yt_dlp/extractor/newgrounds.py

   1 import functools
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_html,
   7     extract_attributes,
   8     get_element_by_id,
   9     int_or_none,
  10     parse_count,
  11     parse_duration,
  12     unified_timestamp,
  13     OnDemandPagedList,
  14     try_get,
  15 )
  16
  17
  18 class NewgroundsIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>\d+)(?:/format/flash)?'
  20     _TESTS = [{
  21         'url': 'https://www.newgrounds.com/audio/listen/549479',
  22         'md5': 'fe6033d297591288fa1c1f780386f07a',
  23         'info_dict': {
  24             'id': '549479',
  25             'ext': 'mp3',
  26             'title': 'B7 - BusMode',
  27             'uploader': 'Burn7',
  28             'timestamp': 1378878540,
  29             'upload_date': '20130911',
  30             'duration': 143,
  31             'view_count': int,
  32             'description': 'md5:b8b3c2958875189f07d8e313462e8c4f',
  33         },
  34     }, {
  35         'url': 'https://www.newgrounds.com/portal/view/1',
  36         'md5': 'fbfb40e2dc765a7e830cb251d370d981',
  37         'info_dict': {
  38             'id': '1',
  39             'ext': 'mp4',
  40             'title': 'Scrotum 1',
  41             'uploader': 'Brian-Beaton',
  42             'timestamp': 955064100,
  43             'upload_date': '20000406',
  44             'view_count': int,
  45             'description': 'Scrotum plays "catch."',
  46             'age_limit': 17,
  47         },
  48     }, {
  49         # source format unavailable, additional mp4 formats
  50         'url': 'http://www.newgrounds.com/portal/view/689400',
  51         'info_dict': {
  52             'id': '689400',
  53             'ext': 'mp4',
  54             'title': 'ZTV News Episode 8',
  55             'uploader': 'ZONE-SAMA',
  56             'timestamp': 1487965140,
  57             'upload_date': '20170224',
  58             'view_count': int,
  59             'description': 'md5:aff9b330ec2e78ed93b1ad6d017accc6',
  60             'age_limit': 17,
  61         },
  62         'params': {
  63             'skip_download': True,
  64         },
  65     }, {
  66         'url': 'https://www.newgrounds.com/portal/view/297383',
  67         'md5': '2c11f5fd8cb6b433a63c89ba3141436c',
  68         'info_dict': {
  69             'id': '297383',
  70             'ext': 'mp4',
  71             'title': 'Metal Gear Awesome',
  72             'uploader': 'Egoraptor',
  73             'timestamp': 1140663240,
  74             'upload_date': '20060223',
  75             'view_count': int,
  76             'description': 'md5:9246c181614e23754571995104da92e0',
  77             'age_limit': 13,
  78         }
  79     }, {
  80         'url': 'https://www.newgrounds.com/portal/view/297383/format/flash',
  81         'md5': '5d05585a9a0caca059f5abfbd3865524',
  82         'info_dict': {
  83             'id': '297383',
  84             'ext': 'swf',
  85             'title': 'Metal Gear Awesome',
  86             'description': 'Metal Gear Awesome',
  87             'uploader': 'Egoraptor',
  88             'upload_date': '20060223',
  89             'timestamp': 1140663240,
  90             'age_limit': 13,
  91         }
  92     }]
  93     _AGE_LIMIT = {
  94         'e': 0,
  95         't': 13,
  96         'm': 17,
  97         'a': 18,
  98     }
  99
 100     def _real_extract(self, url):
 101         media_id = self._match_id(url)
 102         formats = []
 103         uploader = None
 104         webpage = self._download_webpage(url, media_id)
 105
 106         title = self._html_extract_title(webpage)
 107
 108         media_url_string = self._search_regex(
 109             r'"url"\s*:\s*("[^"]+"),', webpage, 'media url', default=None)
 110
 111         if media_url_string:
 112             media_url = self._parse_json(media_url_string, media_id)
 113             formats = [{
 114                 'url': media_url,
 115                 'format_id': 'source',
 116                 'quality': 1,
 117             }]
 118         else:
 119             json_video = self._download_json('https://www.newgrounds.com/portal/video/' + media_id, media_id, headers={
 120                 'Accept': 'application/json',
 121                 'Referer': url,
 122                 'X-Requested-With': 'XMLHttpRequest'
 123             })
 124
 125             uploader = json_video.get('author')
 126             media_formats = json_video.get('sources', [])
 127             for media_format in media_formats:
 128                 media_sources = media_formats[media_format]
 129                 for source in media_sources:
 130                     formats.append({
 131                         'format_id': media_format,
 132                         'quality': int_or_none(media_format[:-1]),
 133                         'url': source.get('src')
 134                     })
 135
 136         if not uploader:
 137             uploader = self._html_search_regex(
 138                 (r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>',
 139                  r'(?:Author|Writer)\s*<a[^>]+>([^<]+)'), webpage, 'uploader',
 140                 fatal=False)
 141
 142         age_limit = self._html_search_regex(
 143             r'<h2\s*class=["\']rated-([^"\'])["\'][^>]+>', webpage, 'age_limit', default='e')
 144         age_limit = self._AGE_LIMIT.get(age_limit)
 145
 146         timestamp = unified_timestamp(self._html_search_regex(
 147             (r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+</dd>\s*<dd>[^<]+)',
 148              r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+)'), webpage, 'timestamp',
 149             default=None))
 150
 151         duration = parse_duration(self._html_search_regex(
 152             r'"duration"\s*:\s*["\']?(\d+)["\']?', webpage,
 153             'duration', default=None))
 154
 155         description = clean_html(get_element_by_id('author_comments', webpage)) or self._og_search_description(webpage)
 156
 157         view_count = parse_count(self._html_search_regex(
 158             r'(?s)<dt>\s*(?:Views|Listens)\s*</dt>\s*<dd>([\d\.,]+)</dd>', webpage,
 159             'view count', default=None))
 160
 161         filesize = int_or_none(self._html_search_regex(
 162             r'"filesize"\s*:\s*["\']?([\d]+)["\']?,', webpage, 'filesize',
 163             default=None))
 164
 165         video_type_description = self._html_search_regex(
 166             r'"description"\s*:\s*["\']?([^"\']+)["\']?,', webpage, 'filesize',
 167             default=None)
 168
 169         if len(formats) == 1:
 170             formats[0]['filesize'] = filesize
 171
 172         if video_type_description == 'Audio File':
 173             formats[0]['vcodec'] = 'none'
 174         self._check_formats(formats, media_id)
 175         self._sort_formats(formats)
 176
 177         return {
 178             'id': media_id,
 179             'title': title,
 180             'uploader': uploader,
 181             'timestamp': timestamp,
 182             'duration': duration,
 183             'formats': formats,
 184             'thumbnail': self._og_search_thumbnail(webpage),
 185             'description': description,
 186             'age_limit': age_limit,
 187             'view_count': view_count,
 188         }
 189
 190
 191 class NewgroundsPlaylistIE(InfoExtractor):
 192     IE_NAME = 'Newgrounds:playlist'
 193     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
 194     _TESTS = [{
 195         'url': 'https://www.newgrounds.com/collection/cats',
 196         'info_dict': {
 197             'id': 'cats',
 198             'title': 'Cats',
 199         },
 200         'playlist_mincount': 45,
 201     }, {
 202         'url': 'https://www.newgrounds.com/collection/dogs',
 203         'info_dict': {
 204             'id': 'dogs',
 205             'title': 'Dogs',
 206         },
 207         'playlist_mincount': 26,
 208     }, {
 209         'url': 'http://www.newgrounds.com/audio/search/title/cats',
 210         'only_matching': True,
 211     }]
 212
 213     def _real_extract(self, url):
 214         playlist_id = self._match_id(url)
 215
 216         webpage = self._download_webpage(url, playlist_id)
 217
 218         title = self._html_extract_title(webpage, default=None)
 219
 220         # cut left menu
 221         webpage = self._search_regex(
 222             r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
 223             webpage, 'wide column', default=webpage)
 224
 225         entries = []
 226         for a, path, media_id in re.findall(
 227                 r'(<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>)',
 228                 webpage):
 229             a_class = extract_attributes(a).get('class')
 230             if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
 231                 continue
 232             entries.append(
 233                 self.url_result(
 234                     f'https://www.newgrounds.com/{path}',
 235                     ie=NewgroundsIE.ie_key(), video_id=media_id))
 236
 237         return self.playlist_result(entries, playlist_id, title)
 238
 239
 240 class NewgroundsUserIE(InfoExtractor):
 241     IE_NAME = 'Newgrounds:user'
 242     _VALID_URL = r'https?://(?P<id>[^\.]+)\.newgrounds\.com/(?:movies|audio)/?(?:[#?]|$)'
 243     _TESTS = [{
 244         'url': 'https://burn7.newgrounds.com/audio',
 245         'info_dict': {
 246             'id': 'burn7',
 247         },
 248         'playlist_mincount': 150,
 249     }, {
 250         'url': 'https://burn7.newgrounds.com/movies',
 251         'info_dict': {
 252             'id': 'burn7',
 253         },
 254         'playlist_mincount': 2,
 255     }, {
 256         'url': 'https://brian-beaton.newgrounds.com/movies',
 257         'info_dict': {
 258             'id': 'brian-beaton',
 259         },
 260         'playlist_mincount': 10,
 261     }]
 262     _PAGE_SIZE = 30
 263
 264     def _fetch_page(self, channel_id, url, page):
 265         page += 1
 266         posts_info = self._download_json(
 267             f'{url}/page/{page}', channel_id,
 268             note=f'Downloading page {page}', headers={
 269                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
 270                 'X-Requested-With': 'XMLHttpRequest',
 271             })
 272         sequence = posts_info.get('sequence', [])
 273         for year in sequence:
 274             posts = try_get(posts_info, lambda x: x['years'][str(year)]['items'])
 275             for post in posts:
 276                 path, media_id = self._search_regex(
 277                     r'<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>',
 278                     post, 'url', group=(1, 2))
 279                 yield self.url_result(f'https://www.newgrounds.com/{path}', NewgroundsIE.ie_key(), media_id)
 280
 281     def _real_extract(self, url):
 282         channel_id = self._match_id(url)
 283
 284         entries = OnDemandPagedList(functools.partial(
 285             self._fetch_page, channel_id, url), self._PAGE_SIZE)
 286
 287         return self.playlist_result(entries, channel_id)