From f7a7601f27951db481cd23c3bc8491d6bf86524b Mon Sep 17 00:00:00 2001
From: Alexander Gedeon <agedeon@umich.edu>
Date: Thu, 22 Apr 2021 15:13:12 -0400
Subject: [PATCH] [webarchive] Added new extractor for the web archive (closes
 #13655)

---
 youtube_dl/extractor/extractors.py |  1 +
 youtube_dl/extractor/webarchive.py | 54 ++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)
 create mode 100644 youtube_dl/extractor/webarchive.py

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index ac33cd996..062cc1f4a 100644
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -1520,6 +1520,7 @@ from .wdr import (
     WDRElefantIE,
     WDRMobileIE,
 )
+from .webarchive import WebArchiveIE
 from .webcaster import (
     WebcasterIE,
     WebcasterFeedIE,
diff --git a/youtube_dl/extractor/webarchive.py b/youtube_dl/extractor/webarchive.py
new file mode 100644
index 000000000..4e1bca7ca
--- /dev/null
+++ b/youtube_dl/extractor/webarchive.py
@@ -0,0 +1,54 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class WebArchiveIE(InfoExtractor):
+    _VALID_URL = r'https?:\/\/(?:www\.)?web\.archive\.org\/web\/([0-9]+)\/https?:\/\/(?:www\.)?youtube\.com\/watch\?v=(?P<id>[0-9A-Za-z_-]{1,11})$'
+    _TEST = {
+        'url': 'https://web.archive.org/web/20150415002341/https://www.youtube.com/watch?v=aYAGB11YrSs',
+        'md5': 'ec44dc1177ae37189a8606d4ca1113ae',
+        'info_dict': {
+            'url': 'https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/aYAGB11YrSs',
+            'id': 'aYAGB11YrSs',
+            'ext': 'mp4',
+            'title': 'Team Fortress 2 - Sandviches!',
+            'author': 'Zeurel',
+        }
+    }
+
+    def _real_extract(self, url):
+        # Get video ID and page
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        # Extract title and author
+        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title').strip()
+        author = self._html_search_regex(r'"author":"([a-zA-Z0-9]+)"', webpage, 'author').strip()
+
+        # Parse title
+        if title.endswith(' - YouTube'):
+            title = title[:-10]
+
+        # Use link translator mentioned in https://github.com/ytdl-org/youtube-dl/issues/13655
+        link_stub = "https://web.archive.org/web/2oe_/http://wayback-fakeurl.archive.org/yt/"
+
+        # Extract hash from url
+        hash_idx = url.find("watch?v=") + len("watch?v=")
+        youtube_hash = url[hash_idx:]
+
+        # If there's an ampersand, cut off before it
+        ampersand = youtube_hash.find('&')
+        if ampersand != -1:
+            youtube_hash = youtube_hash[:ampersand]
+
+        # Recreate the fixed pattern url and return
+        reconstructed_url = link_stub + youtube_hash
+        return {
+            'url': reconstructed_url,
+            'id': video_id,
+            'title': title,
+            'author': author,
+            'ext': "mp4"
+        }