Merge 141679549f into c5098961b0

youtube_dl/extractor/doodstream.py

@@ -6,53 +6,85 @@ import string
 import time
 import re
 
+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?://(?P<host>(?:www\.)?(dood|ds2play)\.(?:[^/]*))/[ed]/(?P<id>[a-z0-9]+)'
+    _VALID_URL = r'https?://(?P<host>(?:www\.)?dood\.(?:[^/]*))/[ed]/(?P<id>[a-z0-9]+)'
     _TESTS = [{
-        'url': 'https://dood.li/e/h7ecgw5oqn8k',
+        'url': 'http://dood.to/e/5s1wmbdacezb',
-        'md5': '90f2af170551c17fc78bee7426890054',
+        'md5': '4568b83b31e13242b3f1ff96c55f0595',
         'info_dict': {
-            'id': 'h7ecgw5oqn8k',
+            'id': '5s1wmbdacezb',
             'ext': 'mp4',
-            'title': 'Free-Slow-Music - DoodStream',
+            'title': 'Kat Wonders - Monthly May 2020',
-            'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
+            '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',
+            'upload_date': '20211202',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/[\w/]+\.jpg',
+            'filesize_approx': int,
+            'duration': 9886,
         }
     }, {
-        'url': 'http://dood.watch/d/h7ecgw5oqn8k',
+        'url': 'https://dood.so/d/wlihoael8uog',
-        'md5': '90f2af170551c17fc78bee7426890054',
-        'info_dict': {
-            'id': 'h7ecgw5oqn8k',
-            'ext': 'mp4',
-            'title': 'Free-Slow-Music - DoodStream',
-            'thumbnail': 'https://img.doodcdn.co/splash/7mbnwydhb6kb7xyk.jpg',
-        }
-    }, {
-        'url': 'https://dood.li/d/wlihoael8uog',
         'md5': '2c14444c89788cc309738c1560abe278',
         'info_dict': {
             'id': 'wlihoael8uog',
             'ext': 'mp4',
-            'title': 'VID 20220319 161659 - DoodStream',
+            'title': 'VID 20220319 161659',
-            'thumbnail': 'https://img.doodcdn.co/splash/rmpnhb8ckkk79cge.jpg',
+            'thumbnail': r're:https?://img\.doodcdn\.com?/splash/rmpnhb8ckkk79cge\.jpg',
+            'upload_date': '20220319',
+            'filesize_approx': int,
+            'duration': 12.0,
         }
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         host = re.match(self._VALID_URL, url).groups()[0]
-        url = url.replace(host, 'dood.li')
+        print('https://%s/' % host)
-        host = 'dood.li'
         webpage = self._download_webpage(url, video_id)
 
         if '/d/' in url:
@@ -72,12 +104,15 @@ class DoodStreamIE(InfoExtractor):
             webpage, default=None)
         auth_url = ('https://%s/' % host) + self._html_search_regex(
             r'(/pass_md5.*?)\'', webpage, 'pass_md5')
+        print('%s' % auth_url)
         headers = {
             'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
             'Referer': url
         }
-        authpage = self._download_webpage(auth_url, video_id, headers=headers)
+
-        final_url = authpage + ''.join([random.choice(string.ascii_letters + string.digits) for _ in
+        webpage = self._download_webpage(auth_url, video_id, headers=headers)
+
+        final_url = webpage + ''.join([random.choice(string.ascii_letters + string.digits) for _ in
                                        range(10)]) + "?token=" + token + "&expiry=" + str(int(time.time() * 1000))
 
         def get_class_text(x):
@@ -95,3 +130,4 @@ class DoodStreamIE(InfoExtractor):
             'description': description,
             'thumbnail': thumb,
         }
+