From 80e311a07ed9a1c0ffd0b7c394bc0f04c8a41f22 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Mon, 22 Jul 2024 14:03:16 +0200
Subject: [PATCH] Fix Docs plaintext link scan (#14583)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Ultralytics Assistant <135830346+UltralyticsAssistant@users.noreply.github.com>
---
 .github/workflows/links.yml    | 2 ++
 docs/build_docs.py             | 6 +++++-
 ultralytics/utils/downloads.py | 2 +-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/links.yml b/.github/workflows/links.yml
index 73542b3a..216250fb 100644
--- a/.github/workflows/links.yml
+++ b/.github/workflows/links.yml
@@ -52,6 +52,7 @@ jobs:
             --exclude-path docs/hi \
             --exclude-path docs/ar \
             --github-token ${{ secrets.GITHUB_TOKEN }} \
+            --header "User-Agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \
             './**/*.md' \
             './**/*.html'
 
@@ -82,6 +83,7 @@ jobs:
             --exclude-path docs/hi \
             --exclude-path docs/ar \
             --github-token ${{ secrets.GITHUB_TOKEN }} \
+            --header "User-Agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.6478.183 Safari/537.36" \
             './**/*.md' \
             './**/*.html' \
             './**/*.yml' \
diff --git a/docs/build_docs.py b/docs/build_docs.py
index 67ec5bd1..a6fd39b0 100644
--- a/docs/build_docs.py
+++ b/docs/build_docs.py
@@ -192,7 +192,11 @@ def convert_plaintext_links_to_html(content):
     for paragraph in main_content.find_all(["p", "li"]):  # Focus on paragraphs and list items
         for text_node in paragraph.find_all(string=True, recursive=False):
             if text_node.parent.name not in {"a", "code"}:  # Ignore links and code blocks
-                new_text = re.sub(r"(https?://\S+?)(?=[,.!?;:]?\s|[,.!?;:]?$)", r'<a href="\1">\1</a>', str(text_node))
+                new_text = re.sub(
+                    r'(https?://[^\s\'")]+)(?=[,.!?;:]?(?:\s|$)|[\'")])',
+                    r'<a href="\1">\1</a>',
+                    str(text_node),
+                )
                 if "<a" in new_text:
                     new_soup = BeautifulSoup(new_text, "html.parser")
                     text_node.replace_with(new_soup)
diff --git a/ultralytics/utils/downloads.py b/ultralytics/utils/downloads.py
index f2cd5e58..bc9ac2cb 100644
--- a/ultralytics/utils/downloads.py
+++ b/ultralytics/utils/downloads.py
@@ -199,7 +199,7 @@ def check_disk_space(url="https://ultralytics.com/assets/coco8.zip", path=Path.c
     Check if there is sufficient disk space to download and store a file.
 
     Args:
-        url (str, optional): The URL to the file. Defaults to 'https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8.zip'.
+        url (str, optional): The URL to the file. Defaults to 'https://ultralytics.com/assets/coco8.zip'.
         path (str | Path, optional): The path or drive to check the available free space on.
         sf (float, optional): Safety factor, the multiplier for the required free space. Defaults to 2.0.
         hard (bool, optional): Whether to throw an error or not on insufficient disk space. Defaults to True.