X-Git-Url: https://jfr.im/git/yt-dlp.git/blobdiff_plain/86e5f3ed2e6e71eb81ea4c9e26288f16119ffd0c..61edf57f8f13f6dfd81154174e647eb5fdd26089:/yt_dlp/extractor/tube8.py

diff --git a/yt_dlp/extractor/tube8.py b/yt_dlp/extractor/tube8.py
index 32e80d9d2..7267bf2bd 100644
--- a/yt_dlp/extractor/tube8.py
+++ b/yt_dlp/extractor/tube8.py
@@ -1,14 +1,22 @@
 import re
+import urllib.parse
 
+from .common import InfoExtractor
+from ..aes import aes_decrypt_text
 from ..utils import (
+    determine_ext,
+    format_field,
     int_or_none,
     str_to_int,
+    strip_or_none,
+    url_or_none,
 )
-from .keezmovies import KeezMoviesIE
 
 
-class Tube8IE(KeezMoviesIE):
+class Tube8IE(InfoExtractor):
+    _WORKING = False
     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)']
     _TESTS = [{
         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
         'md5': '65e20c48e6abff62ed0c3965fff13a39',
@@ -29,11 +37,89 @@ class Tube8IE(KeezMoviesIE):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
-            webpage)
+    def _extract_info(self, url, fatal=True):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+        display_id = (mobj.group('display_id')
+                      if 'display_id' in mobj.groupdict()
+                      else None) or mobj.group('id')
+
+        webpage = self._download_webpage(
+            url, display_id, headers={'Cookie': 'age_verified=1'})
+
+        formats = []
+        format_urls = set()
+
+        title = None
+        thumbnail = None
+        duration = None
+        encrypted = False
+
+        def extract_format(format_url, height=None):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//')):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': format_field(height, None, '%dp'),
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(urllib.parse.unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                self.raise_no_formats(
+                    f'Video {video_id} is no longer available', expected=True)
+
+        if not title:
+            title = self._html_search_regex(
+                r'<h1[^>]*>([^<]+)', webpage, 'title')
+
+        return webpage, {
+            'id': video_id,
+            'display_id': display_id,
+            'title': strip_or_none(title),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
+            'formats': formats,
+        }
 
     def _real_extract(self, url):
         webpage, info = self._extract_info(url)
@@ -67,8 +153,8 @@ def _real_extract(self, url):
         tags_str = self._search_regex(
             r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
             webpage, 'tags', fatal=False)
-        tags = [t for t in re.findall(
-            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
+        tags = list(re.findall(
+            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)) if tags_str else None
 
         info.update({
             'description': description,