From 041cd20a71ed11b5aa785a0239c01ccf67d092f2 Mon Sep 17 00:00:00 2001
From: df <fieldhouse@gmx.net>
Date: Wed, 25 Aug 2021 18:56:01 +0100
Subject: [PATCH] Update Beeg extractor for new API

---
 youtube_dl/extractor/beeg.py | 83 ++++++++++++++++++++++++++++++++----
 1 file changed, 74 insertions(+), 9 deletions(-)

diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py
index 5788d13ba..551b789e5 100644
--- a/youtube_dl/extractor/beeg.py
+++ b/youtube_dl/extractor/beeg.py
@@ -6,13 +6,17 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
+    dict_get,
     int_or_none,
+    parse_iso8601,
+    try_get,
     unified_timestamp,
+    urljoin,
 )
 
 
 class BeegIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/-?(?P<id>\d+)'
     _TESTS = [{
         # api/v6 v1
         'url': 'http://beeg.com/5416503',
@@ -27,7 +31,8 @@ class BeegIE(InfoExtractor):
             'duration': 383,
             'tags': list,
             'age_limit': 18,
-        }
+        },
+        'skip': 'no longer available',
     }, {
         # api/v6 v2
         'url': 'https://beeg.com/1941093077?t=911-1391',
@@ -42,13 +47,23 @@ class BeegIE(InfoExtractor):
     }, {
         'url': 'https://beeg.porn/5416503',
         'only_matching': True,
+    }, {
+        'url': 'https://beeg.com/-01882333214',
+        'md5': 'f8fd97a58a09bc6d2ac25b6bbc98c220',
+        'info_dict': {
+            'id': '01882333214',
+            'ext': 'mp4',
+            'title': 'Be mine',
+            'description': 'Lil cam dork living in Canada with 4 kitties',
+            'timestamp': 1628218803,
+            'upload_date': '20210806',
+            'duration': 559,
+            'tags': list,
+            'age_limit': 18,
+        },
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
+    def _old_real_extract(self, url, video_id, webpage):
         beeg_version = self._search_regex(
             r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
             default='1546225636701')
@@ -67,11 +82,14 @@ class BeegIE(InfoExtractor):
         else:
             query = {'v': 1}
 
-        for api_path in ('', 'api.'):
+        def reverse_enumerate(l):
+            return zip(reversed(zip(*enumerate(l))[0]), l)
+
+        for rcnt, api_path in reverse_enumerate(('', 'api.')):
             video = self._download_json(
                 'https://%sbeeg.com/api/v6/%s/video/%s'
                 % (api_path, beeg_version, video_id), video_id,
-                fatal=api_path == 'api.', query=query)
+                fatal=(rcnt == 0), query=query)
             if video:
                 break
 
@@ -114,3 +132,50 @@ class BeegIE(InfoExtractor):
             'formats': formats,
             'age_limit': self._rta_search(webpage),
         }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        formats = []
+        # leading 0s stripped from ID by site, though full ID also works
+        video = self._download_json(
+            'https://store.externulls.com/facts/file/%d' % int(video_id),
+            video_id, fatal=False)
+        if video:
+            video_data = try_get(video, lambda x: x['file'], dict) or {}
+            video_data.update(video_data.get('stuff', {}))
+            video_data.update(try_get(video, lambda x: x['fc_facts'][0], dict))
+            for format_id, key in try_get(video_data, lambda x: iter(x['resources'].items())) or []:
+                if not format_id:
+                    continue
+                formats.append({
+                    'url': urljoin('https://video.beeg.com', key),
+                    'format_id': format_id,
+                    'height': int_or_none(format_id.rsplit('_', 1)[-1]),
+                })
+            if formats:
+                self._sort_formats(formats)
+                title = video_data.get('sf_name') or 'Beeg video %s' % video_id
+                tags = try_get(video_data, lambda v: [tag['tg_slug'] for tag in v['tags'] if tag.get('tg_slug')])
+                result = {
+                    'id': video_id,
+                    'title': video_data.get('sf_name') or 'Beeg video %s' % video_id,
+                    'description': video_data.get('sf_story', title),
+                    'timestamp': parse_iso8601(video_data.get('fc_created')),
+                    'duration': int_or_none(dict_get(video_data, ('fl_duration', 'sf_duration'))),
+                    'tags': tags,
+                    'formats': formats,
+                    'age_limit': self._rta_search(webpage),
+                    'height': int_or_none(video_data.get('fl_height')),
+                    'width': int_or_none(video_data.get('fl_width')),
+                }
+                set_id = video_data['resources'].get('set_id')
+                thumb_id = try_get(video_data, lambda x: x['fc_facts'][0]['fc_thumbs'][0], int)
+                if set_id and thumb_id:
+                    result['thumbnail'] = (
+                        'https://thumbs-015.externulls.com/sets/%s/thumbs/%s-%0.4d.jpg' % (set_id, set_id, thumb_id))
+                return result
+
+        return self._old_real_extract(url, video_id, webpage)