feat: Add DOI-specific headers for link validation

cms/djangoapps/contentstore/tasks.py

@@ -12,6 +12,7 @@
 from datetime import datetime, timezone
 from importlib.metadata import entry_points
 from tempfile import NamedTemporaryFile, mkdtemp
+from urllib.parse import urlparse
 
 import aiohttp
 import olxcleaner
@@ -56,16 +57,16 @@
 from cms.djangoapps.contentstore.utils import (
     IMPORTABLE_FILE_TYPES,
     contains_previous_course_reference,
-    get_previous_run_course_key,
+    create_course_info_usage_key,
     create_or_update_xblock_upstream_link,
     delete_course,
+    get_previous_run_course_key,
     initialize_permissions,
     reverse_usage_url,
     translation_language
 )
 from cms.djangoapps.contentstore.xblock_storage_handlers.view_handlers import get_block_info
 from cms.djangoapps.models.settings.course_metadata import CourseMetadata
-from cms.djangoapps.contentstore.utils import create_course_info_usage_key
 from common.djangoapps.course_action_state.models import CourseRerunState
 from common.djangoapps.static_replace import replace_static_urls
 from common.djangoapps.student.auth import has_course_author_access
@@ -116,6 +117,18 @@
     "Connection": "keep-alive",
 }
 
+# DOI-specific headers
+DOI_HEADERS = {
+    "User-Agent": DEFAULT_HEADERS["User-Agent"],
+    "Accept": "application/vnd.citationstyles.csl+json",
+    "Connection": "keep-alive",
+}
+
+# Domain-specific header mapping
+DOMAIN_HEADERS = {
+    "doi.org": DOI_HEADERS,
+}
+
 
 class LinkState:
     """
@@ -1434,7 +1447,7 @@ async def _validate_urls_access_in_batches(url_list, course_key, batch_size=100)
 
 async def _validate_batch(batch, course_key):
     """Validate a batch of URLs"""
-    async with aiohttp.ClientSession(headers=DEFAULT_HEADERS) as session:
+    async with aiohttp.ClientSession() as session:
         tasks = [_validate_url_access(session, url_data, course_key) for url_data in batch]
         batch_results = await asyncio.gather(*tasks)
         return batch_results
@@ -1462,8 +1475,17 @@ async def _validate_url_access(session, url_data, course_key):
     url = url.strip()  # Trim leading/trailing whitespace
     result = {'block_id': block_id, 'url': url}
     standardized_url = _convert_to_standard_url(url, course_key)
+
+    try:
+        parsed = urlparse(url)
+        domain = parsed.netloc.lower()
+        headers = DOMAIN_HEADERS.get(domain, DEFAULT_HEADERS)
+    except Exception as e:  # lint-amnesty, pylint: disable=broad-except
+        LOGGER.debug(f'[Link Check] Error parsing URL {url}: {str(e)}')
+        headers = DEFAULT_HEADERS
+
     try:
-        async with session.get(standardized_url, timeout=5) as response:
+        async with session.get(standardized_url, headers=headers, timeout=5) as response:
             result.update({'status': response.status})
     except Exception as e:  # lint-amnesty, pylint: disable=broad-except
         result.update({'status': None})