yt_dlp/extractor/samplefocus.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     extract_attributes,
   6     get_element_by_attribute,
   7     int_or_none,
   8 )
   9
  10
  11 class SampleFocusIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
  13     _TESTS = [{
  14         'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
  15         'md5': '48c8d62d60be467293912e0e619a5120',
  16         'info_dict': {
  17             'id': '40316',
  18             'display_id': 'lil-peep-sad-emo-guitar',
  19             'ext': 'mp3',
  20             'title': 'Lil Peep Sad Emo Guitar',
  21             'thumbnail': r're:^https?://.+\.png',
  22             'license': 'Standard License',
  23             'uploader': 'CapsCtrl',
  24             'uploader_id': 'capsctrl',
  25             'like_count': int,
  26             'comment_count': int,
  27             'categories': ['Samples', 'Guitar', 'Electric guitar'],
  28         },
  29     }, {
  30         'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
  31         'only_matching': True,
  32     }, {
  33         'url': 'https://samplefocus.com/samples/young-chop-kick',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         display_id = self._match_id(url)
  39         webpage = self._download_webpage(url, display_id, impersonate=True)
  40
  41         sample_id = self._search_regex(
  42             r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
  43             webpage, 'sample id', group='id')
  44
  45         title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
  46             r'<h1>(.+?)</h1>', webpage, 'title')
  47
  48         mp3_url = self._search_regex(
  49             r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
  50             webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
  51                 r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
  52                 webpage, 'mp3 url', group=0))['content']
  53
  54         thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
  55             r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
  56             webpage, 'mp3', fatal=False, group='url')
  57
  58         comments = []
  59         for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
  60             comments.append({
  61                 'author': author,
  62                 'author_id': author_id,
  63                 'text': body,
  64             })
  65
  66         uploader_id = uploader = None
  67         mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
  68         if mobj:
  69             uploader_id, uploader = mobj.groups()
  70
  71         breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
  72         categories = []
  73         if breadcrumb:
  74             for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
  75                 categories.append(name)
  76
  77         def extract_count(klass):
  78             return int_or_none(self._html_search_regex(
  79                 rf'<span[^>]+class=(?:["\'])?{klass}-count[^>]*>(\d+)',
  80                 webpage, klass, fatal=False))
  81
  82         return {
  83             'id': sample_id,
  84             'title': title,
  85             'formats': [{
  86                 'url': mp3_url,
  87                 'ext': 'mp3',
  88                 'vcodec': 'none',
  89                 'acodec': 'mp3',
  90                 'http_headers': {
  91                     'Referer': url,
  92                 },
  93             }],
  94             'display_id': display_id,
  95             'thumbnail': thumbnail,
  96             'uploader': uploader,
  97             'license': self._html_search_regex(
  98                 r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
  99                 webpage, 'license', fatal=False, group='license'),
 100             'uploader_id': uploader_id,
 101             'like_count': extract_count(f'sample-{sample_id}-favorites'),
 102             'comment_count': extract_count('comments'),
 103             'comments': comments,
 104             'categories': categories,
 105         }