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_search_regex(
 110             r'<title>(.+?)</title>', webpage, 'title')
 111
 112         media_url_string = self._search_regex(
 113             r'"url"\s*:\s*("[^"]+"),', webpage, 'media url', default=None)
 114
 115         if media_url_string:
 116             media_url = self._parse_json(media_url_string, media_id)
 117             formats = [{
 118                 'url': media_url,
 119                 'format_id': 'source',
 120                 'quality': 1,
 121             }]
 122         else:
 123             json_video = self._download_json('https://www.newgrounds.com/portal/video/' + media_id, media_id, headers={
 124                 'Accept': 'application/json',
 125                 'Referer': url,
 126                 'X-Requested-With': 'XMLHttpRequest'
 127             })
 128
 129             uploader = json_video.get('author')
 130             media_formats = json_video.get('sources', [])
 131             for media_format in media_formats:
 132                 media_sources = media_formats[media_format]
 133                 for source in media_sources:
 134                     formats.append({
 135                         'format_id': media_format,
 136                         'quality': int_or_none(media_format[:-1]),
 137                         'url': source.get('src')
 138                     })
 139
 140         if not uploader:
 141             uploader = self._html_search_regex(
 142                 (r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>',
 143                  r'(?:Author|Writer)\s*<a[^>]+>([^<]+)'), webpage, 'uploader',
 144                 fatal=False)
 145
 146         age_limit = self._html_search_regex(
 147             r'<h2\s*class=["\']rated-([^"\'])["\'][^>]+>', webpage, 'age_limit', default='e')
 148         age_limit = self._AGE_LIMIT.get(age_limit)
 149
 150         timestamp = unified_timestamp(self._html_search_regex(
 151             (r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+</dd>\s*<dd>[^<]+)',
 152              r'<dt>\s*Uploaded\s*</dt>\s*<dd>([^<]+)'), webpage, 'timestamp',
 153             default=None))
 154
 155         duration = parse_duration(self._html_search_regex(
 156             r'"duration"\s*:\s*["\']?(\d+)["\']?', webpage,
 157             'duration', default=None))
 158
 159         description = clean_html(get_element_by_id('author_comments', webpage)) or self._og_search_description(webpage)
 160
 161         view_count = parse_count(self._html_search_regex(
 162             r'(?s)<dt>\s*(?:Views|Listens)\s*</dt>\s*<dd>([\d\.,]+)</dd>', webpage,
 163             'view count', default=None))
 164
 165         filesize = int_or_none(self._html_search_regex(
 166             r'"filesize"\s*:\s*["\']?([\d]+)["\']?,', webpage, 'filesize',
 167             default=None))
 168
 169         video_type_description = self._html_search_regex(
 170             r'"description"\s*:\s*["\']?([^"\']+)["\']?,', webpage, 'filesize',
 171             default=None)
 172
 173         if len(formats) == 1:
 174             formats[0]['filesize'] = filesize
 175
 176         if video_type_description == 'Audio File':
 177             formats[0]['vcodec'] = 'none'
 178         self._check_formats(formats, media_id)
 179         self._sort_formats(formats)
 180
 181         return {
 182             'id': media_id,
 183             'title': title,
 184             'uploader': uploader,
 185             'timestamp': timestamp,
 186             'duration': duration,
 187             'formats': formats,
 188             'thumbnail': self._og_search_thumbnail(webpage),
 189             'description': description,
 190             'age_limit': age_limit,
 191             'view_count': view_count,
 192         }
 193
 194
 195 class NewgroundsPlaylistIE(InfoExtractor):
 196     IE_NAME = 'Newgrounds:playlist'
 197     _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P<id>[^/?#&]+)'
 198     _TESTS = [{
 199         'url': 'https://www.newgrounds.com/collection/cats',
 200         'info_dict': {
 201             'id': 'cats',
 202             'title': 'Cats',
 203         },
 204         'playlist_mincount': 45,
 205     }, {
 206         'url': 'https://www.newgrounds.com/collection/dogs',
 207         'info_dict': {
 208             'id': 'dogs',
 209             'title': 'Dogs',
 210         },
 211         'playlist_mincount': 26,
 212     }, {
 213         'url': 'http://www.newgrounds.com/audio/search/title/cats',
 214         'only_matching': True,
 215     }]
 216
 217     def _real_extract(self, url):
 218         playlist_id = self._match_id(url)
 219
 220         webpage = self._download_webpage(url, playlist_id)
 221
 222         title = self._search_regex(
 223             r'<title>([^>]+)</title>', webpage, 'title', default=None)
 224
 225         # cut left menu
 226         webpage = self._search_regex(
 227             r'(?s)<div[^>]+\bclass=["\']column wide(.+)',
 228             webpage, 'wide column', default=webpage)
 229
 230         entries = []
 231         for a, path, media_id in re.findall(
 232                 r'(<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>)',
 233                 webpage):
 234             a_class = extract_attributes(a).get('class')
 235             if a_class not in ('item-portalsubmission', 'item-audiosubmission'):
 236                 continue
 237             entries.append(
 238                 self.url_result(
 239                     f'https://www.newgrounds.com/{path}',
 240                     ie=NewgroundsIE.ie_key(), video_id=media_id))
 241
 242         return self.playlist_result(entries, playlist_id, title)
 243
 244
 245 class NewgroundsUserIE(InfoExtractor):
 246     IE_NAME = 'Newgrounds:user'
 247     _VALID_URL = r'https?://(?P<id>[^\.]+)\.newgrounds\.com/(?:movies|audio)/?(?:[#?]|$)'
 248     _TESTS = [{
 249         'url': 'https://burn7.newgrounds.com/audio',
 250         'info_dict': {
 251             'id': 'burn7',
 252         },
 253         'playlist_mincount': 150,
 254     }, {
 255         'url': 'https://burn7.newgrounds.com/movies',
 256         'info_dict': {
 257             'id': 'burn7',
 258         },
 259         'playlist_mincount': 2,
 260     }, {
 261         'url': 'https://brian-beaton.newgrounds.com/movies',
 262         'info_dict': {
 263             'id': 'brian-beaton',
 264         },
 265         'playlist_mincount': 10,
 266     }]
 267     _PAGE_SIZE = 30
 268
 269     def _fetch_page(self, channel_id, url, page):
 270         page += 1
 271         posts_info = self._download_json(
 272             f'{url}/page/{page}', channel_id,
 273             note=f'Downloading page {page}', headers={
 274                 'Accept': 'application/json, text/javascript, */*; q = 0.01',
 275                 'X-Requested-With': 'XMLHttpRequest',
 276             })
 277         sequence = posts_info.get('sequence', [])
 278         for year in sequence:
 279             posts = try_get(posts_info, lambda x: x['years'][str(year)]['items'])
 280             for post in posts:
 281                 path, media_id = self._search_regex(
 282                     r'<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>',
 283                     post, 'url', group=(1, 2))
 284                 yield self.url_result(f'https://www.newgrounds.com/{path}', NewgroundsIE.ie_key(), media_id)
 285
 286     def _real_extract(self, url):
 287         channel_id = self._match_id(url)
 288
 289         entries = OnDemandPagedList(functools.partial(
 290             self._fetch_page, channel_id, url), self._PAGE_SIZE)
 291
 292         return self.playlist_result(entries, channel_id)