add doostream extractor

youtube_dl/extractor/doodstream.py

@@ -0,0 +1,127 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import random
+import string
+import time
+import re
+
+from ..utils import (
+    clean_html,
+    get_element_by_class,
+    parse_duration,
+    parse_filesize,
+    unified_strdate,
+)
+
+from .common import InfoExtractor
+
+
+class DoodStreamIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<host>(?:www\.)?dood\.(?:[^/]*))/[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',
+            '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):
+        video_id = self._match_id(url)
+        host = re.match(self._VALID_URL, url).groups()[0]
+        print('https://%s/' % host)
+        webpage = self._download_webpage(url, video_id)
+
+        if '/d/' in url:
+            url = ('https://%s' % host) + self._html_search_regex(
+                r'<iframe src="(/e/[a-z0-9]+)"', webpage, 'embed')
+            video_id = self._match_id(url)
+            webpage = self._download_webpage(url, video_id)
+
+        title = self._html_search_meta(['og:title', 'twitter:title'],
+                                       webpage, default=None) or self._html_search_regex(
+            r'<title\b[^>]*>([^<]+)</title>', webpage, 'title', default=None)
+        thumb = self._html_search_meta(['og:image', 'twitter:image', 'poster'],
+                                       webpage, default=None)
+        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://%s/' % host) + 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
+        }
+        authpage = self._download_webpage(auth_url, video_id, headers=headers)
+        print('%s' % authpage)
+        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):
+            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,
+        }

youtube_dl/extractor/extractors.py

@@ -309,6 +309,7 @@ from .douyutv import (
     DouyuShowIE,
     DouyuTVIE,
 )
+from .doodstream import DoodStreamIE
 from .dplay import (
     DPlayIE,
     DiscoveryPlusIE,