chirbit.py (2946B)
1 # coding: utf-8 2 from __future__ import unicode_literals 3 4 import re 5 6 from .common import InfoExtractor 7 from ..compat import compat_b64decode 8 from ..utils import parse_duration 9 10 11 class ChirbitIE(InfoExtractor): 12 IE_NAME = 'chirbit' 13 _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)' 14 _TESTS = [{ 15 'url': 'http://chirb.it/be2abG', 16 'info_dict': { 17 'id': 'be2abG', 18 'ext': 'mp3', 19 'title': 'md5:f542ea253f5255240be4da375c6a5d7e', 20 'description': 'md5:f24a4e22a71763e32da5fed59e47c770', 21 'duration': 306, 22 'uploader': 'Gerryaudio', 23 }, 24 'params': { 25 'skip_download': True, 26 } 27 }, { 28 'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5', 29 'only_matching': True, 30 }, { 31 'url': 'https://chirb.it/wp/MN58c2', 32 'only_matching': True, 33 }] 34 35 def _real_extract(self, url): 36 audio_id = self._match_id(url) 37 38 webpage = self._download_webpage( 39 'http://chirb.it/%s' % audio_id, audio_id) 40 41 data_fd = self._search_regex( 42 r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1', 43 webpage, 'data fd', group='url') 44 45 # Reverse engineered from https://chirb.it/js/chirbit.player.js (look 46 # for soundURL) 47 audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8') 48 49 title = self._search_regex( 50 r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title') 51 description = self._search_regex( 52 r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>', 53 webpage, 'description', default=None) 54 duration = parse_duration(self._search_regex( 55 r'class=["\']c-length["\'][^>]*>([^<]+)', 56 webpage, 'duration', fatal=False)) 57 uploader = self._search_regex( 58 r'id=["\']chirbit-username["\'][^>]*>([^<]+)', 59 webpage, 'uploader', fatal=False) 60 61 return { 62 'id': audio_id, 63 'url': audio_url, 64 'title': title, 65 'description': description, 66 'duration': duration, 67 'uploader': uploader, 68 } 69 70 71 class ChirbitProfileIE(InfoExtractor): 72 IE_NAME = 'chirbit:profile' 73 _VALID_URL = r'https?://(?:www\.)?chirbit\.com/(?:rss/)?(?P<id>[^/]+)' 74 _TEST = { 75 'url': 'http://chirbit.com/ScarletBeauty', 76 'info_dict': { 77 'id': 'ScarletBeauty', 78 }, 79 'playlist_mincount': 3, 80 } 81 82 def _real_extract(self, url): 83 profile_id = self._match_id(url) 84 85 webpage = self._download_webpage(url, profile_id) 86 87 entries = [ 88 self.url_result(self._proto_relative_url('//chirb.it/' + video_id)) 89 for _, video_id in re.findall(r'<input[^>]+id=([\'"])copy-btn-(?P<id>[0-9a-zA-Z]+)\1', webpage)] 90 91 return self.playlist_result(entries, profile_id)