#!/usr/bin/env python3
"""Parse GitHub Trending page via curl + regex.

Use this when browser_navigate to GitHub trending fails (CDP timeout).
Write to /tmp/parse_trending.py, then run: python3 /tmp/parse_trending.py

Usage:
    python3 /tmp/parse_trending.py                    # daily trending (default)
    python3 /tmp/parse_trending.py weekly             # this week
    python3 /tmp/parse_trending.py monthly            # this month

Output: JSON array of repo objects.
"""

import subprocess, re, json, sys

since = sys.argv[1] if len(sys.argv) > 1 else "daily"
url = f"https://github.com/trending?since={since}"

result = subprocess.run(['curl', '-s', url], capture_output=True, text=True)
html = result.stdout

# Find all article elements (each is a trending repo card)
articles = re.findall(r'<article[^>]*>(.*?)</article>', html, re.DOTALL)

results = []
for art in articles:
    # Extract repo name from h2 > a href=\"/owner/repo\"
    # ⚠️ The FIRST <a> in <h2> is often a /sponsors/ or /login? link, NOT the repo.
    # Skip any href starting with "sponsors/" or "login?".
    h2_section = re.search(r'<h2[^>]*>(.*?)</h2>', art, re.DOTALL)
    if h2_section:
        repo_hrefs = re.findall(r'href=\"/[^\"#]+/[^\"]+\"', h2_section.group(1))
        # Pick the first href that is NOT a sponsors or login link
        name = ''
        for href in repo_hrefs:
            href_val = href.split('"')[1]  # extract value from href="..."
            if not href_val.startswith('/sponsors/') and not href_val.startswith('/login?'):
                name = href_val.lstrip('/')
                break
    else:
        # Fallback: scan the whole article
        all_hrefs = re.findall(r'href=\"/[^\"#]+/[^\"]+\"', art)
        for href in all_hrefs:
            href_val = href.split('"')[1]
            if not href_val.startswith('/sponsors/') and not href_val.startswith('/login?'):
                name = href_val.lstrip('/')
                break
        else:
            name = ''

    # Extract description from <p class="col-9...>
    desc_match = re.search(r'<p class=\"col-9[^>]*>(.*?)</p>', art, re.DOTALL)
    desc = desc_match.group(1).strip() if desc_match else ''

    # Extract total stars from stargazers link
    stars_match = re.search(r'href=\"[^\"]*stargazers\"[^>]*>\s*(.*?)\s*</a>', art, re.DOTALL)
    stars = ''
    if stars_match:
        s = stars_match.group(1).strip()
        s = re.sub(r'[,\s]', '', s)
        stars = s

    # Extract language (known languages only)
    lang_match = re.search(
        r'<span[^>]*>(TypeScript|Python|JavaScript|Rust|Go|C\+\+|Java|Kotlin|Swift|Ruby|PHP|Shell|HTML|CSS|Jupyter Notebook)</span>',
        art
    )
    lang = lang_match.group(1) if lang_match else ''

    # Extract stars today / this week / this month
    stars_period = ''
    for span in re.finditer(r'<span[^>]*>(.*?)</span>', art, re.DOTALL):
        t = span.group(1).strip()
        if 'stars today' in t or 'stars this week' in t or 'stars this month' in t:
            stars_period = t

    if name:
        results.append({
            'name': name,
            'desc': desc,
            'stars': stars,
            'lang': lang,
            'starsPeriod': stars_period,
        })

print(json.dumps(results, ensure_ascii=False, indent=2))