From 847a6464a8a1c3b6848d3cdb26f19c4cf79dd10e Mon Sep 17 00:00:00 2001
From: schnusch <schnusch@users.noreply.github.com>
Date: Sat, 24 Apr 2021 22:10:05 +0200
Subject: [PATCH] [doodstream] fix and add more metadata

  * metadata
      * fetch and decrypt video title
          * implemented doodExe
      * add filesize and duration
      * removed description
      * use _og_search_thumbnail
  * remove User-Agent from HTTP headers because it is not needed
---
 youtube_dl/extractor/doodstream.py | 60 +++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 14 deletions(-)

diff --git a/youtube_dl/extractor/doodstream.py b/youtube_dl/extractor/doodstream.py
index ddddd717a..cfc5ebafd 100644
--- a/youtube_dl/extractor/doodstream.py
+++ b/youtube_dl/extractor/doodstream.py
@@ -7,10 +7,28 @@ import time
 
 from .common import InfoExtractor
 from ..utils import (
+    js_to_json,
     urljoin,
 )
 
 
+def doodExe(crp, crs):
+    if crp == 'N_crp':
+        return crs
+    sorted_crp = ''.join(sorted(crp))
+    result = ''
+    for c in crs:
+        i = crp.find(c)
+        if i >= 0:
+            result += sorted_crp[i]
+    result = result.replace('+.+', '(')
+    result = result.replace('+..+', ')')
+    result = result.replace('+-+', '[')
+    result = result.replace('+--+', ']')
+    result = result.replace('+', ' ')
+    return result
+
+
 class DoodStreamIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:doodstream\.com|dood\.(?:so|to|watch))/[de]/(?P<id>[^/?#]+)'
     _TESTS = [{
@@ -21,6 +39,8 @@ class DoodStreamIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Big Buck Bunny Trailer',
             'thumbnail': r're:^https?://.*\.jpg$',
+            'filesize': 4447915,
+            'duration': 33,
         },
     }]
 
@@ -28,32 +48,44 @@ class DoodStreamIE(InfoExtractor):
         video_id = self._match_id(url)
 
         url = urljoin(url, '/e/' + video_id)
+        referer = {'Referer': url}
         webpage = self._download_webpage(url, video_id)
 
-        title = self._html_search_meta(['og:title', 'twitter:title'],
-                                       webpage, default=None)
-        thumb = self._html_search_meta(['og:image', 'twitter:image'],
-                                       webpage, default=None)
+        metadata_url = self._html_search_regex(r"('/cptr/[^']*')", webpage,
+                                               'video metadata')
+        metadata_url = self._parse_json(metadata_url, video_id,
+                                        transform_source=js_to_json)
+        metadata_url = urljoin(url, metadata_url)
+        metadata = self._download_json(metadata_url, video_id, headers=referer)
+
+        thumb = self._og_search_thumbnail(webpage)
+        try:
+            filesize = int(doodExe(**metadata['siz']), 10)
+        except (KeyError, ValueError):
+            filesize = None
+        try:
+            duration = int(doodExe(**metadata['len']), 10)
+        except (KeyError, ValueError):
+            duration = None
+        try:
+            title = doodExe(**metadata['ttl'])
+        except KeyError:
+            title = video_id
+
         token = self._html_search_regex(r'[?&]token=([a-z0-9]+)[&\']', webpage, 'token')
-        description = self._html_search_meta(
-            ['og:description', 'description', 'twitter:description'],
-            webpage, default=None)
         auth_url = 'https://dood.to' + self._html_search_regex(
             r'(/pass_md5.*?)\'', webpage, 'pass_md5')
-        headers = {
-            'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
-            'referer': url
-        }
 
-        webpage = self._download_webpage(auth_url, video_id, headers=headers)
+        webpage = self._download_webpage(auth_url, video_id, headers=referer)
         final_url = webpage + ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(10)) + "?token=" + token + "&expiry=" + str(int(time.time() * 1000))
 
         return {
             'id': video_id,
             'title': title,
             'url': final_url,
-            'http_headers': headers,
+            'http_headers': referer,
             'ext': 'mp4',
-            'description': description,
             'thumbnail': thumb,
+            'filesize': filesize,
+            'duration': duration,
         }