Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/jamendo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from ..compat import compat_urlparse
   7 from .common import InfoExtractor
   8
   9
  10 class JamendoIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
  12     _TEST = {
  13         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
  14         'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
  15         'info_dict': {
  16             'id': '196219',
  17             'display_id': 'stories-from-emona-i',
  18             'ext': 'flac',
  19             'title': 'Stories from Emona I',
  20             'thumbnail': 're:^https?://.*\.jpg'
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = self._VALID_URL_RE.match(url)
  26         track_id = mobj.group('id')
  27         display_id = mobj.group('display_id')
  28
  29         webpage = self._download_webpage(url, display_id)
  30
  31         title = self._html_search_meta('name', webpage, 'title')
  32
  33         formats = [{
  34             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
  35                    % (sub_domain, track_id, format_id),
  36             'format_id': format_id,
  37             'ext': ext,
  38             'quality': quality,
  39         } for quality, (format_id, sub_domain, ext) in enumerate((
  40             ('mp31', 'mp3l', 'mp3'),
  41             ('mp32', 'mp3d', 'mp3'),
  42             ('ogg1', 'ogg', 'ogg'),
  43             ('flac', 'flac', 'flac'),
  44         ))]
  45         self._sort_formats(formats)
  46
  47         thumbnail = self._html_search_meta(
  48             'image', webpage, 'thumbnail', fatal=False)
  49
  50         return {
  51             'id': track_id,
  52             'display_id': display_id,
  53             'thumbnail': thumbnail,
  54             'title': title,
  55             'formats': formats
  56         }
  57
  58
  59 class JamendoAlbumIE(InfoExtractor):
  60     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
  61     _TEST = {
  62         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
  63         'info_dict': {
  64             'id': '121486',
  65             'title': 'Duck On Cover'
  66         },
  67         'playlist': [{
  68             'md5': 'e1a2fcb42bda30dfac990212924149a8',
  69             'info_dict': {
  70                 'id': '1032333',
  71                 'ext': 'flac',
  72                 'title': 'Warmachine'
  73             }
  74         }, {
  75             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
  76             'info_dict': {
  77                 'id': '1032330',
  78                 'ext': 'flac',
  79                 'title': 'Without Your Ghost'
  80             }
  81         }],
  82         'params': {
  83             'playlistend': 2
  84         }
  85     }
  86
  87     def _real_extract(self, url):
  88         mobj = self._VALID_URL_RE.match(url)
  89         album_id = mobj.group('id')
  90
  91         webpage = self._download_webpage(url, mobj.group('display_id'))
  92
  93         title = self._html_search_meta('name', webpage, 'title')
  94
  95         entries = [
  96             self.url_result(
  97                 compat_urlparse.urljoin(url, m.group('path')),
  98                 ie=JamendoIE.ie_key(),
  99                 video_id=self._search_regex(
 100                     r'/track/(\d+)', m.group('path'),
 101                     'track id', default=None))
 102             for m in re.finditer(
 103                 r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
 104                 webpage)
 105         ]
 106
 107         return self.playlist_result(entries, album_id, title)