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 from ..utils import parse_duration
   9
  10
  11 class JamendoBaseIE(InfoExtractor):
  12     def _extract_meta(self, webpage, fatal=True):
  13         title = self._og_search_title(
  14             webpage, default=None) or self._search_regex(
  15             r'<title>([^<]+)', webpage,
  16             'title', default=None)
  17         if title:
  18             title = self._search_regex(
  19                 r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
  20         if not title:
  21             title = self._html_search_meta(
  22                 'name', webpage, 'title', fatal=fatal)
  23         mobj = re.search(r'(.+) - (.+)', title or '')
  24         artist, second = mobj.groups() if mobj else [None] * 2
  25         return title, artist, second
  26
  27
  28 class JamendoIE(JamendoBaseIE):
  29     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)'
  30     _TEST = {
  31         'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
  32         'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
  33         'info_dict': {
  34             'id': '196219',
  35             'display_id': 'stories-from-emona-i',
  36             'ext': 'flac',
  37             'title': 'Maya Filipič - Stories from Emona I',
  38             'artist': 'Maya Filipič',
  39             'track': 'Stories from Emona I',
  40             'duration': 210,
  41             'thumbnail': r're:^https?://.*\.jpg'
  42         }
  43     }
  44
  45     def _real_extract(self, url):
  46         mobj = self._VALID_URL_RE.match(url)
  47         track_id = mobj.group('id')
  48         display_id = mobj.group('display_id')
  49
  50         webpage = self._download_webpage(url, display_id)
  51
  52         title, artist, track = self._extract_meta(webpage)
  53
  54         formats = [{
  55             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
  56                    % (sub_domain, track_id, format_id),
  57             'format_id': format_id,
  58             'ext': ext,
  59             'quality': quality,
  60         } for quality, (format_id, sub_domain, ext) in enumerate((
  61             ('mp31', 'mp3l', 'mp3'),
  62             ('mp32', 'mp3d', 'mp3'),
  63             ('ogg1', 'ogg', 'ogg'),
  64             ('flac', 'flac', 'flac'),
  65         ))]
  66         self._sort_formats(formats)
  67
  68         thumbnail = self._html_search_meta(
  69             'image', webpage, 'thumbnail', fatal=False)
  70         duration = parse_duration(self._search_regex(
  71             r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
  72             webpage, 'duration', fatal=False))
  73
  74         return {
  75             'id': track_id,
  76             'display_id': display_id,
  77             'thumbnail': thumbnail,
  78             'title': title,
  79             'duration': duration,
  80             'artist': artist,
  81             'track': track,
  82             'formats': formats
  83         }
  84
  85
  86 class JamendoAlbumIE(JamendoBaseIE):
  87     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
  88     _TEST = {
  89         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
  90         'info_dict': {
  91             'id': '121486',
  92             'title': 'Shearer - Duck On Cover'
  93         },
  94         'playlist': [{
  95             'md5': 'e1a2fcb42bda30dfac990212924149a8',
  96             'info_dict': {
  97                 'id': '1032333',
  98                 'ext': 'flac',
  99                 'title': 'Shearer - Warmachine',
 100                 'artist': 'Shearer',
 101                 'track': 'Warmachine',
 102             }
 103         }, {
 104             'md5': '1f358d7b2f98edfe90fd55dac0799d50',
 105             'info_dict': {
 106                 'id': '1032330',
 107                 'ext': 'flac',
 108                 'title': 'Shearer - Without Your Ghost',
 109                 'artist': 'Shearer',
 110                 'track': 'Without Your Ghost',
 111             }
 112         }],
 113         'params': {
 114             'playlistend': 2
 115         }
 116     }
 117
 118     def _real_extract(self, url):
 119         mobj = self._VALID_URL_RE.match(url)
 120         album_id = mobj.group('id')
 121
 122         webpage = self._download_webpage(url, mobj.group('display_id'))
 123
 124         title, artist, album = self._extract_meta(webpage, fatal=False)
 125
 126         entries = [{
 127             '_type': 'url_transparent',
 128             'url': compat_urlparse.urljoin(url, m.group('path')),
 129             'ie_key': JamendoIE.ie_key(),
 130             'id': self._search_regex(
 131                 r'/track/(\d+)', m.group('path'), 'track id', default=None),
 132             'artist': artist,
 133             'album': album,
 134         } for m in re.finditer(
 135             r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
 136             webpage)]
 137
 138         return self.playlist_result(entries, album_id, title)