added scripts to get abstract and bibliography easily from papers

1 files changed, 42 insertions, 0 deletions

diff --git a/scripts/extract_abstract b/scripts/extract_abstract
new file mode 100755
index 0000000..e70b3cb
--- /dev/null
+++ b/scripts/extract_abstract
@@ -0,0 +1,42 @@
+#!/bin/bash
+
+# Directory containing the papers
+PAPER_DIR="../papers"
+
+echo "Fetching abstracts for arXiv papers in $PAPER_DIR..."
+echo "===================================================="
+
+for file in "$PAPER_DIR"/*.pdf; do
+    # Extract the arXiv ID (e.g., 2401.05566) from the filename
+    filename=$(basename "$file")
+    id=$(echo "$filename" | grep -oE '[0-9]{4}\.[0-9]{4,5}')
+
+    if [ -n "$id" ]; then
+        echo "FILE: $filename"
+        echo "ID:   $id"
+
+        # Fetch XML from arXiv API and parse the <summary> tag using Python
+        curl -s "https://export.arxiv.org/api/query?id_list=$id" | \
+        python3 -c "
+import sys, xml.etree.ElementTree as ET
+try:
+    xml_data = sys.stdin.read()
+    root = ET.fromstring(xml_data)
+    ns = {'atom': 'http://www.w3.org/2005/Atom'}
+    summary = root.find('.//atom:summary', ns)
+    if summary is not None:
+        print(summary.text.strip())
+    else:
+        print('Abstract not found in API response.')
+except Exception as e:
+    print(f'Error parsing response: {e}')
+"
+        echo "----------------------------------------------------"
+    else
+        echo "Skipping: $filename (No arXiv ID detected)"
+        echo "----------------------------------------------------"
+    fi
+    sleep 1
+done
+
+