From 3687a4f9bdb025855acd2a4e782748c8e3810765 Mon Sep 17 00:00:00 2001
From: dirkf <fieldhouse@gmx.net>
Date: Sat, 4 Jun 2022 08:07:54 +0100
Subject: [PATCH 1/2] [DoodStream] Add extractor from yt-dlp back-port and
 improve

---
 youtube_dl/extractor/doodstream.py | 119 +++++++++++++++++++++++++++++
 youtube_dl/extractor/extractors.py |   1 +
 2 files changed, 120 insertions(+)
 create mode 100644 youtube_dl/extractor/doodstream.py

diff --git a/youtube_dl/extractor/doodstream.py b/youtube_dl/extractor/doodstream.py
new file mode 100644
index 000000000..70bf4e512
--- /dev/null
+++ b/youtube_dl/extractor/doodstream.py
@@ -0,0 +1,119 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import string
+import time
+
+from ..compat import compat_filter as filter
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    get_element_by_class,
+    parse_duration,
+    parse_filesize,
+    update_url_query,
+    unified_strdate,
+    url_or_none,
+)
+
+from .common import InfoExtractor
+
+
+class DoodStreamIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch)/[ed]/(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'http://dood.to/e/5s1wmbdacezb',
+        'md5': '4568b83b31e13242b3f1ff96c55f0595',
+        'info_dict': {
+            'id': '5s1wmbdacezb',
+            'ext': 'mp4',
+            'title': 'Kat Wonders - Monthly May 2020',
+            'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
+            'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
+        },
+        'skip': 'Video not found',
+    }, {
+        'url': 'http://dood.watch/d/5s1wmbdacezb',
+        'md5': '4568b83b31e13242b3f1ff96c55f0595',
+        'info_dict': {
+            'id': '5s1wmbdacezb',
+            'ext': 'mp4',
+            'title': 'Kat Wonders - Monthly May 2020',
+            'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
+            'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
+        },
+        'skip': 'Video not found',
+    }, {
+        'url': 'https://dood.to/d/jzrxn12t2s7n',
+        'md5': '3207e199426eca7c2aa23c2872e6728a',
+        'info_dict': {
+            'id': 'jzrxn12t2s7n',
+            'ext': 'mp4',
+            'title': 'Stacy Cruz Cute ALLWAYSWELL',
+            'description': 'Stacy Cruz Cute ALLWAYSWELL | DoodStream.com',
+            'thumbnail': 'https://img.doodcdn.com/snaps/8edqd5nppkac3x8u.jpg',
+        },
+        'skip': 'Video not found',
+    }, {
+        'url': 'https://dood.to/d/is34uy8wvaet',
+        'md5': '04740d3ba93bcd638aa7a097d9226710',
+        'info_dict': {
+            'id': 'is34uy8wvaet',
+            'ext': 'mp4',
+            'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB - DoodStream',
+            'upload_date': '20211202',
+            'filesize_approx': int,
+            'duration': 9886,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = 'https://dood.to/e/' + video_id
+        headers = {
+            'User-Agent': 'Mozilla/5.0',  # (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
+        }
+        webpage = self._download_webpage(url, video_id, headers=headers)
+
+        title = self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
+        if not title:
+            title = self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:\|\s+DoodStream\s*)?</title', webpage, 'title')
+            if title == 'Video not found':
+                raise ExtractorError(title, expected=True)
+        token = self._html_search_regex(r'''[?&]token=([a-z0-9]+)[&']''', webpage, 'token')
+
+        headers.update({
+            # 'User-Agent': 'Mozilla/5.0',  # (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
+            'referer': url
+        })
+
+        pass_md5 = self._html_search_regex(r'(/pass_md5.*?)\'', webpage, 'pass_md5')
+        final_url = (
+            self._download_webpage('https://dood.to' + pass_md5, video_id, headers=headers, note='Downloading final URL')
+            + ''.join((random.choice(string.ascii_letters + string.digits) for _ in range(10)))
+        )
+        final_url = update_url_query(final_url, {'token': token, 'expiry': int(time.time() * 1000), })
+
+        thumb = next(filter(None, (url_or_none(self._html_search_meta(x, webpage, default=None))
+                                   for x in ('og:image', 'twitter:image'))), None)
+        description = self._html_search_meta(
+            ('og:description', 'description', 'twitter:description'), webpage, default=None)
+
+        webpage = self._download_webpage('https://dood.to/d/' + video_id, video_id, headers=headers, fatal=False)
+
+        def get_class_text(x):
+            return clean_html(get_element_by_class(x, webpage))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': final_url,
+            'http_headers': headers,
+            'ext': 'mp4',
+            'upload_date': unified_strdate(get_class_text('uploadate')),
+            'duration': parse_duration(get_class_text('length')),
+            'filesize_approx': parse_filesize(get_class_text('size')),
+            'description': description,
+            'thumbnail': thumb,
+        }
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 452caeade..3d1d9375e 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -299,6 +299,7 @@ from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
+from .doodstream import DoodStreamIE
 from .dotsub import DotsubIE
 from .douyutv import (
     DouyuShowIE,

From 9dd91758aea6b3427662cac1efde1c5b5c1de6c3 Mon Sep 17 00:00:00 2001
From: dirkf <fieldhouse@gmx.net>
Date: Sat, 4 Jun 2022 09:26:41 +0100
Subject: [PATCH 2/2] [DoodStream] Support more TLDs * also fix title
 extraction

---
 youtube_dl/extractor/doodstream.py | 35 +++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/youtube_dl/extractor/doodstream.py b/youtube_dl/extractor/doodstream.py
index 70bf4e512..94411ebb0 100644
--- a/youtube_dl/extractor/doodstream.py
+++ b/youtube_dl/extractor/doodstream.py
@@ -21,7 +21,7 @@ from .common import InfoExtractor
 
 
 class DoodStreamIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch)/[ed]/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?dood\.(?:to|watch|so|la|pm|sh|ws|one)/[ed]/(?P<id>[a-z0-9]+)'
     _TESTS = [{
         'url': 'http://dood.to/e/5s1wmbdacezb',
         'md5': '4568b83b31e13242b3f1ff96c55f0595',
@@ -61,11 +61,24 @@ class DoodStreamIE(InfoExtractor):
         'info_dict': {
             'id': 'is34uy8wvaet',
             'ext': 'mp4',
-            'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB - DoodStream',
+            'title': 'Akhanda (2021) Telugu DVDScr MP3 700MB',
             'upload_date': '20211202',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
             'filesize_approx': int,
             'duration': 9886,
         }
+    }, {
+        'url': 'https://dood.so/d/wlihoael8uog',
+        'md5': '2c14444c89788cc309738c1560abe278',
+        'info_dict': {
+            'id': 'wlihoael8uog',
+            'ext': 'mp4',
+            'title': 'VID 20220319 161659',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
+            'upload_date': '20220319',
+            'filesize_approx': int,
+            'duration': 12.0,
+        }
     }]
 
     def _real_extract(self, url):
@@ -76,11 +89,12 @@ class DoodStreamIE(InfoExtractor):
         }
         webpage = self._download_webpage(url, video_id, headers=headers)
 
-        title = self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
-        if not title:
-            title = self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:\|\s+DoodStream\s*)?</title', webpage, 'title')
-            if title == 'Video not found':
-                raise ExtractorError(title, expected=True)
+        def get_title(html, fatal=False):
+            return self._html_search_regex(r'<title\b[^>]*>([^<]+?)(?:[|-]\s+DoodStream\s*)?</title', html, 'title', fatal=fatal)
+
+        title = get_title(webpage)
+        if title == 'Video not found':
+            raise ExtractorError(title, expected=True)
         token = self._html_search_regex(r'''[?&]token=([a-z0-9]+)[&']''', webpage, 'token')
 
         headers.update({
@@ -100,7 +114,12 @@ class DoodStreamIE(InfoExtractor):
         description = self._html_search_meta(
             ('og:description', 'description', 'twitter:description'), webpage, default=None)
 
-        webpage = self._download_webpage('https://dood.to/d/' + video_id, video_id, headers=headers, fatal=False)
+        webpage = self._download_webpage('https://dood.to/d/' + video_id, video_id, headers=headers, fatal=False) or ''
+
+        title = (
+            self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
+            or get_title(webpage, fatal=(title is not None))
+            or title)
 
         def get_class_text(x):
             return clean_html(get_element_by_class(x, webpage))