feat: add browser-based torrent download and package-only Scrapling usage

scrape_happyfappy_bookmarks.py

@@ -5,21 +5,12 @@ import argparse
 import json
 import random
 import re
-import sys
 import time
 from pathlib import Path
 from typing import Any
 from urllib.parse import urlparse
 
-try:
-    from scrapling.fetchers import DynamicSession
-except ModuleNotFoundError:
-    local_repo = Path(__file__).resolve().parent / "Scrapling"
-    if local_repo.exists():
-        sys.path.insert(0, str(local_repo))
-        from scrapling.fetchers import DynamicSession
-    else:
-        raise
+from scrapling.fetchers import DynamicSession
 
 STOP_TEXT = "You have not bookmarked any torrents."
 BG_URL_RE = re.compile(r"url\((?:'|\")?(.*?)(?:'|\")?\)")
@@ -122,11 +113,13 @@ def extract_background_image(style: str) -> str | None:
     return value or None
 
 
-def extract_torrent_cards(response: Any) -> list[dict[str, Any]]:
+def extract_torrent_cards(response: Any, base_url: str) -> list[dict[str, Any]]:
     records: list[dict[str, Any]] = []
     cards = response.css("div.torrent_grid div.torrent_grid__torrent")
     for card in cards:
         page_url = (card.css('a[href^="/torrents.php?id="]::attr(href)').get("") or "").strip()
+        if page_url and not page_url.startswith("http"):
+            page_url = f"{base_url.rstrip('/')}{page_url}"
         category = (card.css("span.torrent_grid__torrent__cat::text").get("") or "").strip()
         title = (
             card.css("h3.trim::attr(title)").get("")
@@ -220,7 +213,7 @@ def run(args: argparse.Namespace) -> None:
             if should_stop(response):
                 break
 
-            page_records = extract_torrent_cards(response)
+            page_records = extract_torrent_cards(response, args.base_url)
             all_records.extend(page_records)
             print(f"[page={page}] extracted={len(page_records)} total={len(all_records)}")
             page += 1