jbrechtel
ed70f6e3c2
Downloaded recipe images from source URLs (NYT Cooking, Love & Lemons, Food Network, etc.) via og:image scraping and DuckDuckGo search + page scraping for recipes without direct source URLs.
27 lines
774 B
Bash
Executable File
27 lines
774 B
Bash
Executable File
#!/usr/bin/env bash
|
|
set -euo pipefail
|
|
|
|
slug="$1"
|
|
url="$2"
|
|
|
|
echo "[$slug] Fetching $url" >&2
|
|
html=$(curl -sL --max-time 15 "$url" 2>/dev/null) || { echo "[$slug] FETCH FAILED" >&2; echo ""; exit 0; }
|
|
|
|
# Try multiple og:image patterns
|
|
img_url=$(echo "$html" | grep -oP 'property="og:image"\s+content="[^"]*"' | sed 's/.*content="//;s/"//' | head -1)
|
|
|
|
if [ -z "$img_url" ]; then
|
|
img_url=$(echo "$html" | grep -oP 'name="og:image"\s+content="[^"]*"' | sed 's/.*content="//;s/"//' | head -1)
|
|
fi
|
|
|
|
if [ -z "$img_url" ]; then
|
|
img_url=$(echo "$html" | grep -oP 'content="[^"]*"[^>]*property="og:image"' | sed 's/.*content="//;s/".*//' | head -1)
|
|
fi
|
|
|
|
if [ -n "$img_url" ]; then
|
|
echo "[$slug] Found: $img_url" >&2
|
|
echo "$img_url"
|
|
else
|
|
echo "[$slug] No og:image found" >&2
|
|
fi
|