github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[xminus] Fix extraction (closes #9228)

Browse source
This commit is contained in:
Yen Chi Hsuan 2016-04-24 23:18:34 +08:00
parent 8b38f2ac40
commit 51762e1a31
No known key found for this signature in database
GPG key ID: 3FDDD575826C5C30
1 changed files with 24 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

45
youtube_dl/extractor/xminus.py
View file

@ -2,15 +2,15 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import time
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_chr,
compat_ord, compat_ord,
) )
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
parse_filesize, parse_duration,
) )
@ -22,7 +22,7 @@ class XMinusIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '4542', 'id': '4542',
'ext': 'mp3', 'ext': 'mp3',
'title': 'Леонид Агутин-Песенка шофера', 'title': 'Леонид Агутин-Песенка шофёра',
'duration': 156, 'duration': 156,
'tbr': 320, 'tbr': 320,
'filesize_approx': 5900000, 'filesize_approx': 5900000,
@ -36,38 +36,41 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
artist = self._html_search_regex( artist = self._html_search_regex(
r'minus_track\.artist="(.+?)"', webpage, 'artist') r'<a[^>]+href="/artist/\d+">([^<]+)</a>', webpage, 'artist')
title = artist + '-' + self._html_search_regex( title = artist + '-' + self._html_search_regex(
r'minus_track\.title="(.+?)"', webpage, 'title') r'<span[^>]+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title')
duration = int_or_none(self._html_search_regex( duration = parse_duration(self._html_search_regex(
r'minus_track\.dur_sec=\'([0-9]*?)\'', r'<span[^>]+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)',
webpage, 'duration', fatal=False)) webpage, 'duration', fatal=False))
filesize_approx = parse_filesize(self._html_search_regex( mobj = re.search(
r'<div id="finfo"[^>]*>\s*↓\s*([0-9.]+\s*[a-zA-Z][bB])', r'<div[^>]+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P<tbr>\d+)\s*кбит/c\s+(?P<filesize>[0-9.]+)\s*мб</div>',
webpage, 'approximate filesize', fatal=False)) webpage)
tbr = int_or_none(self._html_search_regex( tbr = filesize_approx = None
r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps', if mobj:
webpage, 'bitrate', fatal=False)) filesize_approx = float(mobj.group('filesize')) * 1000000
tbr = float(mobj.group('tbr'))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<div class="quality.*?► ([0-9]+)', r'<span><[^>]+class="icon-chart-bar".*?>(\d+)</span>',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
description = self._html_search_regex( description = self._html_search_regex(
r'(?s)<div id="song_texts">(.*?)</div><br', r'(?s)<pre[^>]+id="lyrics-original"[^>]*>(.*?)</pre>',
webpage, 'song lyrics', fatal=False) webpage, 'song lyrics', fatal=False)
if description: if description:
description = re.sub(' *\r *', '\n', description) description = re.sub(' *\r *', '\n', description)
enc_token = self._html_search_regex( k = self._search_regex(
r'minus_track\.s?tkn="(.+?)"', webpage, 'enc_token') r'<div[^>]+id="player-bottom"[^>]+data-k="([^"]+)">', webpage,
token = ''.join( 'encoded data')
c if pos == 3 else compat_chr(compat_ord(c) - 1) h = time.time() / 3600
for pos, c in enumerate(reversed(enc_token))) a = sum(map(int, [compat_ord(c) for c in k])) + int(video_id) + h
video_url = 'http://x-minus.org/dwlf/%s/%s.mp3' % (video_id, token) video_url = 'http://x-minus.me/dl/minus?id=%s&tkn2=%df%d' % (video_id, a, h)
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
# The extension is unknown until actual downloading
'ext': 'mp3',
'duration': duration, 'duration': duration,
'filesize_approx': filesize_approx, 'filesize_approx': filesize_approx,
'tbr': tbr, 'tbr': tbr,