initial commit

.gitignore

@@ -0,0 +1,10 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

.python-version

@@ -0,0 +1 @@
+3.14

main.py

@@ -0,0 +1,298 @@
+# /// script
+# requires-python = ">=3.12"
+# dependencies = [
+#     "requests",
+#     "beautifulsoup4",
+# ]
+# ///
+"""
+Generic scraper. Saves all files flat in ./scraped_<domain>/ with sanitized filenames.
+Writes structured error log to ./scraped_<domain>/scrape_errors.jsonl.
+
+Usage:
+    uv run scraper.py https://www.logting.fo
+    uv run scraper.py https://taks.fo
+"""
+
+import hashlib
+import json
+import sys
+import time
+from collections import deque
+from datetime import datetime, timezone
+from pathlib import Path
+from urllib.parse import urljoin, urlparse
+
+import requests
+from bs4 import BeautifulSoup
+
+DELAY = 0.1
+TIMEOUT = 60
+MAX_RETRIES = 3
+RETRY_BACKOFF = 5.0
+USER_AGENT = "web-scraper/1.0 (research)"
+
+CONTENT_TYPE_EXT = {
+    "text/html": ".html",
+    "application/pdf": ".pdf",
+    "application/json": ".json",
+    "application/xml": ".xml",
+    "text/xml": ".xml",
+    "text/plain": ".txt",
+    "text/css": ".css",
+    "application/javascript": ".js",
+    "text/javascript": ".js",
+    "image/png": ".png",
+    "image/jpeg": ".jpg",
+    "image/gif": ".gif",
+    "image/svg+xml": ".svg",
+    "image/webp": ".webp",
+    "application/vnd.ms-excel": ".xls",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+    "application/msword": ".doc",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
+    "application/zip": ".zip",
+    "application/octet-stream": ".bin",
+}
+
+SEEN: set[str] = set()
+
+
+def log_error(
+    log_path: Path,
+    url: str,
+    error_type: str,
+    message: str,
+    status_code: int | None = None,
+) -> None:
+    entry = {
+        "timestamp": datetime.now(timezone.utc).isoformat(),
+        "url": url,
+        "error_type": error_type,
+        "message": message,
+        "status_code": status_code,
+    }
+    with open(log_path, "a", encoding="utf-8") as f:
+        f.write(json.dumps(entry, ensure_ascii=False) + "\n")
+    print(f"  LOGGED ERROR [{error_type}]: {message}")
+
+
+def derive_base_domain(url: str) -> str:
+    parsed = urlparse(url)
+    hostname = parsed.hostname
+    if not hostname:
+        print(f"Could not parse hostname from {url}")
+        sys.exit(1)
+    parts = hostname.split(".")
+    if len(parts) >= 2:
+        return ".".join(parts[-2:])
+    return hostname
+
+
+def is_internal(url: str, base_domain: str) -> bool:
+    parsed = urlparse(url)
+    hostname = parsed.hostname
+    if not hostname:
+        return False
+    return hostname == base_domain or hostname.endswith(f".{base_domain}")
+
+
+def normalize_url(url: str) -> str:
+    url = url.split("#")[0].rstrip("?&")
+    parsed = urlparse(url)
+    scheme = parsed.scheme.lower()
+    netloc = parsed.netloc.lower()
+    path = parsed.path
+    query = parsed.query
+    if query:
+        return f"{scheme}://{netloc}{path}?{query}"
+    return f"{scheme}://{netloc}{path}"
+
+
+def get_extension(url: str, content_type: str) -> str:
+    path_suffix = Path(urlparse(url).path).suffix.lower()
+    if path_suffix:
+        return path_suffix
+
+    ct = content_type.lower().split(";")[0].strip()
+    if ct in CONTENT_TYPE_EXT:
+        return CONTENT_TYPE_EXT[ct]
+
+    return ".bin"
+
+
+def url_to_filename(url: str, content_type: str = "") -> str:
+    parsed = urlparse(url)
+
+    if len(url) > 200:
+        hash_part = hashlib.sha256(url.encode()).hexdigest()[:16]
+        ext = get_extension(url, content_type)
+        return f"{hash_part}{ext}"
+
+    host_prefix = parsed.netloc.replace(".", "_").replace(":", "_")
+    path = parsed.path.lstrip("/") or "index"
+
+    # Split extension from path so query hash goes before it
+    path_obj = Path(path)
+    stem = path_obj.stem
+    ext = path_obj.suffix.lower()
+    if not ext:
+        ext = get_extension(url, content_type)
+
+    query_suffix = ""
+    if parsed.query:
+        query_hash = hashlib.md5(parsed.query.encode()).hexdigest()[:8]
+        query_suffix = f"_{query_hash}"
+
+    filename = f"{host_prefix}_{stem}{query_suffix}{ext}"
+    filename = "".join(c if c.isalnum() or c in "._-" else "_" for c in filename)
+
+    return filename
+
+
+def save(output_dir: Path, url: str, content: bytes, content_type: str = "") -> None:
+    filename = url_to_filename(url, content_type)
+    filepath = output_dir / filename
+    filepath.write_bytes(content)
+    print(f"  saved -> {filepath.name}")
+
+
+def extract_links(base_url: str, html: str, base_domain: str) -> set[str]:
+    soup = BeautifulSoup(html, "html.parser")
+    links: set[str] = set()
+
+    for tag in soup.find_all("a", href=True):
+        href = tag["href"].strip()
+        if not href or href.startswith(("mailto:", "tel:", "javascript:")):
+            continue
+        full_url = urljoin(base_url, href)
+        full_url = normalize_url(full_url)
+        if is_internal(full_url, base_domain):
+            links.add(full_url)
+
+    return links
+
+
+def fetch(url: str, log_path: Path) -> requests.Response | None:
+    for attempt in range(1, MAX_RETRIES + 1):
+        try:
+            return requests.get(
+                url,
+                timeout=TIMEOUT,
+                headers={"User-Agent": USER_AGENT},
+                allow_redirects=True,
+            )
+        except requests.Timeout:
+            if attempt < MAX_RETRIES:
+                wait = RETRY_BACKOFF * attempt
+                print(f"  timeout, retry {attempt}/{MAX_RETRIES} in {wait}s...")
+                time.sleep(wait)
+            else:
+                log_error(
+                    log_path,
+                    url,
+                    "timeout",
+                    f"Timed out after {MAX_RETRIES} retries ({TIMEOUT}s each)",
+                )
+                return None
+        except requests.ConnectionError as e:
+            if attempt < MAX_RETRIES:
+                wait = RETRY_BACKOFF * attempt
+                print(
+                    f"  connection error, retry {attempt}/{MAX_RETRIES} in {wait}s..."
+                )
+                time.sleep(wait)
+            else:
+                log_error(log_path, url, "connection_error", str(e))
+                return None
+        except requests.RequestException as e:
+            log_error(log_path, url, "request_error", str(e))
+            return None
+    return None
+
+
+def main() -> None:
+    if len(sys.argv) < 2:
+        print("Usage: uv run scraper.py <start-url>")
+        print("Example: uv run scraper.py https://www.logting.fo")
+        sys.exit(1)
+
+    start_url = sys.argv[1]
+    base_domain = derive_base_domain(start_url)
+    output_dir = Path(f"./scraped_{base_domain.replace('.', '_')}")
+    log_dir = output_dir / "logs"
+    log_dir.mkdir(parents=True, exist_ok=True)
+    log_path = log_dir / "scrape_errors.jsonl"
+
+    output_dir.mkdir(parents=True, exist_ok=True)
+    log_path.unlink(missing_ok=True)
+
+    queue: deque[str] = deque([start_url])
+    count = 0
+    error_count = 0
+
+    print(f"Scraping: {start_url}")
+    print(f"Base domain: {base_domain}")
+    print(f"Output dir: {output_dir}")
+    print()
+
+    while queue:
+        url = normalize_url(queue.popleft())
+
+        if url in SEEN:
+            continue
+        SEEN.add(url)
+
+        print(f"[{count}] fetching: {url}")
+        resp = fetch(url, log_path)
+
+        if resp is None:
+            error_count += 1
+            time.sleep(DELAY)
+            continue
+
+        if resp.status_code != 200:
+            log_error(
+                log_path,
+                url,
+                "http_error",
+                f"HTTP {resp.status_code}",
+                resp.status_code,
+            )
+            error_count += 1
+            time.sleep(DELAY)
+            continue
+
+        final_url = normalize_url(resp.url)
+        content_type = resp.headers.get("Content-Type", "")
+
+        if "text/html" in content_type:
+            try:
+                html = resp.text
+                save(output_dir, final_url, html.encode("utf-8"), content_type)
+                links = extract_links(final_url, html, base_domain)
+                new_links = [u for u in links if u not in SEEN]
+                queue.extend(new_links)
+                print(f"  found {len(links)} links ({len(new_links)} new)")
+            except Exception as e:
+                log_error(log_path, final_url, "parse_error", str(e))
+                error_count += 1
+        else:
+            try:
+                save(output_dir, final_url, resp.content, content_type)
+                print(f"  binary: {content_type}")
+            except Exception as e:
+                log_error(log_path, final_url, "save_error", str(e))
+                error_count += 1
+
+        count += 1
+        time.sleep(DELAY)
+
+    print(
+        f"\nDone. Fetched {count} URLs ({len(SEEN)} seen total). Errors: {error_count}."
+    )
+    print(f"Error log: {log_path}")
+
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -0,0 +1,12 @@
+[project]
+name = "taks-scraper"
+version = "0.1.0"
+description = "Scrape taks.fo and subdomains for raw HTML and files"
+requires-python = ">=3.14"
+dependencies = [
+    "requests>=2.31.0",
+    "beautifulsoup4>=4.12.0",
+]
+
+[tool.uv]
+dev-dependencies = []

uv.lock

@@ -0,0 +1,129 @@
+version = 1
+revision = 3
+requires-python = ">=3.14"
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.15.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "soupsieve" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/43/65/318323f98dbee45d42dff61d8f047181bc6f2268a9068cfad035a46be5af/beautifulsoup4-4.15.0.tar.gz", hash = "sha256:288e3ca7d54b06f2ac191970bc275c1939cb46d450b255bf6718b04aa37ab4f7", size = 632571, upload-time = "2026-06-07T16:44:20.453Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/88/c6/92fcd42f1ba33e1184263f25bfabf3d27c383410470f169e4b8163bf9c17/beautifulsoup4-4.15.0-py3-none-any.whl", hash = "sha256:d6f88de62e1d4e38ecb1077eb9724cd0eff29d2a08ca16a401e9b9e93f117cf9", size = 109924, upload-time = "2026-06-07T16:44:21.566Z" },
+]
+
+[[package]]
+name = "certifi"
+version = "2026.7.22"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a3/c2/24167ea9858356b47a87a50d39908bfdb72ceeefe0041586e704e5376b3a/certifi-2026.7.22.tar.gz", hash = "sha256:741e2c3b351ddf169a738da9f2c048608ff7f2c5cc02f1ebc6b118bb090d5d55", size = 138112, upload-time = "2026-07-22T03:35:12.644Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0b/a7/71ac2cff56fec219ed242bb11b8efb69fcc4bec75db06fb7bfe35de520e6/certifi-2026.7.22-py3-none-any.whl", hash = "sha256:62f22742b58a1a33014a2b6b706588a8d7e2a88ae7bd1a6ebe8c992928483775", size = 136983, upload-time = "2026-07-22T03:35:11.276Z" },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.9"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bd/2a/23f34ec9d04624958e137efdc394888716353190e75f25dd22c7a2c7a8aa/charset_normalizer-3.4.9.tar.gz", hash = "sha256:673611bbd43f0810bec0b0f028ddeaaa501190339cac411f347ac76917c3ae7b", size = 152439, upload-time = "2026-07-07T14:34:58.454Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/8d/496817fa0944239ecae662dd57ea765cfeaec6a735f9f025d4b7b72e7143/charset_normalizer-3.4.9-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:0327fcd59a935777d83410750c50600ee9571af2846f71ce40f25b13da1ef380", size = 317253, upload-time = "2026-07-07T14:33:54.994Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/f9/ef4a69ea338ad3c0deceea0f5f7d2380ae8b52132b06d652cb0d2cd86706/charset_normalizer-3.4.9-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8a79d9f4d8001473a30c163556b3c3bfebec837495a412dde78b51672f6134f9", size = 215898, upload-time = "2026-07-07T14:33:56.334Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/e7/5ddfd76fc061eb52de219658a4aa431cbacadf0a0219c8854f00da50d289/charset_normalizer-3.4.9-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:33bdcc2a32c0a0e861f60841a512c8acc658c87c2ac59d89e3a46dacf7d866e4", size = 236718, upload-time = "2026-07-07T14:33:57.9Z" },
+    { url = "https://files.pythonhosted.org/packages/49/ba/768fa3f36048d81c477a0ce61f813bc1454d80917ccfe550abd9f44f5e24/charset_normalizer-3.4.9-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:f840ed6d8ecba8255df8c42b87fadeda98ddfc6eeec05e2dc66e26d46dd6f58a", size = 232519, upload-time = "2026-07-07T14:33:59.811Z" },
+    { url = "https://files.pythonhosted.org/packages/f4/c4/b3e049d2aa3766180c78507110543d9d50894cc97f57de543f1be521dcdc/charset_normalizer-3.4.9-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c25fe15c70c59eb7c5ce8c06a1f3fa1da0ecc5ea1e7a5922c40fd2fa9b0d5046", size = 223143, upload-time = "2026-07-07T14:34:01.517Z" },
+    { url = "https://files.pythonhosted.org/packages/19/79/55c32d06d76ae4feafe053f061f3e3ab70bcf19f4007797ce8c3efda7830/charset_normalizer-3.4.9-cp314-cp314-manylinux_2_31_armv7l.whl", hash = "sha256:f7fb7d750cfa0a070d2c24e831fd3481019a60dd317ea2b39acbcebc08b6ed81", size = 206742, upload-time = "2026-07-07T14:34:03.04Z" },
+    { url = "https://files.pythonhosted.org/packages/10/e0/47c079dd82d217c807479cd59ffd30af56307ea31c108b75758970459ad3/charset_normalizer-3.4.9-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:4d1c96a7a18b9690a4d46df09e3e3382406ae3213727cd1019ebade1c4a81917", size = 219191, upload-time = "2026-07-07T14:34:04.657Z" },
+    { url = "https://files.pythonhosted.org/packages/42/ab/b9bc2e77d6b44a7e46ef62ec5cac1c9a6ba7b9135a5d560f002696ec9995/charset_normalizer-3.4.9-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:a4cfde78a9f2880208d16a93b795726a3017d5977e08d1e162a7a31322479c41", size = 218328, upload-time = "2026-07-07T14:34:06.115Z" },
+    { url = "https://files.pythonhosted.org/packages/f1/78/c9c71d599f5aa2d42bcdd35cbbd46d7f535351a57e40ff7d8e5a7e219401/charset_normalizer-3.4.9-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:d4d6fcde76f94f5cb9e43e9e9a61f16dacefd228cbbf6f1a09bd9b219a92f1a1", size = 207406, upload-time = "2026-07-07T14:34:07.554Z" },
+    { url = "https://files.pythonhosted.org/packages/f6/39/c914445c321a845097ce4f6ac7de9a18228a77b766272125a1ce00d851eb/charset_normalizer-3.4.9-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:898f0e9068ca27d37f8e83a5b962821df851532e6c4a7d615c1c033f9da6eedf", size = 225157, upload-time = "2026-07-07T14:34:09.061Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/f2/c0d4b8508565a36bc5c624e88ed297f5b0b1095011034d7f5b83a69908b5/charset_normalizer-3.4.9-cp314-cp314-win32.whl", hash = "sha256:c1c948747b03be832dceed96ca815cef7360de9aa19d37c730f8e3f6101aca48", size = 151095, upload-time = "2026-07-07T14:34:10.901Z" },
+    { url = "https://files.pythonhosted.org/packages/49/fd/a1d26144398c67486422a72bf5812cda22cb4ccfcd95a290fb41ceb4b8e2/charset_normalizer-3.4.9-cp314-cp314-win_amd64.whl", hash = "sha256:16b65ea0f2465b6fb52aa22de5eca612aa964ddfec00a912e26f4656cbef890b", size = 162796, upload-time = "2026-07-07T14:34:12.47Z" },
+    { url = "https://files.pythonhosted.org/packages/20/95/d75e82f8ce9fd323ebf059c16c9aadefb22a1ecde13b7840b35835e4886c/charset_normalizer-3.4.9-cp314-cp314-win_arm64.whl", hash = "sha256:40a126142a56b2dfc0aacbad1de8310cbf60da7656db0e6b16eebd48e3e93519", size = 153334, upload-time = "2026-07-07T14:34:14.044Z" },
+    { url = "https://files.pythonhosted.org/packages/00/5e/17398df3a139985ba9d11ed072531986f408c8fca952835ef1ab1820c02b/charset_normalizer-3.4.9-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:609b3ba8fcc0fb5ab7af00719d0fb6ad0cb518e48e7712d12fd68f1327951198", size = 338848, upload-time = "2026-07-07T14:34:15.688Z" },
+    { url = "https://files.pythonhosted.org/packages/cd/91/7253a32e86b7e1d1239b1b36ba6dd0f021a21107ab33054b53119cc083b9/charset_normalizer-3.4.9-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:51447e9aa2684679af07ca5021c3db526e0284347ebf4ffcec1154c3350cfe32", size = 223022, upload-time = "2026-07-07T14:34:17.248Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/32/2e64bd2be10e89c61e57ebe6a93fd98ae88eb7ebe414b5121f22c96c69eb/charset_normalizer-3.4.9-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:cc1b0fff8ead343dae06305f954eb8468ba0ec1a97881f42489d198e4ce3c632", size = 241590, upload-time = "2026-07-07T14:34:18.813Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/ef/d96ec496cfea0c21db43b0ad03891308b02388d054cc902cf0e5a1ad6a88/charset_normalizer-3.4.9-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:fa36ec09ef71d158186bc79e359ff5fdd6e7996fe8ab638f00d6b93139ba4fcf", size = 239584, upload-time = "2026-07-07T14:34:20.52Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/ce/9af95f7876194bd7a14e3dfe4a4de2e0bff02666a3910d72beafd06cc297/charset_normalizer-3.4.9-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:df115d4d83168fdf2cae48ef1ff6d1cb4c466364e30861b37121de0f3bf1b990", size = 230224, upload-time = "2026-07-07T14:34:22.189Z" },
+    { url = "https://files.pythonhosted.org/packages/52/94/af74dde74a3996bd959c350709bfe50e297823d70a8c1cbd54b838880863/charset_normalizer-3.4.9-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:f86c6358749bd4fda175388691e3ba8c46e24c5347d0afd20f9b7edfc9faf07d", size = 212667, upload-time = "2026-07-07T14:34:23.857Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/f0/f1c4fe746c395922961b5916ed1d7d6e7d4c84851d19ed43cc89980ec953/charset_normalizer-3.4.9-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:32286a2c8d167e897177b673176c1e3e00d4057caf5d2b64eef9a3666b03018e", size = 227179, upload-time = "2026-07-07T14:34:25.586Z" },
+    { url = "https://files.pythonhosted.org/packages/e4/56/6c745619ac397e8871e2bcd3cea1eec86b877488f33888b3aef5c3ed506e/charset_normalizer-3.4.9-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:83aed2c10721ddd90f68140685391b50811a880af20654c59af6b6c66c40513c", size = 225372, upload-time = "2026-07-07T14:34:27.212Z" },
+    { url = "https://files.pythonhosted.org/packages/78/ad/98aae8630ac71f16711968e38a5acfecce41b778bf2f0312851020f565a8/charset_normalizer-3.4.9-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:cd6c3d4b783c556fa00bf540854e42f135e2f256abd29669fcd0da0f2dec79c2", size = 215222, upload-time = "2026-07-07T14:34:28.774Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/40/9593d54209765207a7f11073c06494c1721e4ca4a0a426c597679bf7f91e/charset_normalizer-3.4.9-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:ee2f2a527e3c1a6e6411eb4209642e138b544a2d72fe5d0d76daf77b24063534", size = 231958, upload-time = "2026-07-07T14:34:30.345Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/27/693ee5e8a18191eb38647360c51cd505013e2bd3b366aa43fd5344c21e3c/charset_normalizer-3.4.9-cp314-cp314t-win32.whl", hash = "sha256:0d861473f743244d349b50f850d10eb87aeb22bbdcc8e64f79273c94af5a8226", size = 155580, upload-time = "2026-07-07T14:34:31.884Z" },
+    { url = "https://files.pythonhosted.org/packages/80/3f/bd97d3d9c613013d07cb7733d299385b41df37f0471310f5a73dc359f0b8/charset_normalizer-3.4.9-cp314-cp314t-win_amd64.whl", hash = "sha256:9b8e0f3107e2200b76f6054de99016eac3ee6762713587b36baaa7e4bd2ae177", size = 167620, upload-time = "2026-07-07T14:34:33.438Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/c6/eee9dca4439b1061f76373f06ea855678cc4a64c1c3c90b50e479edbb8eb/charset_normalizer-3.4.9-cp314-cp314t-win_arm64.whl", hash = "sha256:19ac87f93086ce37b86e098888555c4b4bc48102279bae3350098c0ed664b501", size = 158037, upload-time = "2026-07-07T14:34:35.018Z" },
+    { url = "https://files.pythonhosted.org/packages/98/2b/f97f1c193fb855c345d678f5077d6926034db0722df74c8f057020e05a25/charset_normalizer-3.4.9-py3-none-any.whl", hash = "sha256:68e5f26a1ad57ded6d1cfb85331d1c1a195314756471d97758c48498bb4dcdf5", size = 64538, upload-time = "2026-07-07T14:34:56.993Z" },
+]
+
+[[package]]
+name = "idna"
+version = "3.18"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/cd/63/9496c57188a2ee585e0f1db071d75089a11e98aa86eb99d9d7618fc1edce/idna-3.18.tar.gz", hash = "sha256:ffb385a7e039654cef1ab9ef32c6fafe283c0c0467bba1d9029738ce4a14a848", size = 196711, upload-time = "2026-06-02T14:34:07.794Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1e/5e/d4e9f1a599fb8e573b7b87160658329fbf28d19eac2718f51fc3def3aa5a/idna-3.18-py3-none-any.whl", hash = "sha256:7f952cbe720b688055e3f87de14f5c3e5fdaa8bc3928985c4077ca689de849a2", size = 65455, upload-time = "2026-06-02T14:34:06.319Z" },
+]
+
+[[package]]
+name = "requests"
+version = "2.34.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "idna" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ac/c3/e2a2b89f2d3e2179abd6d00ebd70bff6273f37fb3e0cc209f48b39d00cbf/requests-2.34.2.tar.gz", hash = "sha256:f288924cae4e29463698d6d60bc6a4da69c89185ad1e0bcc4104f584e960b9ed", size = 142856, upload-time = "2026-05-14T19:25:27.735Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/f4/c67b0b3f1b9245e8d266f0f112c500d50e5b4e83cb6f3b71b6528104182a/requests-2.34.2-py3-none-any.whl", hash = "sha256:2a0d60c172f83ac6ab31e4554906c0f3b3588d37b5cb939b1c061f4907e278e0", size = 73075, upload-time = "2026-05-14T19:25:26.443Z" },
+]
+
+[[package]]
+name = "soupsieve"
+version = "2.9.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d9/38/e12680bbe6b4f8f3d17adcaf38d26850aa756c85cf4a80e79fc12a018fe8/soupsieve-2.9.1.tar.gz", hash = "sha256:c33e6605bbc71dd628b00c632d58ae607c22bade247e52553928f83bbb75b4ba", size = 122261, upload-time = "2026-07-21T16:57:17.452Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/0f/2c/437fe806897c2d6cfdc3ee43a18da8bf8e568530a4ae9bac781541ca9896/soupsieve-2.9.1-py3-none-any.whl", hash = "sha256:4f4477399246b7a0c720a88ca2454b11cd6bb9ae4c9d170140786e916776c14c", size = 37404, upload-time = "2026-07-21T16:57:16.421Z" },
+]
+
+[[package]]
+name = "taks-scraper"
+version = "0.1.0"
+source = { virtual = "." }
+dependencies = [
+    { name = "beautifulsoup4" },
+    { name = "requests" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "beautifulsoup4", specifier = ">=4.12.0" },
+    { name = "requests", specifier = ">=2.31.0" },
+]
+
+[package.metadata.requires-dev]
+dev = []
+
+[[package]]
+name = "typing-extensions"
+version = "4.16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/cc/6253133b5bb138fc3306cebfbda2c520f545d36b5be2c7255cc528bb45d6/typing_extensions-4.16.0.tar.gz", hash = "sha256:dc983d19a509c94dba722ee6abd33940f7c05a89e243c47e907eb4db6f1a43e5", size = 113555, upload-time = "2026-07-02T08:40:05.92Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/49/d3/b8441a820a491ddfc024b0b0cf0393375b75ea13866d9c66727e54c2fc80/typing_extensions-4.16.0-py3-none-any.whl", hash = "sha256:481caa481374e813c1b176ada14e97f1f67a4539ce9cfeb3f350d78d6370c2e8", size = 45571, upload-time = "2026-07-02T08:40:04.659Z" },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.7.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/53/0c/06f8b233b8fd13b9e5ee11424ef85419ba0d8ba0b3138bf360be2ff56953/urllib3-2.7.0.tar.gz", hash = "sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c", size = 433602, upload-time = "2026-05-07T16:13:18.596Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7f/3e/5db95bcf282c52709639744ca2a8b149baccf648e39c8cc87553df9eae0c/urllib3-2.7.0-py3-none-any.whl", hash = "sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897", size = 131087, upload-time = "2026-05-07T16:13:17.151Z" },
+]