[yapfiles] Add extractor (closes #15726, refs #11085)

youtube_dl/extractor/extractors.py

@@ -1369,6 +1369,7 @@ from .yandexmusic import (
     YandexMusicPlaylistIE,
 )
 from .yandexdisk import YandexDiskIE
+from .yapfiles import YapFilesIE
 from .yesjapan import YesJapanIE
 from .yinyuetai import YinYueTaiIE
 from .ynet import YnetIE

youtube_dl/extractor/generic.py

@@ -102,6 +102,7 @@ from .channel9 import Channel9IE
 from .vshare import VShareIE
 from .mediasite import MediasiteIE
 from .springboardplatform import SpringboardPlatformIE
+from .yapfiles import YapFilesIE
 
 
 class GenericIE(InfoExtractor):
@@ -1970,6 +1971,18 @@ class GenericIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+        },
+        {
+            'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html',
+            'info_dict': {
+                'id': 'vMDE4NzI1Mjgt690b',
+                'ext': 'mp4',
+                'title': 'Котята',
+            },
+            'add_ie': [YapFilesIE.ie_key()],
+            'params': {
+                'skip_download': True,
+            },
         }
         # {
         #     # TODO: find another test
@@ -2947,6 +2960,11 @@ class GenericIE(InfoExtractor):
                 springboardplatform_urls, video_id, video_title,
                 ie=SpringboardPlatformIE.ie_key())
 
+        yapfiles_urls = YapFilesIE._extract_urls(webpage)
+        if yapfiles_urls:
+            return self.playlist_from_matches(
+                yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key())
+
         def merge_dicts(dict1, dict2):
             merged = {}
             for k, v in dict1.items():

youtube_dl/extractor/yapfiles.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+    unescapeHTML,
+)
+
+
+class YapFilesIE(InfoExtractor):
+    _YAPFILES_URL = r'//(?:(?:www|api)\.)?yapfiles\.ru/get_player/*\?.*?\bv=(?P<id>\w+)'
+    _VALID_URL = r'https?:%s' % _YAPFILES_URL
+    _TESTS = [{
+        # with hd
+        'url': 'http://www.yapfiles.ru/get_player/?v=vMDE1NjcyNDUt0413',
+        'md5': '2db19e2bfa2450568868548a1aa1956c',
+        'info_dict': {
+            'id': 'vMDE1NjcyNDUt0413',
+            'ext': 'mp4',
+            'title': 'Самый худший пароль WIFI',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 72,
+        },
+    }, {
+        # without hd
+        'url': 'https://api.yapfiles.ru/get_player/?uid=video_player_1872528&plroll=1&adv=1&v=vMDE4NzI1Mjgt690b',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [unescapeHTML(mobj.group('url')) for mobj in re.finditer(
+            r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?%s.*?)\1'
+            % YapFilesIE._YAPFILES_URL, webpage)]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id, fatal=False)
+
+        player_url = None
+        query = {}
+        if webpage:
+            player_url = self._search_regex(
+                r'player\.init\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+                'player url', default=None, group='url')
+
+        if not player_url:
+            player_url = 'http://api.yapfiles.ru/load/%s/' % video_id
+            query = {
+                'md5': 'ded5f369be61b8ae5f88e2eeb2f3caff',
+                'type': 'json',
+                'ref': url,
+            }
+
+        player = self._download_json(
+            player_url, video_id, query=query)['player']
+
+        playlist_url = player['playlist']
+        title = player['title']
+        thumbnail = player.get('poster')
+
+        if title == 'Ролик удален' or 'deleted.jpg' in (thumbnail or ''):
+            raise ExtractorError(
+                'Video %s has been removed' % video_id, expected=True)
+
+        playlist = self._download_json(
+            playlist_url, video_id)['player']['main']
+
+        hd_height = int_or_none(player.get('hd'))
+
+        QUALITIES = ('sd', 'hd')
+        quality_key = qualities(QUALITIES)
+        formats = []
+        for format_id in QUALITIES:
+            is_hd = format_id == 'hd'
+            format_url = playlist.get(
+                'file%s' % ('_hd' if is_hd else ''))
+            if not format_url or not isinstance(format_url, compat_str):
+                continue
+            formats.append({
+                'url': format_url,
+                'format_id': format_id,
+                'quality': quality_key(format_id),
+                'height': hd_height if is_hd else None,
+            })
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(player.get('length')),
+            'formats': formats,
+        }