_ 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     clean_html,
   9     ExtractorError,
  10     float_or_none,
  11     parse_iso8601,
  12     sanitized_Request,
  13 )
  14
  15
  16 class TapelyIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?(?:tape\.ly|tapely\.com)/(?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     _SOUNDCLOUD_SONG_URL = 'http://api.soundcloud.com{0:}'
  21     _TESTS = [
  22         {
  23             'url': 'http://tape.ly/my-grief-as-told-by-water',
  24             'info_dict': {
  25                 'id': 23952,
  26                 'title': 'my grief as told by water',
  27                 'thumbnail': 're:^https?://.*\.png$',
  28                 'uploader_id': 16484,
  29                 'timestamp': 1411848286,
  30                 'description': 'For Robin and Ponkers, whom the tides of life have taken out to sea.',
  31             },
  32             'playlist_count': 13,
  33         },
  34         {
  35             'url': 'http://tape.ly/my-grief-as-told-by-water/1',
  36             'md5': '79031f459fdec6530663b854cbc5715c',
  37             'info_dict': {
  38                 'id': 258464,
  39                 'title': 'Dreaming Awake  (My Brightest Diamond)',
  40                 'ext': 'm4a',
  41             },
  42         },
  43         {
  44             'url': 'https://tapely.com/my-grief-as-told-by-water',
  45             'only_matching': True,
  46         },
  47     ]
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         display_id = mobj.group('id')
  52
  53         playlist_url = self._API_URL.format(display_id)
  54         request = sanitized_Request(playlist_url)
  55         request.add_header('X-Requested-With', 'XMLHttpRequest')
  56         request.add_header('Accept', 'application/json')
  57         request.add_header('Referer', url)
  58
  59         playlist = self._download_json(request, display_id)
  60
  61         tape = playlist['tape']
  62
  63         entries = []
  64         for s in tape['songs']:
  65             song = s['song']
  66             entry = {
  67                 'id': song['id'],
  68                 'duration': float_or_none(song.get('songduration'), 1000),
  69                 'title': song['title'],
  70             }
  71             if song['source'] == 'S3':
  72                 entry.update({
  73                     'url': self._S3_SONG_URL.format(song['filename']),
  74                 })
  75                 entries.append(entry)
  76             elif song['source'] == 'YT':
  77                 self.to_screen('YouTube video detected')
  78                 yt_id = song['filename'].replace('/youtube/', '')
  79                 entry.update(self.url_result(yt_id, 'Youtube', video_id=yt_id))
  80                 entries.append(entry)
  81             elif song['source'] == 'SC':
  82                 self.to_screen('SoundCloud song detected')
  83                 sc_url = self._SOUNDCLOUD_SONG_URL.format(song['filename'])
  84                 entry.update(self.url_result(sc_url, 'Soundcloud'))
  85                 entries.append(entry)
  86             else:
  87                 self.report_warning('Unknown song source: %s' % song['source'])
  88
  89         if mobj.group('songnr'):
  90             songnr = int(mobj.group('songnr')) - 1
  91             try:
  92                 return entries[songnr]
  93             except IndexError:
  94                 raise ExtractorError(
  95                     'No song with index: %s' % mobj.group('songnr'),
  96                     expected=True)
  97
  98         return {
  99             '_type': 'playlist',
 100             'id': tape['id'],
 101             'display_id': display_id,
 102             'title': tape['name'],
 103             'entries': entries,
 104             'thumbnail': tape.get('image_url'),
 105             'description': clean_html(tape.get('subtext')),
 106             'like_count': tape.get('likescount'),
 107             'uploader_id': tape.get('user_id'),
 108             'timestamp': parse_iso8601(tape.get('published_at')),
 109         }