X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxminus.py;h=36e5ead1e690db9bb0c1c1a64650a69c784bbe76;hb=HEAD;hp=c92c8451a2716e0e31057959fe2f82bb61e6044e;hpb=0bbf12239c5a97ddcaa9d54012cbcb2448223072;p=youtube-dl diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py index c92c8451a..36e5ead1e 100644 --- a/youtube_dl/extractor/xminus.py +++ b/youtube_dl/extractor/xminus.py @@ -1,8 +1,17 @@ # coding: utf-8 from __future__ import unicode_literals +import re +import time + from .common import InfoExtractor -from ..utils import int_or_none +from ..compat import ( + compat_ord, +) +from ..utils import ( + int_or_none, + parse_duration, +) class XMinusIE(InfoExtractor): @@ -13,41 +22,58 @@ class XMinusIE(InfoExtractor): 'info_dict': { 'id': '4542', 'ext': 'mp3', - 'title': 'Леонид Агутин-Песенка шофера', + 'title': 'Леонид Агутин-Песенка шофёра', 'duration': 156, + 'tbr': 320, + 'filesize_approx': 5900000, + 'view_count': int, + 'description': 'md5:03238c5b663810bc79cf42ef3c03e371', } } def _real_extract(self, url): video_id = self._match_id(url) - - # TODO more code goes here, for example ... webpage = self._download_webpage(url, video_id) + artist = self._html_search_regex( - r'minus_track.artist="(.+?)"', webpage, 'artist') + r']+href="/artist/\d+">([^<]+)', webpage, 'artist') title = artist + '-' + self._html_search_regex( - r'minus_track.title="(.+?)"', webpage, 'title') - duration = int_or_none(self._html_search_regex( - r'minus_track.dur_sec=\'([0-9]+?)\'', webpage, 'duration')) - enc_token = self._html_search_regex( - r'data-mt="(.*?)"', webpage, 'enc_token') - token = self._decode_token(enc_token) - url = 'http://x-minus.org/dwlf/{}/{}.mp3'.format(video_id, token) + r']+class="minustrack-full-title(?:\s+[^"]+)?"[^>]*>([^<]+)', webpage, 'title') + duration = parse_duration(self._html_search_regex( + r']+class="player-duration(?:\s+[^"]+)?"[^>]*>([^<]+)', + webpage, 'duration', fatal=False)) + mobj = re.search( + r']+class="dw-info(?:\s+[^"]+)?"[^>]*>(?P\d+)\s*кбит/c\s+(?P[0-9.]+)\s*мб', + webpage) + tbr = filesize_approx = None + if mobj: + filesize_approx = float(mobj.group('filesize')) * 1000000 + tbr = float(mobj.group('tbr')) + view_count = int_or_none(self._html_search_regex( + r'<[^>]+class="icon-chart-bar".*?>(\d+)', + webpage, 'view count', fatal=False)) + description = self._html_search_regex( + r'(?s)]+id="lyrics-original"[^>]*>(.*?)', + webpage, 'song lyrics', fatal=False) + if description: + description = re.sub(' *\r *', '\n', description) + + k = self._search_regex( + r']+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) return { 'id': video_id, 'title': title, - 'url': url, + 'url': video_url, + # The extension is unknown until actual downloading + 'ext': 'mp3', 'duration': duration, + 'filesize_approx': filesize_approx, + 'tbr': tbr, + 'view_count': view_count, + 'description': description, } - - def _decode_token(self, enc_token): - token = '' - pos = 0 - for c in reversed(enc_token): - if pos != 3: - token += chr(ord(c) - 1) - else: - token += c - pos += 1 - return token