generate_results

src.scrapers.generate_results

Generate artifact-evaluation results.md files for sysartifacts and secartifacts sites.

This is the unified entry point for generating results pages for both

• sysartifacts.github.io (USENIX systems conferences: FAST, OSDI, ATC, NSDI)
• secartifacts.github.io (security conferences: USENIX Security, ACSAC)

The --target flag selects the output format (badge images, Liquid template). The --conference flag selects which scraper to use.

Usage

sysartifacts: FAST 2025

python -m src.scrapers.generate_results --target sysartifacts --conference fast --years 2025

sysartifacts: OSDI 2024 with custom dir prefix

python -m src.scrapers.generate_results --target sysartifacts --conference osdi --years 2024 --dir-prefix osdi

secartifacts: ACSAC 2025

python -m src.scrapers.generate_results --target secartifacts --conference acsac --years 2025

secartifacts: USENIX Security 2025

python -m src.scrapers.generate_results --target secartifacts --conference usenixsec --years 2025

Preview without writing

python -m src.scrapers.generate_results --target secartifacts --conference acsac --years 2025 --dry-run

Requirements

pip install requests beautifulsoup4 pyyaml lxml

Output: //results.md (and organizers.md when available)

scrape_artifacts(config, year, **kwargs)

Dispatch to the appropriate scraper.

Returns list of dicts with: title, badges (list[str]), artifact_urls (list[str]), paper_url (str).

Source code in src/scrapers/generate_results.py

def scrape_artifacts(config, year, **kwargs):
    """
    Dispatch to the appropriate scraper.

    Returns list of dicts with: title, badges (list[str]), artifact_urls (list[str]), paper_url (str).
    """
    scraper = config["scraper"]

    if scraper == "acsac":
        from .acsac_scrape import scrape_acsac_artifacts

        return scrape_acsac_artifacts(year)

    # All USENIX conferences (fast, osdi, atc, nsdi, usenixsecurity)
    from .usenix_scrape import scrape_conference_year

    max_workers = kwargs.get("max_workers", 4)
    delay = kwargs.get("delay", 0.5)
    all_papers = scrape_conference_year(scraper, year, max_workers=max_workers, delay=delay)

    # Normalize to common format, keep only papers with badges
    artifacts = []
    for p in all_papers:
        if not p.get("badges"):
            continue
        artifacts.append(
            {
                "title": p["title"],
                "badges": p["badges"],
                "artifact_urls": [],
                "paper_url": p.get("paper_url", ""),
            }
        )
    return artifacts

scrape_organizers_for(config, year)

Scrape AE committee organizers if supported for this config.

Source code in src/scrapers/generate_results.py

def scrape_organizers_for(config, year):
    """Scrape AE committee organizers if supported for this config."""
    if not config.get("scrape_organizers"):
        return None
    from .usenix_scrape import scrape_organizers

    return scrape_organizers(config["scraper"], year)

generate_results_md(config, year, artifacts)

Generate a results.md string from config + scraped artifacts.

Source code in src/scrapers/generate_results.py

def generate_results_md(config, year, artifacts):
    """Generate a results.md string from config + scraped artifacts."""
    badge_cols = config["badge_columns"]
    badge_labels = config["badge_labels"]
    badges_fmt = config["badges_format"]
    include_empty = config.get("include_empty_artifact_fields", False)

    # Count badges
    counts = {b: sum(1 for a in artifacts if b in a["badges"]) for b in badge_cols}

    # Build artifact YAML entries
    yaml_artifacts = []
    for a in artifacts:
        entry = {"title": a["title"]}
        entry["badges"] = _format_badges(a["badges"], badges_fmt)

        # Artifact URLs
        if a.get("artifact_urls"):
            if len(a["artifact_urls"]) == 1:
                entry["artifact_url"] = a["artifact_urls"][0]
            else:
                entry["artifact_urls"] = a["artifact_urls"]
        elif include_empty:
            entry["artifact_url"] = ""

        if a.get("paper_url"):
            entry["paper_url"] = a["paper_url"]

        if include_empty:
            entry["appendix_url"] = ""

        yaml_artifacts.append(entry)

    # Front matter
    front = {"title": "Results"}
    front.update(config["front_matter"])
    front["artifacts"] = yaml_artifacts

    front_yaml = yaml.dump(front, default_flow_style=False, allow_unicode=True, sort_keys=False, width=120)

    # Summary
    summary = "\n".join(f"* {counts[b]} {badge_labels[b]}" for b in badge_cols)

    # Template
    template_name = config["template"]
    table = _render_template(template_name, year, badge_cols)

    return f"---\n{front_yaml.rstrip()}\n---\n\n**Evaluation Results**:\n\n{summary}\n\n{table}\n"

generate_organizers_md(organizers)

Generate organizers.md from scraped organizer data, or None.

Source code in src/scrapers/generate_results.py

def generate_organizers_md(organizers):
    """Generate organizers.md from scraped organizer data, or None."""
    if not organizers or (not organizers.get("chairs") and not organizers.get("members")):
        return None

    lines = ["---", "title: Organizers", "order: 20", "---", "", "## Artifact Evaluation Committee Co-Chairs", ""]

    for chair in organizers.get("chairs", []):
        aff = f", {chair['affiliation']}" if chair["affiliation"] else ""
        lines.append(f"{chair['name']}{aff} <br>")

    lines.extend(["", "## Artifact Evaluation Committee", ""])

    members = organizers.get("members", [])
    for i, member in enumerate(members):
        aff = f", {member['affiliation']}" if member["affiliation"] else ""
        suffix = "<br>" if i < len(members) - 1 else ""
        lines.append(f"{member['name']}{aff}{suffix}")

    return "\n".join(lines) + "\n"