youtube_dl/extractor/soundgasm.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class SoundgasmIE(InfoExtractor):
  10     IE_NAME = 'soundgasm'
  11     _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<user>[0-9a-zA-Z_\-]+)/(?P<title>[0-9a-zA-Z_\-]+)'
  12     _TEST = {
  13         'url': 'http://soundgasm.net/u/ytdl/Piano-sample',
  14         'md5': '010082a2c802c5275bb00030743e75ad',
  15         'info_dict': {
  16             'id': '88abd86ea000cafe98f96321b23cc1206cbcbcc9',
  17             'ext': 'm4a',
  18             'title': 'ytdl_Piano-sample',
  19             'description': 'Royalty Free Sample Music'
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         display_id = mobj.group('title')
  26         audio_title = mobj.group('user') + '_' + mobj.group('title')
  27         webpage = self._download_webpage(url, display_id)
  28         audio_url = self._html_search_regex(
  29             r'(?s)m4a\:\s"([^"]+)"', webpage, 'audio URL')
  30         audio_id = re.split(r'\/|\.', audio_url)[-2]
  31         description = self._html_search_regex(
  32             r'(?s)<li>Description:\s(.*?)<\/li>', webpage, 'description',
  33             fatal=False)
  34
  35         return {
  36             'id': audio_id,
  37             'display_id': display_id,
  38             'url': audio_url,
  39             'title': audio_title,
  40             'description': description
  41         }
  42
  43
  44 class SoundgasmProfileIE(InfoExtractor):
  45     IE_NAME = 'soundgasm:profile'
  46     _VALID_URL = r'https?://(?:www\.)?soundgasm\.net/u/(?P<id>[^/]+)/?(?:\#.*)?$'
  47     _TEST = {
  48         'url': 'http://soundgasm.net/u/ytdl',
  49         'info_dict': {
  50             'id': 'ytdl',
  51         },
  52         'playlist_count': 1,
  53     }
  54
  55     def _real_extract(self, url):
  56         profile_id = self._match_id(url)
  57
  58         webpage = self._download_webpage(url, profile_id)
  59
  60         entries = [
  61             self.url_result(audio_url, 'Soundgasm')
  62             for audio_url in re.findall(r'href="([^"]+/u/%s/[^"]+)' % profile_id, webpage)]
  63
  64         return self.playlist_result(entries, profile_id)