[chirbit] Fix extraction (Closes #10296)

pull/9409/merge
Sergey M․ 2016-08-11 23:37:56 +07:00
parent 30b25d382d
commit 0c070681c5
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 30 additions and 24 deletions

View File

@ -1,30 +1,33 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
)
from ..utils import parse_duration
class ChirbitIE(InfoExtractor):
IE_NAME = 'chirbit'
_VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://chirb.it/PrIPv5',
'md5': '9847b0dad6ac3e074568bf2cfb197de8',
'url': 'http://chirb.it/be2abG',
'info_dict': {
'id': 'PrIPv5',
'id': 'be2abG',
'ext': 'mp3',
'title': 'Фасадстрой',
'duration': 52,
'view_count': int,
'comment_count': int,
'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
'duration': 306,
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
'only_matching': True,
}, {
'url': 'https://chirb.it/wp/MN58c2',
'only_matching': True,
}]
def _real_extract(self, url):
@ -33,27 +36,30 @@ class ChirbitIE(InfoExtractor):
webpage = self._download_webpage(
'http://chirb.it/%s' % audio_id, audio_id)
audio_url = self._search_regex(
r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
data_fd = self._search_regex(
r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'data fd', group='url')
# Reverse engineered from https://chirb.it/js/chirbit.player.js (look
# for soundURL)
audio_url = base64.b64decode(
data_fd[::-1].encode('ascii')).decode('utf-8')
title = self._search_regex(
r'itemprop="name">([^<]+)', webpage, 'title')
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'itemprop="playCount"\s*>(\d+)', webpage,
'listen count', fatal=False))
comment_count = int_or_none(self._search_regex(
r'>(\d+) Comments?:', webpage,
'comment count', fatal=False))
r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
description = self._search_regex(
r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
webpage, 'description', default=None)
duration = parse_duration(self._search_regex(
r'class=["\']c-length["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
return {
'id': audio_id,
'url': audio_url,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
}