yt-dlp/yt_dlp/extractor/xminus.py

80 lines
2.9 KiB
Python
Raw Normal View History

2014-11-25 04:25:28 +01:00
# coding: utf-8
from __future__ import unicode_literals
2014-12-04 17:43:34 +01:00
import re
2016-04-24 17:18:34 +02:00
import time
2014-12-04 17:43:34 +01:00
2014-11-25 04:25:28 +01:00
from .common import InfoExtractor
2014-11-25 09:54:54 +01:00
from ..compat import (
compat_ord,
)
from ..utils import (
int_or_none,
2016-04-24 17:18:34 +02:00
parse_duration,
2014-11-25 09:54:54 +01:00
)
2014-11-25 04:25:28 +01:00
class XMinusIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html',
'md5': '401a15f2d2dcf6d592cb95528d72a2a8',
'info_dict': {
'id': '4542',
'ext': 'mp3',
2016-04-24 17:18:34 +02:00
'title': 'Леонид Агутин-Песенка шофёра',
2014-11-25 04:25:28 +01:00
'duration': 156,
2014-11-25 09:54:54 +01:00
'tbr': 320,
'filesize_approx': 5900000,
'view_count': int,
2014-12-04 17:43:34 +01:00
'description': 'md5:03238c5b663810bc79cf42ef3c03e371',
2014-11-25 04:25:28 +01:00
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2014-11-25 09:54:54 +01:00
2014-11-25 04:25:28 +01:00
artist = self._html_search_regex(
2016-04-24 17:18:34 +02:00
r'<a[^>]+href="/artist/\d+">([^<]+)</a>', webpage, 'artist')
2014-11-25 04:25:28 +01:00
title = artist + '-' + self._html_search_regex(
2016-04-24 17:18:34 +02:00
r'<span[^>]+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title')
duration = parse_duration(self._html_search_regex(
r'<span[^>]+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)',
2014-11-25 09:54:54 +01:00
webpage, 'duration', fatal=False))
2016-04-24 17:18:34 +02:00
mobj = re.search(
r'<div[^>]+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P<tbr>\d+)\s*кбит/c\s+(?P<filesize>[0-9.]+)\s*мб</div>',
webpage)
tbr = filesize_approx = None
if mobj:
filesize_approx = float(mobj.group('filesize')) * 1000000
tbr = float(mobj.group('tbr'))
2014-11-25 09:54:54 +01:00
view_count = int_or_none(self._html_search_regex(
2016-04-24 17:18:34 +02:00
r'<span><[^>]+class="icon-chart-bar".*?>(\d+)</span>',
2014-11-25 09:54:54 +01:00
webpage, 'view count', fatal=False))
2014-12-04 17:43:34 +01:00
description = self._html_search_regex(
2016-04-24 17:18:34 +02:00
r'(?s)<pre[^>]+id="lyrics-original"[^>]*>(.*?)</pre>',
2014-12-04 17:43:34 +01:00
webpage, 'song lyrics', fatal=False)
if description:
description = re.sub(' *\r *', '\n', description)
2014-11-25 09:54:54 +01:00
2016-04-24 17:18:34 +02:00
k = self._search_regex(
r'<div[^>]+id="player-bottom"[^>]+data-k="([^"]+)">', webpage,
'encoded data')
h = time.time() / 3600
a = sum(map(int, [compat_ord(c) for c in k])) + int(video_id) + h
video_url = 'http://x-minus.me/dl/minus?id=%s&tkn2=%df%d' % (video_id, a, h)
2014-11-25 04:25:28 +01:00
return {
'id': video_id,
'title': title,
2014-11-25 09:54:54 +01:00
'url': video_url,
2016-04-24 17:18:34 +02:00
# The extension is unknown until actual downloading
'ext': 'mp3',
2014-11-25 04:25:28 +01:00
'duration': duration,
2014-11-25 09:54:54 +01:00
'filesize_approx': filesize_approx,
'tbr': tbr,
'view_count': view_count,
2014-12-04 17:43:34 +01:00
'description': description,
2014-11-25 04:25:28 +01:00
}