[gfycat] Support embeds (#2229)

Closes #2214
Authored by: coletdjnz

yt_dlp/extractor/generic.py

@@ -137,6 +137,7 @@
 from .wimtv import WimTVIE
 from .tvp import TVPEmbedIE
 from .blogger import BloggerIE
+from .gfycat import GfycatIE
 
 
 class GenericIE(InfoExtractor):
@@ -2382,6 +2383,33 @@ class GenericIE(InfoExtractor):
                 'timestamp': 1636788683.0,
                 'upload_date': '20211113'
             }
+        },
+        {
+            # Multiple gfycat iframe embeds
+            'url': 'https://www.gezip.net/bbs/board.php?bo_table=entertaine&wr_id=613422',
+            'info_dict': {
+                'title': '재이, 윤, 세은 황금 드레스를 입고 빛난다',
+                'id': 'board'
+            },
+            'playlist_count': 8,
+        },
+        {
+            # Multiple gfycat gifs (direct links)
+            'url': 'https://www.gezip.net/bbs/board.php?bo_table=entertaine&wr_id=612199',
+            'info_dict': {
+                'title': '옳게 된 크롭 니트 스테이씨 아이사',
+                'id': 'board'
+            },
+            'playlist_count': 6
+        },
+        {
+            # Multiple gfycat embeds, with uppercase "IFR" in urls
+            'url': 'https://kkzz.kr/?vid=2295',
+            'info_dict': {
+                'title': '지방시 앰버서더 에스파 카리나 움짤',
+                'id': '?vid=2295'
+            },
+            'playlist_count': 9
         }
         #
     ]
@@ -3572,6 +3600,10 @@ def _real_extract(self, url):
         if tvp_urls:
             return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key())
 
+        # Look for Gfycat Embeds
+        gfycat_urls = GfycatIE._extract_urls(webpage)
+        if gfycat_urls:
+            return self.playlist_from_matches(gfycat_urls, video_id, video_title, ie=GfycatIE.ie_key())
         # Look for HTML5 media
         entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
         if entries:

yt_dlp/extractor/gfycat.py

@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     int_or_none,
@@ -11,7 +13,7 @@
 
 
 class GfycatIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\.]+)'
+    _VALID_URL = r'(?i)https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\."\']+)'
     _TESTS = [{
         'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
         'info_dict': {
@@ -78,8 +80,19 @@ class GfycatIE(InfoExtractor):
     }, {
         'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
         'only_matching': True
+    }, {
+        'url': 'http://gfycat.com/IFR/JauntyTimelyAmazontreeboa',
+        'only_matching': True
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<(?:iframe|source)[^>]+\bsrc=["\'](?P<url>%s)' % GfycatIE._VALID_URL,
+                webpage)]
+
     def _real_extract(self, url):
         video_id = self._match_id(url)