#!/usr/bin/env python3
"""archive.org — EN full-text search + metadata + file lists ("English libgen").

Usage:
  tools/ia.py search "creator:(Carl Gustav Jung)" [rows]   # advancedsearch, mediatype filtered
  tools/ia.py meta <identifier>                            # /metadata/<id> — files, size, format
  tools/ia.py title "Aion"                                 # convenience: title:("...") AND mediatype:texts

Output (search): numFound + rows: identifier | title | year | downloads | restricted | mediatype.
Output (meta): item fields + list of files (name, format, size) — pick _pdf/_epub/_fb2/_djvu.

Notes:
- query syntax: Solr — creator:(...), title:(...), subject:(...), AND/OR/NOT; + = space.
- access-restricted-item=true → controlled digital lending (borrow, no direct download).
- creator: is loose (images/misattributions included) — add AND mediatype:texts in query
  (the tool appends it for search/title unless the query already has 'mediatype').
- Politeness: 2s between calls. No key needed.
"""
import json, sys, time, urllib.parse, urllib.request

UA = "Mozilla/5.0 (research; contact: dmitry@kokorin.org)"

def fetch(url, tries=3):
    last = None
    for i in range(tries):
        try:
            req = urllib.request.Request(url, headers={"User-Agent": UA})
            return urllib.request.urlopen(req, timeout=60).read().decode("utf-8", "replace")
        except Exception as e:
            last = e
            time.sleep(3 + 3 * i)
    raise SystemExit(f"fetch failed: {last}")

FL = "identifier,title,year,downloads,access-restricted-item,mediatype"

def main():
    if len(sys.argv) < 3:
        sys.exit(__doc__)
    cmd, q = sys.argv[1], sys.argv[2]
    if cmd == "search":
        rows = int(sys.argv[3]) if len(sys.argv) > 3 else 20
        if "mediatype" not in q:
            q = q + " AND mediatype:texts"
        url = "https://archive.org/advancedsearch.php?" + urllib.parse.urlencode(
            {"q": q, "output": "json", "rows": rows, "fl[]": FL})
        d = json.loads(fetch(url))
        print("numFound:", d.get("response", {}).get("numFound"))
        for x in d.get("response", {}).get("docs", []):
            r = x.get("access-restricted-item", "")
            print(f"  {x.get('identifier')[:60]:60s} {x.get('year') or '?':>5} "
                  f"dl={x.get('downloads', 0):>7} {'RESTRICTED' if r == 'true' else 'open':10s} {x.get('title', '')[:60]}")
    elif cmd == "title":
        q = f'title:("{q}")'
        rows = 20
        if "mediatype" not in q:
            q = q + " AND mediatype:texts"
        url = "https://archive.org/advancedsearch.php?" + urllib.parse.urlencode(
            {"q": q, "output": "json", "rows": rows, "fl[]": FL})
        d = json.loads(fetch(url))
        print("numFound:", d.get("response", {}).get("numFound"))
        for x in d.get("response", {}).get("docs", []):
            r = x.get("access-restricted-item", "")
            print(f"  {x.get('identifier')[:60]:60s} {x.get('year') or '?':>5} "
                  f"dl={x.get('downloads', 0):>7} {'RESTRICTED' if r == 'true' else 'open':10s} {x.get('title', '')[:60]}")
    elif cmd == "meta":
        d = json.loads(fetch(f"https://archive.org/metadata/{q}"))
        meta = d.get("metadata", {})
        print("title:", meta.get("title"), "| creator:", meta.get("creator"), "| year:", meta.get("year"))
        print("restricted:", d.get("is_access_restricted"))
        for f in d.get("files", []):
            n, fmt, size = f.get("name"), f.get("format"), f.get("size", "?")
            if fmt in ("Text PDF", "EPUB", "FB3", "DJVU", "Full Text OCR", "Mobi", "DAISY") or "pdf" in str(fmt):
                print(f"  {n[:70]:70s} {fmt:15s} {size}")
    else:
        sys.exit("cmd: search|title|meta")

if __name__ == "__main__":
    main()