: Playlist URL: %s" % (video_id, playlist_url))
playlist = self._download_json(playlist_url, video_id, "Downloading playlist")
playlist_item = playlist[0]
url = playlist_item["sources"][0]["file"]
full_title = playlist_item.get("title")
(title, ext) = full_title.split(".", 2)
jwplayer_data = playlist[0]
return self._parse_jwplayer_data(jwplayer_data, video_id=video_id)
return {
'id': video_id,
'url': url,
'title': title,
'ext': ext
}