_ Git - youtube-dl/blob - youtube_dl/extractor/chirbit.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     parse_duration,
   7     int_or_none,
   8 )
   9
  10
  11 class ChirbitIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
  13     _TESTS = [{
  14         'url': 'http://chirb.it/PrIPv5',
  15         'md5': '9847b0dad6ac3e074568bf2cfb197de8',
  16         'info_dict': {
  17             'id': 'PrIPv5',
  18             'ext': 'mp3',
  19             'title': 'Фасадстрой',
  20             'duration': 52,
  21             'view_count': int,
  22             'comment_count': int,
  23         }
  24     }, {
  25         'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         audio_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(
  33             'http://chirb.it/%s' % audio_id, audio_id)
  34
  35         audio_url = self._search_regex(
  36             r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
  37
  38         title = self._search_regex(
  39             r'itemprop="name">([^<]+)', webpage, 'title')
  40         duration = parse_duration(self._html_search_meta(
  41             'duration', webpage, 'duration', fatal=False))
  42         view_count = int_or_none(self._search_regex(
  43             r'itemprop="playCount"\s*>(\d+)', webpage,
  44             'listen count', fatal=False))
  45         comment_count = int_or_none(self._search_regex(
  46             r'>(\d+) Comments?:', webpage,
  47             'comment count', fatal=False))
  48
  49         return {
  50             'id': audio_id,
  51             'url': audio_url,
  52             'title': title,
  53             'duration': duration,
  54             'view_count': view_count,
  55             'comment_count': comment_count,
  56         }
  57
  58
  59 class ChirbitProfileIE(InfoExtractor):
  60     _VALID_URL = r'https?://(?:www\.)?chirbit.com/(?:rss/)?(?P<id>[^/]+)'
  61     _TEST = {
  62         'url': 'http://chirbit.com/ScarletBeauty',
  63         'info_dict': {
  64             'id': 'ScarletBeauty',
  65             'title': 'Chirbits by ScarletBeauty',
  66         },
  67         'playlist_mincount': 3,
  68     }
  69
  70     def _real_extract(self, url):
  71         profile_id = self._match_id(url)
  72
  73         rss = self._download_xml(
  74             'http://chirbit.com/rss/%s' % profile_id, profile_id)
  75
  76         entries = [
  77             self.url_result(audio_url.text, 'Chirbit')
  78             for audio_url in rss.findall('./channel/item/link')]
  79
  80         title = rss.find('./channel/title').text
  81
  82         return self.playlist_result(entries, profile_id, title)