#!/usr/bin/env python3
"""Search libgen.vg (Library Genesis). Usage: lg.sh "query" [limit]
Polite mode: one request per query."""
import sys, time, urllib.parse, urllib.request, re

UA = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"

def fetch(url, tries=3):
    last = None
    for i in range(tries):
        try:
            req = urllib.request.Request(url, headers={"User-Agent": UA, "Accept-Language": "ru-RU,ru;q=0.9"})
            return urllib.request.urlopen(req, timeout=90).read().decode("utf-8", "replace")
        except Exception as e:
            last = e
            time.sleep(5 + 5 * i)
    raise SystemExit(f"fetch failed after {tries} tries: {last}")

def main():
    q = sys.argv[1]
    limit = int(sys.argv[2]) if len(sys.argv) > 2 else 10
    url = "https://libgen.vg/index.php?" + urllib.parse.urlencode({
        "req": q, "res": "100", "dlt": "0", "ln": "0",
        "columns[]": ["t","a","s","y","p","i","l","x","sz"]
    })
    html = fetch(url)
    # pagination hint
    m = re.search(r'page=(\d+)', html)
    if m and int(m.group(1)) > 1:
        print(f"[more pages available, max page {m.group(1)} — rerun with &page=N]")
    # parse result rows
    rows = re.findall(r"<tr[^>]*>\s*<td[^>]*>.*?</tr>", html, re.S)
    count = 0
    for r in rows:
        tds = re.findall(r"<td[^>]*>(.*?)</td>", r, re.S)
        tds = [re.sub(r"<[^>]+>", "", t).replace("&amp;","&").strip() for t in tds]
        tds = [re.sub(r"\s+", " ", t) for t in tds]
        if len(tds) < 6:
            continue
        # first cell is usually a link with id, title is the big cell
        title = max(tds, key=len) if tds else ""
        line = " | ".join(tds[:9])
        print(line[:300])
        count += 1
        if count >= limit:
            break
    if count == 0:
        # maybe "No results" or error page
        m = re.search(r"No results|Ничего не найдено|Error[^<]*", html)
        print("(no results)" if m else "(unparsed — check manually)")
        print(html[:500].replace("\n", " "))

if __name__ == "__main__":
    main()