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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9     clean_html,
  10     compat_urllib_request,
  11     float_or_none,
  12     parse_iso8601,
  13 )
  14
  15
  16 class TapelyIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?tape\.ly/(?P<id>[A-Za-z0-9\-_]+)(?:/(?P<songnr>\d+))?'
  18     _API_URL = 'http://tape.ly/showtape?id={0:}'
  19     _S3_SONG_URL = 'http://mytape.s3.amazonaws.com/{0:}'
  20     _TESTS = [
  21         {
  22             'url': 'http://tape.ly/my-grief-as-told-by-water',
  23             'info_dict': {
  24                 'id': 23952,
  25                 'title': 'my grief as told by water',
  26                 'thumbnail': 're:^https?://.*\.png$',
  27                 'uploader_id': 16484,
  28                 'timestamp': 1411848286,
  29                 'description': 'For Robin and Ponkers, whom the tides of life have taken out to sea.',
  30             },
  31             'playlist_count': 13,
  32         },
  33         {
  34             'url': 'http://tape.ly/my-grief-as-told-by-water/1',
  35             'md5': '79031f459fdec6530663b854cbc5715c',
  36             'info_dict': {
  37                 'id': 258464,
  38                 'title': 'Dreaming Awake  (My Brightest Diamond)',
  39                 'ext': 'm4a',
  40             },
  41         },
  42     ]
  43
  44     def _real_extract(self, url):
  45         mobj = re.match(self._VALID_URL, url)
  46         display_id = mobj.group('id')
  47
  48         playlist_url = self._API_URL.format(display_id)
  49         request = compat_urllib_request.Request(playlist_url)
  50         request.add_header('X-Requested-With', 'XMLHttpRequest')
  51         request.add_header('Accept', 'application/json')
  52
  53         playlist = self._download_json(request, display_id)
  54
  55         tape = playlist['tape']
  56
  57         entries = []
  58         for s in tape['songs']:
  59             song = s['song']
  60             entry = {
  61                 'id': song['id'],
  62                 'duration': float_or_none(song.get('songduration'), 1000),
  63                 'title': song['title'],
  64             }
  65             if song['source'] == 'S3':
  66                 entry.update({
  67                     'url': self._S3_SONG_URL.format(song['filename']),
  68                 })
  69                 entries.append(entry)
  70             elif song['source'] == 'YT':
  71                 _, _, yt_id = song['filename'].split('/')
  72                 entry.update(self.url_result(yt_id, 'Youtube', video_id=yt_id))
  73                 entries.append(entry)
  74             else:
  75                 self.report_warning('Unknown song source: %s' % song['source'])
  76
  77         if mobj.group('songnr'):
  78             songnr = int(mobj.group('songnr')) - 1
  79             try:
  80                 return entries[songnr]
  81             except IndexError:
  82                 raise ExtractorError(
  83                     'No song with index: %s' % mobj.group('songnr'),
  84                     expected=True)
  85
  86         return {
  87             '_type': 'playlist',
  88             'id': tape['id'],
  89             'display_id': display_id,
  90             'title': tape['name'],
  91             'entries': entries,
  92             'thumbnail': tape.get('image_url'),
  93             'description': clean_html(tape.get('subtext')),
  94             'like_count': tape.get('likescount'),
  95             'uploader_id': tape.get('user_id'),
  96             'timestamp': parse_iso8601(tape.get('published_at')),
  97         }