Raphaël G. Git Repositories - youtubedl/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 ..compat import (
   8     compat_urllib_request,
   9 )
  10 from ..utils import (
  11     clean_html,
  12     ExtractorError,
  13     float_or_none,
  14     parse_iso8601,
  15 )
  16
  17
  18 class TapelyIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?(?:tape\.ly|tapely\.com)/(?P<id>[A-Za-z0-9\-_]+)(?:/(?P<songnr>\d+))?'
  20     _API_URL = 'http://tape.ly/showtape?id={0:}'
  21     _S3_SONG_URL = 'http://mytape.s3.amazonaws.com/{0:}'
  22     _SOUNDCLOUD_SONG_URL = 'http://api.soundcloud.com{0:}'
  23     _TESTS = [
  24         {
  25             'url': 'http://tape.ly/my-grief-as-told-by-water',
  26             'info_dict': {
  27                 'id': 23952,
  28                 'title': 'my grief as told by water',
  29                 'thumbnail': 're:^https?://.*\.png$',
  30                 'uploader_id': 16484,
  31                 'timestamp': 1411848286,
  32                 'description': 'For Robin and Ponkers, whom the tides of life have taken out to sea.',
  33             },
  34             'playlist_count': 13,
  35         },
  36         {
  37             'url': 'http://tape.ly/my-grief-as-told-by-water/1',
  38             'md5': '79031f459fdec6530663b854cbc5715c',
  39             'info_dict': {
  40                 'id': 258464,
  41                 'title': 'Dreaming Awake  (My Brightest Diamond)',
  42                 'ext': 'm4a',
  43             },
  44         },
  45         {
  46             'url': 'https://tapely.com/my-grief-as-told-by-water',
  47             'only_matching': True,
  48         },
  49     ]
  50
  51     def _real_extract(self, url):
  52         mobj = re.match(self._VALID_URL, url)
  53         display_id = mobj.group('id')
  54
  55         playlist_url = self._API_URL.format(display_id)
  56         request = compat_urllib_request.Request(playlist_url)
  57         request.add_header('X-Requested-With', 'XMLHttpRequest')
  58         request.add_header('Accept', 'application/json')
  59         request.add_header('Referer', url)
  60
  61         playlist = self._download_json(request, display_id)
  62
  63         tape = playlist['tape']
  64
  65         entries = []
  66         for s in tape['songs']:
  67             song = s['song']
  68             entry = {
  69                 'id': song['id'],
  70                 'duration': float_or_none(song.get('songduration'), 1000),
  71                 'title': song['title'],
  72             }
  73             if song['source'] == 'S3':
  74                 entry.update({
  75                     'url': self._S3_SONG_URL.format(song['filename']),
  76                 })
  77                 entries.append(entry)
  78             elif song['source'] == 'YT':
  79                 self.to_screen('YouTube video detected')
  80                 yt_id = song['filename'].replace('/youtube/', '')
  81                 entry.update(self.url_result(yt_id, 'Youtube', video_id=yt_id))
  82                 entries.append(entry)
  83             elif song['source'] == 'SC':
  84                 self.to_screen('SoundCloud song detected')
  85                 sc_url = self._SOUNDCLOUD_SONG_URL.format(song['filename'])
  86                 entry.update(self.url_result(sc_url, 'Soundcloud'))
  87                 entries.append(entry)
  88             else:
  89                 self.report_warning('Unknown song source: %s' % song['source'])
  90
  91         if mobj.group('songnr'):
  92             songnr = int(mobj.group('songnr')) - 1
  93             try:
  94                 return entries[songnr]
  95             except IndexError:
  96                 raise ExtractorError(
  97                     'No song with index: %s' % mobj.group('songnr'),
  98                     expected=True)
  99
 100         return {
 101             '_type': 'playlist',
 102             'id': tape['id'],
 103             'display_id': display_id,
 104             'title': tape['name'],
 105             'entries': entries,
 106             'thumbnail': tape.get('image_url'),
 107             'description': clean_html(tape.get('subtext')),
 108             'like_count': tape.get('likescount'),
 109             'uploader_id': tape.get('user_id'),
 110             'timestamp': parse_iso8601(tape.get('published_at')),
 111         }