yt_dlp/extractor/newgrounds.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import functools
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     clean_html,
  10     extract_attributes,
  11     get_element_by_id,
  12     int_or_none,
  13     parse_count,
  14     parse_duration,
  15     unified_timestamp,
  16     OnDemandPagedList,
  17     try_get,
  18 )
  19
  20
  21 class NewgroundsIE(InfoExtractor):
  22     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>\d+)(?:/format/flash)?'
  23     _TESTS = [{
  24         'url': 'https://www.newgrounds.com/audio/listen/549479',
  25         'md5': 'fe6033d297591288fa1c1f780386f07a',
  26         'info_dict': {
  27             'id': '549479',
  28             'ext': 'mp3',
  29             'title': 'B7 - BusMode',
  30             'uploader': 'Burn7',
  31             'timestamp': 1378878540,
  32             'upload_date': '20130911',
  33             'duration': 143,
  34             'view_count': int,
  35             'description': 'md5:b8b3c2958875189f07d8e313462e8c4f',
  36         },
  37     }, {
  38         'url': 'https://www.newgrounds.com/portal/view/1',
  39         'md5': 'fbfb40e2dc765a7e830cb251d370d981',
  40         'info_dict': {
  41             'id': '1',
  42             'ext': 'mp4',
  43             'title': 'Scrotum 1',
  44             'uploader': 'Brian-Beaton',
  45             'timestamp': 955064100,
  46             'upload_date': '20000406',
  47             'view_count': int,
  48             'description': 'Scrotum plays "catch."',
  49             'age_limit': 17,
  50         },
  51     }, {
  52         # source format unavailable, additional mp4 formats
  53         'url': 'http://www.newgrounds.com/portal/view/689400',
  54         'info_dict': {
  55             'id': '689400',
  56             'ext': 'mp4',
  57             'title': 'ZTV News Episode 8',
  58             'uploader': 'ZONE-SAMA',
  59             'timestamp': 1487965140,
  60             'upload_date': '20170224',
  61             'view_count': int,
  62             'description': 'md5:aff9b330ec2e78ed93b1ad6d017accc6',
  63             'age_limit': 17,
  64         },
  65         'params': {
  66             'skip_download': True,
  67         },
  68     }, {
  69         'url': 'https://www.newgrounds.com/portal/view/297383',
  70         'md5': '2c11f5fd8cb6b433a63c89ba3141436c',
  71         'info_dict': {
  72             'id': '297383',
  73             'ext': 'mp4',
  74             'title': 'Metal Gear Awesome',
  75             'uploader': 'Egoraptor',
  76             'timestamp': 1140663240,
  77             'upload_date': '20060223',
  78             'view_count': int,
  79             'description': 'md5:9246c181614e23754571995104da92e0',
  80             'age_limit': 13,
  81         }
  82     }, {
  83         'url': 'https://www.newgrounds.com/portal/view/297383/format/flash',
  84         'md5': '5d05585a9a0caca059f5abfbd3865524',
  85         'info_dict': {
  86             'id': '297383',
  87             'ext': 'swf',
  88             'title': 'Metal Gear Awesome',
  89             'description': 'Metal Gear Awesome',
  90             'uploader': 'Egoraptor',
  91             'upload_date': '20060223',
  92             'timestamp': 1140663240,
  93             'age_limit': 13,
  94         }
  95     }]
  96     _AGE_LIMIT = {
  97         'e': 0,
  98         't': 13,
  99         'm': 17,
 100         'a': 18,
 101     }
 102
 103     def _real_extract(self, url):
 104         media_id = self._match_id(url)
 105         formats = []
 106         uploader = None
 107         webpage = self._download_webpage(url, media_id)
 108
 109         title = self._html_extract_title(webpage)
 110
 111         media_url_string = self._search_regex(
 112             r'"url"\s*:\s*("[^"]+"),', webpage, 'media url', default=None)
 113
 114         if media_url_string:
 115             media_url = self._parse_json(media_url_string, media_id)
 116             formats = [{
 117                 'url': media_url,
 118                 'format_id': 'source',
 119                 'quality': 1,
 120             }]
 121         else:
 122             json_video = self._download_json('https://www.newgrounds.com/portal/video/' + media_id, media_id, headers={
 123                 'Accept': 'application/json',
 124                 'Referer': url,
 125                 'X-Requested-With': 'XMLHttpRequest'
 126             })
 127
 128             uploader = json_video.get('author')
 129             media_formats = json_video.get('sources', [])
 130             for media_format in media_formats:
 131                 media_sources = media_formats[media_format]
 132                 for source in media_sources:
 133                     formats.append({
 134                         'format_id': media_format,
 135                         'quality': int_or_none(media_format[:-1]),
 136                         'url': source.get('src')
 137                     })
 138
 139         if not uploader:
 140             uploader = self._html_search_regex(
 141                 (r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>',
 142                  r'(?:Author|Writer)\s*<a[^>]+>([^<]+)'), webpage, 'uploader',
 143                 fatal=False)
 144
 145         age_limit = self._html_search_regex(
 146             r'<h2\s*class=["\']rated-([^"\'])["\'][^>]+>', webpage, 'age_limit', default='e')
 147         age_limit = self._AGE_LIMIT.get(age_limit)
 148
 149         timestamp = unified_timestamp(self._html_search_regex(
 150             (r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+</dd>\s*<dd>[^<]+)',
 151              r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+)'), webpage, 'timestamp',
 152             default=None))
 153
 154         duration = parse_duration(self._html_search_regex(
 155             r'"duration"\s*:\s*["\']?(\d+)["\']?', webpage,
 156             'duration', default=None))
 157
 158         description = clean_html(get_element_by_id('author_comments', webpage)) or self._og_search_description(webpage)
 159
 160         view_count = parse_count(self._html_search_regex(
 161             r'(?s)<dt>\s*(?:Views|Listens)\s*</dt>\s*<dd>([\d\.,]+)</dd>', webpage,
 162             'view count', default=None))
 163
 164         filesize = int_or_none(self._html_search_regex(
 165             r'"filesize"\s*:\s*["\']?([\d]+)["\']?,', webpage, 'filesize',
 166             default=None))
 167
 168         video_type_description = self._html_search_regex(
 169             r'"description"\s*:\s*["\']?([^"\']+)["\']?,', webpage, 'filesize',
 170             default=None)
 171
 172         if len(formats) == 1:
 173             formats[0]['filesize'] = filesize
 174
 175         if video_type_description == 'Audio File':
 176             formats[0]['vcodec'] = 'none'
 177         self._check_formats(formats, media_id)
 178         self._sort_formats(formats)
 179
 180         return {
 181             'id': media_id,
 182             'title': title,
 183             'uploader': uploader,
 184             'timestamp': timestamp,
 185             'duration': duration,
 186             'formats': formats,
 187             'thumbnail': self._og_search_thumbnail(webpage),
 188             'description': description,
 189             'age_limit': age_limit,
 190             'view_count': view_count,
 191         }
 192
 193
 194 class NewgroundsPlaylistIE(InfoExtractor):
 195     IE_NAME = 'Newgrounds:playlist'
 196     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
 197     _TESTS = [{
 198         'url': 'https://www.newgrounds.com/collection/cats',
 199         'info_dict': {
 200             'id': 'cats',
 201             'title': 'Cats',
 202         },
 203         'playlist_mincount': 45,
 204     }, {
 205         'url': 'https://www.newgrounds.com/collection/dogs',
 206         'info_dict': {
 207             'id': 'dogs',
 208             'title': 'Dogs',
 209         },
 210         'playlist_mincount': 26,
 211     }, {
 212         'url': 'http://www.newgrounds.com/audio/search/title/cats',
 213         'only_matching': True,
 214     }]
 215
 216     def _real_extract(self, url):
 217         playlist_id = self._match_id(url)
 218
 219         webpage = self._download_webpage(url, playlist_id)
 220
 221         title = self._html_extract_title(webpage, default=None)
 222
 223         # cut left menu
 224         webpage = self._search_regex(
 225             r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
 226             webpage, 'wide column', default=webpage)
 227
 228         entries = []
 229         for a, path, media_id in re.findall(
 230                 r'(<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>)',
 231                 webpage):
 232             a_class = extract_attributes(a).get('class')
 233             if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
 234                 continue
 235             entries.append(
 236                 self.url_result(
 237                     f'https://www.newgrounds.com/{path}',
 238                     ie=NewgroundsIE.ie_key(), video_id=media_id))
 239
 240         return self.playlist_result(entries, playlist_id, title)
 241
 242
 243 class NewgroundsUserIE(InfoExtractor):
 244     IE_NAME = 'Newgrounds:user'
 245     _VALID_URL = r'https?://(?P<id>[^\.]+)\.newgrounds\.com/(?:movies|audio)/?(?:[#?]|$)'
 246     _TESTS = [{
 247         'url': 'https://burn7.newgrounds.com/audio',
 248         'info_dict': {
 249             'id': 'burn7',
 250         },
 251         'playlist_mincount': 150,
 252     }, {
 253         'url': 'https://burn7.newgrounds.com/movies',
 254         'info_dict': {
 255             'id': 'burn7',
 256         },
 257         'playlist_mincount': 2,
 258     }, {
 259         'url': 'https://brian-beaton.newgrounds.com/movies',
 260         'info_dict': {
 261             'id': 'brian-beaton',
 262         },
 263         'playlist_mincount': 10,
 264     }]
 265     _PAGE_SIZE = 30
 266
 267     def _fetch_page(self, channel_id, url, page):
 268         page += 1
 269         posts_info = self._download_json(
 270             f'{url}/page/{page}', channel_id,
 271             note=f'Downloading page {page}', headers={
 272                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
 273                 'X-Requested-With': 'XMLHttpRequest',
 274             })
 275         sequence = posts_info.get('sequence', [])
 276         for year in sequence:
 277             posts = try_get(posts_info, lambda x: x['years'][str(year)]['items'])
 278             for post in posts:
 279                 path, media_id = self._search_regex(
 280                     r'<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>',
 281                     post, 'url', group=(1, 2))
 282                 yield self.url_result(f'https://www.newgrounds.com/{path}', NewgroundsIE.ie_key(), media_id)
 283
 284     def _real_extract(self, url):
 285         channel_id = self._match_id(url)
 286
 287         entries = OnDemandPagedList(functools.partial(
 288             self._fetch_page, channel_id, url), self._PAGE_SIZE)
 289
 290         return self.playlist_result(entries, channel_id)