letterboxd-watchlist

What This Skill Does

The letterboxd-watchlist skill is a specialized agentic tool designed to extract film data from public Letterboxd watchlists without requiring user authentication. It functions by programmatically navigating the paginated HTML structures of a user's watchlist, parsing the relevant film titles and their corresponding Letterboxd URLs. The skill supports exporting this data into either CSV or JSONL formats, making it an excellent utility for users who want to transition their watchlists into database entries, personal spreadsheets, or custom recommendation engines. By leveraging a robust scraping script with configurable delays, retries, and timeouts, it balances efficiency with server politeness.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal:

clawhub install openclaw/skills/skills/0xnuminous/letterboxd-watchlist

Ensure that you have uv installed in your environment, as it is required to execute the underlying Python scripts effectively. After installation, the skill becomes available as a callable tool for your AI agent.

Use Cases

• Personal Data Archiving: Save your Letterboxd history to a local file for permanent backup or offline viewing.
• Recommendation Engineering: Feed the JSONL output into custom machine learning models or filtering scripts to build a 'watch-next' queue based on your preferences.
• Cross-Platform Migration: Export your watchlist to a CSV format to easily import it into other movie-tracking services like Trakt, IMDb, or Notion databases.
• Content Curation: Quickly gather a list of URLs for a newsletter or blog post focused on curated film recommendations.

Example Prompts

1. "Hey OpenClaw, please scrape my Letterboxd watchlist (my username is 'cinephile99') and save the output to watchlist.csv."
2. "Can you help me export my Letterboxd watchlist to a JSONL file? The username is 'movie_buff_88'. Use the robust scraping settings to ensure it completes without errors."
3. "I need to get a list of all films on my public Letterboxd account 'retro_films'. Please save the titles and links into a file so I can import them into Excel."

Tips & Limitations

• Public Access Only: This skill can only access publicly visible watchlists. If a profile is set to private, the scraper will not function.
• Robustness: Always prefer the 'Robust Mode' command (using --delay-ms and --retries) when scraping larger watchlists to prevent rate-limiting or transient connection issues.
• Markup Dependency: This is a best-effort HTML scraper. If Letterboxd updates their website’s CSS classes or DOM structure, the regex in the script may need adjustment by the user or via a library update.
• Accuracy: Ensure the username provided is exactly as it appears on the platform, as partial matches or incorrect casing may lead to request failures. The script validates format, but existence of the user profile is strictly bound to the target server's response.