From 0b5b9d98c5cc165b7e6d019d661c90faf0a6be75 Mon Sep 17 00:00:00 2001 From: Sosokker Date: Wed, 29 Oct 2025 16:12:55 +0700 Subject: [PATCH] add main files --- .github/workflows/ci.yml | 23 ++ .gitignore | 10 + .python-version | 1 + README.md | 38 +++ linetoday/.cli.py.swp | Bin 0 -> 4096 bytes linetoday/__init__.py | 1 + linetoday/cli.py | 198 ++++++++++++ linetoday/extractor.py | 383 ++++++++++++++++++++++++ linetoday/fetcher.py | 246 +++++++++++++++ linetoday/frontier.py | 40 +++ linetoday/metrics.py | 51 ++++ linetoday/robots.py | 88 ++++++ linetoday/storage.py | 57 ++++ pyproject.toml | 18 ++ requirements.txt | 5 + tests/conftest.py | 6 + tests/fixtures/article_RBVxEOM.html | 66 ++++ tests/test_extractor.py | 44 +++ tests/test_frontier.py | 16 + tests/test_metrics.py | 18 ++ tools/convert_all_parsed.py | 42 +++ tools/run_crawl.py | 75 +++++ uv.lock | 449 ++++++++++++++++++++++++++++ 23 files changed, 1875 insertions(+) create mode 100644 .github/workflows/ci.yml create mode 100644 .gitignore create mode 100644 .python-version create mode 100644 README.md create mode 100644 linetoday/.cli.py.swp create mode 100644 linetoday/__init__.py create mode 100644 linetoday/cli.py create mode 100644 linetoday/extractor.py create mode 100644 linetoday/fetcher.py create mode 100644 linetoday/frontier.py create mode 100644 linetoday/metrics.py create mode 100644 linetoday/robots.py create mode 100644 linetoday/storage.py create mode 100644 pyproject.toml create mode 100644 requirements.txt create mode 100644 tests/conftest.py create mode 100644 tests/fixtures/article_RBVxEOM.html create mode 100644 tests/test_extractor.py create mode 100644 tests/test_frontier.py create mode 100644 tests/test_metrics.py create mode 100644 tools/convert_all_parsed.py create mode 100644 tools/run_crawl.py create mode 100644 uv.lock diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml new file mode 100644 index 0000000..eec3a10 --- /dev/null +++ b/.github/workflows/ci.yml @@ -0,0 +1,23 @@ +name: CI + +on: + push: + branches: [ main, master ] + pull_request: + branches: [ main, master ] + +jobs: + test: + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 + - name: Set up Python + uses: actions/setup-python@v4 + with: + python-version: 3.11 + - name: Install dependencies + run: | + python -m pip install --upgrade pip + pip install -r requirements.txt + - name: Run tests + run: pytest -q diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..505a3b1 --- /dev/null +++ b/.gitignore @@ -0,0 +1,10 @@ +# Python-generated files +__pycache__/ +*.py[oc] +build/ +dist/ +wheels/ +*.egg-info + +# Virtual environments +.venv diff --git a/.python-version b/.python-version new file mode 100644 index 0000000..e4fba21 --- /dev/null +++ b/.python-version @@ -0,0 +1 @@ +3.12 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59235a7 --- /dev/null +++ b/README.md @@ -0,0 +1,38 @@ +line-today-scrape +=================== + +Prototype respectful crawler for https://today.line.me/th/ (Thai locale). + +Overview +-------- +This project contains a conservative, policy-first crawler prototype written in Python. +It demonstrates: +- Robots.txt fetching and policy enforcement +- Rate-limited async fetching +- HTML extraction (meta tags + JSON-LD fallback) +- Local storage of raw snapshots and parsed JSON + +Note: This is a prototype. Always review and run responsibly. + +Quickstart +---------- +1. Install dependencies (recommend using poetry or virtualenv) + + poetry install + +2. Run the crawler in dry-run mode (fetch limited pages): + + python -m linetoday.cli --dry-run --limit 5 + +Files +----- +- `linetoday/robots.py` - Robots & policy manager +- `linetoday/fetcher.py` - Async HTTP fetcher with rate limiting +- `linetoday/frontier.py` - URL frontier and canonicalization +- `linetoday/extractor.py` - Article extraction logic +- `linetoday/storage.py` - Local storage for snapshots and parsed JSON +- `linetoday/cli.py` - CLI entrypoint + +License +------- +Prototype for demonstration only. diff --git a/linetoday/.cli.py.swp b/linetoday/.cli.py.swp new file mode 100644 index 0000000000000000000000000000000000000000..db90ea476ef0f3eee4f8a9eaba36d09cc2edb2a5 GIT binary patch literal 4096 zcmYc?2=nw+u+%eT00IF9h7;ErGuh4989bsH7>YBCGV=;DKr(oNzniaTh@V-cL8On5 zF&>q5Py_V~Qj3c7^AdCPb29T%bxZP75-W9!lZz4yQo$l%0sZ8hOud3iJjRVmjfTKz z2oM_rr6p;)7QCUxMur9;Ey_xY3c^C6#OfYZHyQ$?Aut*OqaiRF0;3@?8UmvsFd71* JAutR=008XSBoqJu literal 0 HcmV?d00001 diff --git a/linetoday/__init__.py b/linetoday/__init__.py new file mode 100644 index 0000000..f095add --- /dev/null +++ b/linetoday/__init__.py @@ -0,0 +1 @@ +# linetoday package diff --git a/linetoday/cli.py b/linetoday/cli.py new file mode 100644 index 0000000..b46ebaf --- /dev/null +++ b/linetoday/cli.py @@ -0,0 +1,198 @@ +import argparse +import asyncio +import logging +import signal +import time +from contextlib import suppress + +from .extractor import extract_article +from .fetcher import Fetcher +from .frontier import Frontier +from .metrics import MetricsRecorder +from .robots import RobotsManager +from .storage import store_parsed, store_snapshot + +ORIGIN = 'https://today.line.me/th/v3/tab/wealth' +START_URL = 'https://today.line.me/th/v3/tab/wealth' + + +def build_parser() -> argparse.ArgumentParser: + parser = argparse.ArgumentParser(prog='linetoday') + parser.add_argument('--dry-run', action='store_true', help='Do not persist parsed data') + parser.add_argument('--limit', type=int, default=10, help='Max pages to fetch') + parser.add_argument('--ignore-robots', action='store_true', help='Ignore robots.txt checks (use only for local testing)') + parser.add_argument('--verbose', action='store_true', help='Enable debug logging') + parser.add_argument('--concurrency', type=int, default=4, help='Number of concurrent fetch workers') + parser.add_argument('--metrics-interval', type=float, default=30.0, help='Seconds between metrics log snapshots') + parser.add_argument('--per-origin-capacity', type=int, default=2, help='Burst size per origin token bucket') + parser.add_argument('--per-origin-refill', type=float, default=2.0, help='Seconds per token refill for origin bucket') + parser.add_argument('--timeout', type=float, default=20.0, help='HTTP request timeout') + return parser + + +async def metrics_reporter(metrics: MetricsRecorder, interval: float, stop_event: asyncio.Event) -> None: + try: + while not stop_event.is_set(): + await asyncio.sleep(interval) + logging.info('metrics %s', metrics.format_snapshot()) + except asyncio.CancelledError: + logging.info('metrics %s', metrics.format_snapshot()) + raise + + +async def crawl(args) -> None: + ua = 'LineTodayCrawler/0.1 (+mailto:ops@example.com)' + robots = RobotsManager(user_agent=ua) + frontier = Frontier() + metrics = MetricsRecorder() + + queue: asyncio.Queue[str | None] = asyncio.Queue() + if frontier.add(START_URL): + queue.put_nowait(START_URL) + metrics.inc('frontier_seeded') + + fetched = 0 + fetched_lock = asyncio.Lock() + stop_event = asyncio.Event() + + async with Fetcher( + user_agent=ua, + max_retries=3, + circuit_threshold=5, + circuit_cooldown=60.0, + timeout=args.timeout, + per_origin_capacity=args.per_origin_capacity, + per_origin_refill=args.per_origin_refill, + ) as fetcher: + reporter_task = asyncio.create_task(metrics_reporter(metrics, args.metrics_interval, stop_event)) + + async def worker(worker_id: int) -> None: + nonlocal fetched + logger = logging.getLogger(f'worker-{worker_id}') + while True: + url = await queue.get() + if url is None: + queue.task_done() + logger.debug('received sentinel, exiting') + break + + metrics.inc('queue_dequeued') + if stop_event.is_set(): + queue.task_done() + continue + + if not url.startswith('https://today.line.me/th'): + queue.task_done() + continue + + path = url[len(ORIGIN):] + if not args.ignore_robots: + allowed = await asyncio.to_thread(robots.allowed, ORIGIN, path) + if not allowed: + logger.info('robots disallow %s', url) + metrics.inc('robots_blocked') + queue.task_done() + continue + + logger.info('fetching %s', url) + metrics.inc('fetch_started') + fetch_start = time.perf_counter() + res = await fetcher.fetch(url) + latency_ms = (time.perf_counter() - fetch_start) * 1000 + metrics.observe('fetch_latency_ms', latency_ms) + + status = res.get('status') + if status is None: + metrics.inc('status_none') + logger.error('error fetching %s: %s', url, res.get('error')) + if res.get('pause_seconds'): + pause = res['pause_seconds'] + metrics.inc('retry_pauses') + logger.info('pausing for %s seconds', pause) + await asyncio.sleep(pause) + queue.task_done() + continue + + metrics.inc(f'status_{status}') + counted = False + + if status == 304: + logger.info('not modified %s', url) + counted = True + elif status != 200: + logger.warning('skipping %s status %s', url, status) + else: + html = res.get('text', '') + await asyncio.to_thread(store_snapshot, url, html) + metrics.inc('snapshots_written') + + article, links = extract_article(html, url) + if not args.dry_run: + await asyncio.to_thread(store_parsed, article) + metrics.inc('parsed_written') + + if not stop_event.is_set(): + new_links = 0 + for link in links: + if link.startswith('/'): + link = ORIGIN + link + if frontier.add(link): + queue.put_nowait(link) + new_links += 1 + metrics.inc('links_enqueued', new_links) + counted = True + + if counted: + async with fetched_lock: + fetched += 1 + metrics.inc('fetched_total') + if fetched >= args.limit and not stop_event.is_set(): + logger.info('fetch limit reached (%s)', args.limit) + stop_event.set() + for _ in range(args.concurrency): + queue.put_nowait(None) + + queue.task_done() + + workers = [asyncio.create_task(worker(i)) for i in range(args.concurrency)] + + def _request_stop(*_): + if not stop_event.is_set(): + logging.warning('received shutdown signal; draining queue') + stop_event.set() + for _ in range(args.concurrency): + queue.put_nowait(None) + + loop = asyncio.get_running_loop() + for sig in (signal.SIGINT, signal.SIGTERM): + with suppress(NotImplementedError): + loop.add_signal_handler(sig, _request_stop) + + await queue.join() + if not stop_event.is_set(): + stop_event.set() + for _ in range(args.concurrency): + queue.put_nowait(None) + + await asyncio.gather(*workers, return_exceptions=True) + reporter_task.cancel() + with suppress(asyncio.CancelledError): + await reporter_task + + await asyncio.to_thread(robots._http.close) + logging.info('done') + + +def main(): + parser = build_parser() + args = parser.parse_args() + + level = logging.DEBUG if args.verbose else logging.INFO + logging.basicConfig(level=level, format='%(asctime)s %(levelname)s %(name)s %(message)s') + + asyncio.run(crawl(args)) + + +if __name__ == '__main__': + main() + diff --git a/linetoday/extractor.py b/linetoday/extractor.py new file mode 100644 index 0000000..1d58513 --- /dev/null +++ b/linetoday/extractor.py @@ -0,0 +1,383 @@ +import re +import html +import json +from datetime import datetime, timezone +from typing import Dict, List, Tuple, Optional, Any, Set +from urllib.parse import urljoin, urlparse + +from bs4 import BeautifulSoup + + +def _get_meta(soup: BeautifulSoup, prop: str) -> Optional[str]: + tag = soup.find('meta', attrs={"property": prop}) or soup.find('meta', attrs={"name": prop}) + if tag and tag.get('content'): + return tag.get('content').strip() + return None + + +def _parse_json_ld(soup: BeautifulSoup) -> Optional[dict]: + for tag in soup.find_all('script', type='application/ld+json'): + try: + raw = tag.string + if not raw: + continue + data = json.loads(raw.strip()) + # if list, prefer first NewsArticle + if isinstance(data, list): + for item in data: + if isinstance(item, dict) and item.get('@type') in ('NewsArticle', 'Article'): + return item + if isinstance(data, dict) and data.get('@type') in ('NewsArticle', 'Article'): + return data + except Exception: + continue + return None + + +def _parse_next_data(soup: BeautifulSoup) -> Optional[dict]: + tag = soup.find('script', attrs={'id': '__NEXT_DATA__', 'type': 'application/json'}) + if not tag: + # sometimes it's without type + tag = soup.find('script', attrs={'id': '__NEXT_DATA__'}) + if not tag: + return None + try: + raw = tag.string or tag.get_text() + if not raw: + return None + raw = raw.strip() + # unescape HTML entities that sometimes wrap the JSON + raw = html.unescape(raw) + try: + data = json.loads(raw) + return data + except Exception: + # sometimes the JSON is embedded or has prefix/suffix; try to extract between first and last brace + first = raw.find('{') + last = raw.rfind('}') + if first != -1 and last != -1 and last > first: + snippet = raw[first:last+1] + try: + return json.loads(snippet) + except Exception: + return None + return None + except Exception: + return None + + +def _find_field(obj: Any, keys: List[str]) -> Optional[Any]: + """Recursively search dict/list for first occurrence of any key in keys.""" + if isinstance(obj, dict): + for k, v in obj.items(): + if k in keys: + return v + found = _find_field(v, keys) + if found is not None: + return found + elif isinstance(obj, list): + for item in obj: + found = _find_field(item, keys) + if found is not None: + return found + return None + + +def _extract_article_payload(nextdata: dict) -> Tuple[Optional[dict], Optional[str]]: + """Locate the structured article payload inside Next.js fallback data.""" + props = nextdata.get('props') if isinstance(nextdata, dict) else None + page_props = props.get('pageProps') if isinstance(props, dict) else None + fallback = page_props.get('fallback') if isinstance(page_props, dict) else None + if not isinstance(fallback, dict): + return None, None + + for key, value in fallback.items(): + if isinstance(value, dict): + data = value.get('data') + if isinstance(data, dict) and data.get('content') and data.get('title'): + return data, key + if value.get('content') and value.get('title'): + return value, key + return None, None + + +def _text_from_html_fragment(fragment: str) -> str: + # Use BeautifulSoup to cleanly extract text from HTML fragments + try: + frag_soup = BeautifulSoup(fragment, 'lxml') + return frag_soup.get_text(separator=' ', strip=True) + except Exception: + # fallback: strip tags crudely + return re.sub('<[^<]+?>', '', fragment).strip() + + +def _normalize_paragraphs(text: str) -> str: + """Remove obvious noise (Loading..., duplicate nav labels) while preserving order.""" + if not text: + return '' + cleaned: List[str] = [] + seen_counts: Dict[str, int] = {} + for raw_line in text.splitlines(): + line = raw_line.strip() + if not line: + continue + lower = line.lower() + if 'loading' in lower: + # Catch "Loading...", "Loading... Loading..." etc. + continue + # Allow each distinct line up to twice to keep short quotes + if seen_counts.get(lower, 0) >= 2: + continue + seen_counts[lower] = seen_counts.get(lower, 0) + 1 + cleaned.append(line) + return '\n\n'.join(cleaned) + + +def _is_today_article_url(url: str) -> bool: + parsed = urlparse(url) + if parsed.netloc and 'today.line.me' not in parsed.netloc: + return False + return '/article/' in parsed.path + + +def _collect_structured_links(article_payload: Optional[dict]) -> Set[str]: + links: Set[str] = set() + if not isinstance(article_payload, dict): + return links + + explore = article_payload.get('exploreLinks') + if isinstance(explore, list): + for entry in explore: + page_link = entry.get('pageLink') if isinstance(entry, dict) else None + if not isinstance(page_link, dict): + continue + page_type = page_link.get('pageType') + if page_type == 'ARTICLE': + hash_val = page_link.get('hash') + if hash_val: + links.add(f'https://today.line.me/th/v3/article/{hash_val}') + elif page_type == 'GENERAL': + page = page_link.get('page') + if isinstance(page, dict): + url_path = page.get('urlPath') + if url_path: + links.add(f'https://today.line.me/th/v3/page/{url_path}') + elif page_type == 'TAG': + tag_hash = page_link.get('hash') + if tag_hash: + links.add(f'https://today.line.me/th/v3/tag/{tag_hash}') + return links + + +def extract_article(html: str, url: str) -> Tuple[Dict, List[str]]: + soup = BeautifulSoup(html, 'lxml') + + # meta / og + title = _get_meta(soup, 'og:title') or _get_meta(soup, 'title') + description = _get_meta(soup, 'og:description') or _get_meta(soup, 'description') + image = _get_meta(soup, 'og:image') + published = _get_meta(soup, 'article:published_time') + + # JSON-LD + jsonld = _parse_json_ld(soup) + if jsonld: + title = title or jsonld.get('headline') + if not published: + published = jsonld.get('datePublished') or jsonld.get('dateCreated') + author = None + a = jsonld.get('author') + if isinstance(a, dict): + author = a.get('name') + elif isinstance(a, list) and a: + author = a[0].get('name') if isinstance(a[0], dict) else None + else: + author = a + publisher = None + pub = jsonld.get('publisher') + if isinstance(pub, dict): + publisher = pub.get('name') + else: + author = None + publisher = None + + body_html = None + content_type = None + source_url = None + category = None + tags: List[str] = [] + is_article = False + + # Try Next.js page data + nextdata = _parse_next_data(soup) + if nextdata: + payload, payload_key = _extract_article_payload(nextdata) + if payload: + content_type = payload.get('contentType') + url_info = payload.get('url') if isinstance(payload.get('url'), dict) else None + canonical_url = url_info.get('url') if isinstance(url_info, dict) else None + if canonical_url and _is_today_article_url(canonical_url): + is_article = True + url = canonical_url + elif canonical_url: + url = canonical_url + title = payload.get('title') or title + description = payload.get('shortDescription') or description + author = payload.get('author') or author + publisher = payload.get('publisher') or publisher + source_url = payload.get('sourceUrl') + category = payload.get('categoryName') + publish_unix = payload.get('publishTimeUnix') + if publish_unix and not published: + try: + published = datetime.fromtimestamp(publish_unix, tz=timezone.utc).isoformat() + except Exception: + published = payload.get('publishTime') or published + elif payload.get('publishTime') and not published: + published = payload.get('publishTime') + body_html = payload.get('content') + if body_html: + article_body = _text_from_html_fragment(body_html) + explore_links = payload.get('exploreLinks') + if isinstance(explore_links, list): + for entry in explore_links: + tag_name = entry.get('name') if isinstance(entry, dict) else None + page_link = entry.get('pageLink') if isinstance(entry, dict) else None + if tag_name and page_link and page_link.get('pageType') == 'TAG': + tags.append(tag_name) + else: + # search common fields used by news sites / Next.js props + nd_title = _find_field(nextdata, ['title', 'headline', 'name', 'seoTitle']) + if nd_title and not title: + title = nd_title + nd_desc = _find_field(nextdata, ['description', 'summary', 'seoDescription']) + if nd_desc and not description: + description = nd_desc + nd_body = _find_field(nextdata, ['articleBody', 'body', 'content', 'html']) + if nd_body: + if isinstance(nd_body, str): + article_body = _text_from_html_fragment(nd_body) + elif isinstance(nd_body, list): + parts = [] + for item in nd_body: + if isinstance(item, str): + parts.append(_text_from_html_fragment(item)) + elif isinstance(item, dict): + for k in ('text', 'content', 'body', 'html'): + if k in item and isinstance(item[k], str): + parts.append(_text_from_html_fragment(item[k])) + article_body = '\n\n'.join([p for p in parts if p]) + elif isinstance(nd_body, dict): + if 'html' in nd_body and isinstance(nd_body['html'], str): + article_body = _text_from_html_fragment(nd_body['html']) + else: + article_body = _text_from_html_fragment(str(nd_body)) + else: + article_body = '' + else: + article_body = '' + nd_img = _find_field(nextdata, ['image', 'thumbnail', 'ogImage']) + if nd_img and not image: + if isinstance(nd_img, str): + image = urljoin(url, nd_img) + elif isinstance(nd_img, dict): + candidate = nd_img.get('url') or nd_img.get('src') or nd_img.get('path') + if isinstance(candidate, str): + image = urljoin(url, candidate) + + nd_author = _find_field(nextdata, ['author', 'writer', 'creator']) + if nd_author and not author: + if isinstance(nd_author, str): + author = nd_author + elif isinstance(nd_author, dict): + author = nd_author.get('name') + elif isinstance(nd_author, list) and nd_author: + first = nd_author[0] + if isinstance(first, dict): + author = first.get('name') + elif isinstance(first, str): + author = first + + if not published: + nd_pub = _find_field(nextdata, ['datePublished', 'publishedAt', 'createdAt']) + if isinstance(nd_pub, str): + published = nd_pub + + # If payload explicitly marks article content but lacks meta image, attempt to build from payload thumbnail + if not image and payload and isinstance(payload.get('thumbnail'), dict): + thumb = payload['thumbnail'] + thumb_url = thumb.get('url') or thumb.get('src') + if isinstance(thumb_url, str): + image = urljoin(url, thumb_url) + + else: + article_body = '' + + # fallback title + if not title: + h1 = soup.find('h1') + if h1: + title = h1.get_text(strip=True) + + # if article_body still empty, apply HTML heuristics + if not article_body: + # content extraction heuristics + # try common article containers + candidates = [] + for sel in ['article', 'div[class*="article"]', 'div[itemprop="articleBody"]', 'div[class*="content"]']: + candidates.extend(soup.select(sel)) + if not candidates: + # fallback to main + main = soup.find('main') + if main: + candidates = [main] + if candidates: + # Choose largest candidate by text length + best = max(candidates, key=lambda el: len(el.get_text(strip=True))) + # remove scripts, styles, ads-like nodes + for bad in best.select('script, style, .ad, .ads, .related, .promo'): + bad.decompose() + paragraphs = [p.get_text(separator=' ', strip=True) for p in best.find_all(['p', 'div']) if p.get_text(strip=True)] + article_body = '\n\n'.join(paragraphs) + else: + # as last resort, combine all

+ paragraphs = [p.get_text(strip=True) for p in soup.find_all('p')] + article_body = '\n\n'.join(paragraphs) + + article_body = _normalize_paragraphs(article_body) + + # collect internal links with a bias toward article detail pages + link_candidates: Set[str] = set() + if nextdata: + payload, _ = _extract_article_payload(nextdata) + link_candidates.update(_collect_structured_links(payload)) + + for a in soup.find_all('a', href=True): + href = a['href'] + absolute = urljoin(url, href) + if _is_today_article_url(absolute): + link_candidates.add(absolute) + elif absolute.startswith('https://today.line.me/th/'): + link_candidates.add(absolute) + + if is_article: + link_candidates.add(url) + + links = sorted(link_candidates) + + article = { + 'url': url, + 'title': title, + 'description': description, + 'author': author, + 'publisher': publisher, + 'published_at': published, + 'image': image, + 'body_text': article_body, + 'body_html': body_html, + 'content_type': content_type, + 'category': category, + 'source_url': source_url, + 'tags': tags, + 'is_article': is_article, + } + return article, links diff --git a/linetoday/fetcher.py b/linetoday/fetcher.py new file mode 100644 index 0000000..bb0ab13 --- /dev/null +++ b/linetoday/fetcher.py @@ -0,0 +1,246 @@ +import asyncio +import logging +import random +import time +from collections import defaultdict +from pathlib import Path +from typing import Dict, Optional +from urllib.parse import urlparse + +import json + +try: + import httpx +except Exception: # pragma: no cover + httpx = None # type: ignore + +LOG = logging.getLogger(__name__) + +METADATA_DIR = Path.cwd() / 'data' / 'meta' +METADATA_DIR.mkdir(parents=True, exist_ok=True) + + +class AsyncTokenBucket: + def __init__(self, capacity: int, refill_interval: float): + self.capacity = capacity + self.tokens = capacity + self.refill_interval = refill_interval + self.lock = asyncio.Lock() + self.last_refill = time.monotonic() + + def _refill(self, now: float) -> None: + elapsed = now - self.last_refill + if elapsed <= 0: + return + add = int(elapsed / self.refill_interval) + if add > 0: + self.tokens = min(self.capacity, self.tokens + add) + self.last_refill += add * self.refill_interval + + async def consume(self, timeout: Optional[float] = None) -> bool: + deadline = None if timeout is None else time.monotonic() + timeout + while True: + async with self.lock: + now = time.monotonic() + self._refill(now) + if self.tokens > 0: + self.tokens -= 1 + return True + if deadline and time.monotonic() > deadline: + return False + await asyncio.sleep(0.05) + + +class Fetcher: + def __init__( + self, + user_agent: str = "LineTodayCrawler/0.1 (+mailto:ops@example.com)", + max_retries: int = 3, + circuit_threshold: int = 5, + circuit_cooldown: float = 60.0, + playwright_enabled: bool = False, + timeout: float = 20.0, + per_origin_capacity: int = 2, + per_origin_refill: float = 2.0, + ): + if httpx is None: # pragma: no cover + raise RuntimeError('httpx must be installed to use Fetcher') + self.user_agent = user_agent + self._client = httpx.AsyncClient(timeout=timeout, follow_redirects=True) + self._bucket_capacity = max(1, per_origin_capacity) + self._bucket_refill = max(0.1, per_origin_refill) + self._buckets: Dict[str, AsyncTokenBucket] = defaultdict( + lambda: AsyncTokenBucket(self._bucket_capacity, self._bucket_refill) + ) + self.max_retries = max_retries + self._failures: Dict[str, int] = defaultdict(int) + self._circuit_tripped_until: Dict[str, float] = {} + self.circuit_threshold = circuit_threshold + self.circuit_cooldown = circuit_cooldown + self.playwright_enabled = playwright_enabled + self._pw = None + self._browser = None + + async def __aenter__(self) -> "Fetcher": + return self + + async def __aexit__(self, exc_type, exc, tb) -> None: + await self.close() + + async def close(self) -> None: + try: + if self._browser: + try: + await asyncio.to_thread(self._browser.close) + except Exception: + pass + self._browser = None + if self._pw: + try: + await asyncio.to_thread(self._pw.stop) + except Exception: + pass + self._pw = None + except Exception: + LOG.exception('error while closing Playwright resources') + await self._client.aclose() + + def _origin(self, url: str) -> str: + p = urlparse(url) + return f"{p.scheme}://{p.netloc}" + + async def _acquire(self, url: str) -> bool: + origin = self._origin(url) + until = self._circuit_tripped_until.get(origin) + now = time.monotonic() + if until and now < until: + LOG.warning('circuit open for %s until %s', origin, until) + return False + bucket = self._buckets[origin] + return await bucket.consume() + + def _meta_path(self, url: str) -> Path: + name = str(abs(hash(url))) + '.json' + return METADATA_DIR / name + + def _load_meta_sync(self, url: str) -> dict: + p = self._meta_path(url) + if p.exists(): + try: + return json.loads(p.read_text(encoding='utf-8')) + except Exception: + return {} + return {} + + async def _load_meta(self, url: str) -> dict: + return await asyncio.to_thread(self._load_meta_sync, url) + + def _save_meta_sync(self, url: str, meta: dict) -> None: + p = self._meta_path(url) + p.write_text(json.dumps(meta, ensure_ascii=False), encoding='utf-8') + + async def _save_meta(self, url: str, meta: dict) -> None: + await asyncio.to_thread(self._save_meta_sync, url, meta) + + def _record_failure(self, origin: str) -> None: + self._failures[origin] += 1 + if self._failures[origin] >= self.circuit_threshold: + until = time.monotonic() + self.circuit_cooldown + self._circuit_tripped_until[origin] = until + LOG.error('tripping circuit for %s until %.2f after %d failures', origin, until, self._failures[origin]) + + def _record_success(self, origin: str) -> None: + self._failures[origin] = 0 + if origin in self._circuit_tripped_until: + del self._circuit_tripped_until[origin] + + async def fetch(self, url: str, render_js: bool = False) -> dict: + origin = self._origin(url) + ok = await self._acquire(url) + if not ok: + return {"url": url, "status": None, "error": "rate_limited_or_circuit_open"} + + headers = { + "User-Agent": self.user_agent, + "Accept-Language": "th,en;q=0.8", + "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8", + } + + meta = await self._load_meta(url) + if meta.get('etag'): + headers['If-None-Match'] = meta['etag'] + if meta.get('last_modified'): + headers['If-Modified-Since'] = meta['last_modified'] + + if render_js and self.playwright_enabled: + LOG.warning('render_js mode is not supported in async fetcher yet; falling back to HTTP client for %s', url) + + attempt = 0 + start = time.monotonic() + + while True: + attempt += 1 + try: + LOG.debug('fetch attempt %d %s', attempt, url) + resp = await self._client.get(url, headers=headers) + duration = int((time.monotonic() - start) * 1000) + status = resp.status_code + + out = { + "url": url, + "status": status, + "headers": dict(resp.headers), + "text": resp.text, + "elapsed_ms": duration, + } + + meta2 = {} + if resp.headers.get('etag'): + meta2['etag'] = resp.headers.get('etag') + if resp.headers.get('last-modified'): + meta2['last_modified'] = resp.headers.get('last-modified') + if meta2: + await self._save_meta(url, meta2) + + if 200 <= status < 400: + self._record_success(origin) + + if status in (429, 503): + ra = resp.headers.get('Retry-After') + pause = None + if ra: + try: + pause = int(ra) + except ValueError: + pause = None + if pause and attempt <= self.max_retries: + LOG.warning('honoring Retry-After=%s for %s', pause, url) + out['pause_seconds'] = pause + self._record_failure(origin) + await asyncio.sleep(pause) + continue + + if status == 429 or (500 <= status < 600): + self._record_failure(origin) + if attempt <= self.max_retries: + backoff = (2 ** (attempt - 1)) + random.random() + LOG.warning('transient status %s on %s; retrying in %.2fs (attempt %d)', status, url, backoff, attempt) + await asyncio.sleep(backoff) + continue + LOG.error('giving up after %d attempts for %s status=%s', attempt, url, status) + return out + except httpx.RequestError as e: + duration = int((time.monotonic() - start) * 1000) + LOG.warning('request error on %s: %s', url, e) + self._record_failure(origin) + if attempt <= self.max_retries: + backoff = (2 ** (attempt - 1)) + random.random() + LOG.debug('retrying after error in %.2fs', backoff) + await asyncio.sleep(backoff) + continue + return {"url": url, "status": None, "error": str(e), "elapsed_ms": duration} + except Exception as e: # pragma: no cover - defensive + duration = int((time.monotonic() - start) * 1000) + LOG.exception('unexpected error fetching %s', url) + self._record_failure(origin) + return {"url": url, "status": None, "error": str(e), "elapsed_ms": duration} diff --git a/linetoday/frontier.py b/linetoday/frontier.py new file mode 100644 index 0000000..f4b2604 --- /dev/null +++ b/linetoday/frontier.py @@ -0,0 +1,40 @@ +from collections import deque +from urllib.parse import urlparse, urlunparse, parse_qsl, urlencode + +TRACKING_PARAMS = {"utm_source", "utm_medium", "utm_campaign", "utm_term", "utm_content", "fbclid", "gclid"} + + +def normalize_url(url: str) -> str: + """Normalize URL: force https, remove fragments, drop tracking params, sort query.""" + parsed = urlparse(url) + scheme = parsed.scheme or 'https' + netloc = parsed.netloc + path = parsed.path or '/' + # remove fragment + query_pairs = [(k, v) for k, v in parse_qsl(parsed.query, keep_blank_values=True) if k not in TRACKING_PARAMS] + query_pairs.sort() + query = urlencode(query_pairs) + normalized = urlunparse((scheme, netloc, path, '', query, '')) + return normalized + + +class Frontier: + def __init__(self): + self._seen: set[str] = set() + self._queue: deque[str] = deque() + + def add(self, url: str) -> bool: + url = normalize_url(url) + if url in self._seen: + return False + self._seen.add(url) + self._queue.append(url) + return True + + def pop(self) -> str | None: + if not self._queue: + return None + return self._queue.popleft() + + def __len__(self) -> int: + return len(self._queue) diff --git a/linetoday/metrics.py b/linetoday/metrics.py new file mode 100644 index 0000000..f92e095 --- /dev/null +++ b/linetoday/metrics.py @@ -0,0 +1,51 @@ +from __future__ import annotations + +import time +from collections import defaultdict +from typing import Dict + + +class MetricsRecorder: + """Lightweight in-process metrics aggregator.""" + + def __init__(self) -> None: + self.counters: Dict[str, int] = defaultdict(int) + self.timers: Dict[str, dict[str, float]] = defaultdict(lambda: {"count": 0, "total": 0.0}) + self.last_reset: float = time.time() + + def inc(self, key: str, amount: int = 1) -> None: + self.counters[key] += amount + + def observe(self, key: str, value: float) -> None: + bucket = self.timers[key] + bucket["count"] += 1 + bucket["total"] += value + + def snapshot(self) -> dict: + snap = { + "counters": dict(self.counters), + "timers": { + name: { + "count": data["count"], + "avg": (data["total"] / data["count"]) if data["count"] else 0.0, + } + for name, data in self.timers.items() + }, + "uptime": time.time() - self.last_reset, + } + return snap + + def format_snapshot(self) -> str: + snap = self.snapshot() + counter_parts = [f"{k}={v}" for k, v in sorted(snap["counters"].items())] + timer_parts = [ + f"{name}:count={data['count']},avg_ms={data['avg']:.1f}" + for name, data in sorted(snap["timers"].items()) + ] + parts = [] + if counter_parts: + parts.append("counters[" + ", ".join(counter_parts) + "]") + if timer_parts: + parts.append("timers[" + ", ".join(timer_parts) + "]") + parts.append(f"uptime={snap['uptime']:.1f}s") + return " ".join(parts) diff --git a/linetoday/robots.py b/linetoday/robots.py new file mode 100644 index 0000000..5ddcdfa --- /dev/null +++ b/linetoday/robots.py @@ -0,0 +1,88 @@ +import time +from dataclasses import dataclass +from typing import Optional +from urllib.parse import urljoin +import httpx +import urllib.robotparser as robotparser + + +@dataclass +class RobotsPolicy: + url: str + fetched_at: float + raw: str + hash: Optional[str] + parser: robotparser.RobotFileParser + + +class RobotsManager: + """Fetch and cache robots.txt for origins using standard library parser. + + This implementation fetches robots.txt with httpx and parses Allow/Disallow + and Crawl-delay. It caches results for one hour by default. + """ + + def __init__(self, user_agent: str = "LineTodayCrawler/0.1 (+mailto:ops@example.com)"): + self.user_agent = user_agent + self._cache: dict[str, RobotsPolicy] = {} + self._http = httpx.Client(timeout=10.0) + + def _fetch_robots(self, origin: str) -> RobotsPolicy: + robots_url = urljoin(origin, "/robots.txt") + try: + resp = self._http.get(robots_url) + raw = resp.text if resp.status_code == 200 else "" + except Exception: + raw = "" + parser = robotparser.RobotFileParser() + parser.set_url(robots_url) + try: + parser.parse(raw.splitlines()) + except Exception: + # fall back to empty parser (allows everything) + parser = robotparser.RobotFileParser() + parser.parse([]) + policy = RobotsPolicy(url=robots_url, fetched_at=time.time(), raw=raw, hash=None, parser=parser) + return policy + + def get_policy(self, origin: str) -> RobotsPolicy: + now = time.time() + policy = self._cache.get(origin) + if policy and now - policy.fetched_at < 3600: + return policy + policy = self._fetch_robots(origin) + self._cache[origin] = policy + return policy + + def allowed(self, origin: str, path: str) -> bool: + policy = self.get_policy(origin) + try: + return policy.parser.can_fetch(self.user_agent, path) + except Exception: + return False + + def crawl_delay(self, origin: str) -> Optional[float]: + policy = self.get_policy(origin) + # urllib.robotparser does not expose crawl-delay; parse manually + raw = policy.raw + if not raw: + return None + ua = None + delay = None + for line in raw.splitlines(): + line = line.strip() + if not line or line.startswith('#'): + continue + parts = line.split(':', 1) + if len(parts) != 2: + continue + k, v = parts[0].strip().lower(), parts[1].strip() + if k == 'user-agent': + ua = v + if k == 'crawl-delay' and ua in (self.user_agent, '*'): + try: + delay = float(v) + return delay + except Exception: + continue + return None diff --git a/linetoday/storage.py b/linetoday/storage.py new file mode 100644 index 0000000..97114bf --- /dev/null +++ b/linetoday/storage.py @@ -0,0 +1,57 @@ +import json +from datetime import datetime +from pathlib import Path + +STORAGE_DIR = Path.cwd() / 'data' +SNAPSHOT_DIR = STORAGE_DIR / 'snapshots' +PARSED_DIR = STORAGE_DIR / 'parsed' + + +def ensure_dirs(): + SNAPSHOT_DIR.mkdir(parents=True, exist_ok=True) + PARSED_DIR.mkdir(parents=True, exist_ok=True) + + +def store_snapshot(url: str, html: str) -> str: + ensure_dirs() + ts = datetime.utcnow().strftime('%Y%m%dT%H%M%SZ') + name = f"{ts}_{abs(hash(url))}.html" + path = SNAPSHOT_DIR / name + path.write_text(html, encoding='utf-8') + return str(path) + + +def _article_to_markdown(article: dict) -> str: + parts = [] + title = article.get('title') + if title: + parts.append(f"# {title}") + meta = [] + if article.get('author'): + meta.append(str(article.get('author'))) + if article.get('published_at'): + meta.append(str(article.get('published_at'))) + if meta: + parts.append('_' + ' • '.join(meta) + '_') + if article.get('description'): + parts.append(article.get('description')) + if article.get('image'): + parts.append(f"![image]({article.get('image')})") + body = article.get('body_text') or '' + if body: + parts.append(body) + return '\n\n'.join(parts) + + +def store_parsed(article: dict) -> str: + ensure_dirs() + ts = datetime.utcnow().strftime('%Y%m%dT%H%M%SZ') + fname = f"{ts}_{abs(hash(article.get('url')))}.json" + path = PARSED_DIR / fname + path.write_text(json.dumps(article, ensure_ascii=False, indent=2), encoding='utf-8') + # also write markdown alongside + md = _article_to_markdown(article) + md_name = fname.rsplit('.', 1)[0] + '.md' + md_path = PARSED_DIR / md_name + md_path.write_text(md, encoding='utf-8') + return str(path) diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..ad5d9bd --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,18 @@ +[project] +name = "line-today-scrape" +version = "0.1.0" +description = "Respectful crawler prototype for https://today.line.me/th/" +readme = "README.md" +requires-python = ">=3.11" +dependencies = [ + "anyio>=4.11.0", + "beautifulsoup4>=4.14.2", + "httpx>=0.28.1", + "lxml>=6.0.2", + "playwright>=1.55.0", + "pytest>=8.4.2", + "ujson>=5.11.0", +] + +[project.optional-dependencies] +dev = ["pytest>=8.4.2"] diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..ada03e8 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,5 @@ +httpx>=0.24.0 +beautifulsoup4>=4.12.2 +lxml>=4.9.3 +pytest>=7.0 +playwright>=1.55.0 diff --git a/tests/conftest.py b/tests/conftest.py new file mode 100644 index 0000000..d06c5e4 --- /dev/null +++ b/tests/conftest.py @@ -0,0 +1,6 @@ +import sys +from pathlib import Path +# Ensure project root is on sys.path for tests +ROOT = Path(__file__).resolve().parents[1] +if str(ROOT) not in sys.path: + sys.path.insert(0, str(ROOT)) diff --git a/tests/fixtures/article_RBVxEOM.html b/tests/fixtures/article_RBVxEOM.html new file mode 100644 index 0000000..f598132 --- /dev/null +++ b/tests/fixtures/article_RBVxEOM.html @@ -0,0 +1,66 @@ +เปิดดวงราศีนี้ มีโอกาสได้โชครับทรัพย์ ออร่าคนรวยพุ่ง | sanook.com | LINE TODAY

โปรดอัพเดตเบราว์เซอร์

เบราว์เซอร์ที่คุณใช้เป็นเวอร์ชันเก่าซึ่งไม่สามารถใช้บริการของเราได้ เราขอแนะนำให้อัพเดตเบราว์เซอร์เพื่อการใช้งานที่ดีที่สุด

ดูดวง

เปิดดวงราศีนี้ มีโอกาสได้โชครับทรัพย์ ออร่าคนรวยพุ่ง

sanook.com

เผยแพร่ 3 ชั่วโมงที่ผ่านมา • Sanook
ทำนายดวง พบราศี รับอิทธิพลดาวพฤหัสดีและอาพอลลอนเต็ม ๆ ช่วงนี้มีเกณฑ์รับทรัพย์ หนี้สินมีทางออก ดูดีมีสง่า

ทำนายดวง พบราศี รับอิทธิพลดาวพฤหัสดีและอาพอลลอนเต็ม ๆ ช่วงนี้มีเกณฑ์รับทรัพย์ หนี้สินมีทางออก ดูดีมีสง่า

เช็กดวงช่วงนี้ จาก อาจารย์ธนกร ศานติพรนพเก้า นักพยากรณ์ด้วยวิชาโหราศาสตร์ยูเรเนี่ยนขั้นสูงทำนายทายทักถึงราศีที่ออร่าจับเพราะสวยและรวยมาก โดยมีคำทำนาย ดังนี้

ด้วยอิทธิพลของดาวพฤหัสดี และดาวอาพอลลอน ส่งผลต่อชาวราศีธนู (ผู้ที่เกิดตั้งแต่วันที่ 22 พ.ย. - 21ธ.ค.) ทำให้ช่วงนี้ มีโอกาสได้รับโชครับทรัพย์ มีเงินใช้ไม่ขาดมือจนทำให้ดูดีมีราศีมากเป็นพิเศษ และจะหันมาใส่ใจดูแลตัวเองซื้อเครื่องประดับใหม่เพื่อเป็นรางวัลให้ชีวิตตัวเอง ใครที่มีหนี้สินมีโอกาสที่จะได้พบทางออกในการปลดหนี้สินจนเกิดความพึงพอใจเป็นอย่างมาก

ดูข่าวต้นฉบับ

ดูดวงออนไลน์ กับ LINE ดูดวง

ดูดวงถาม-ตอบแบบส่วนตัว คลิปวิดีโอหรือคอลไลน์ ดูดวงเจาะลึกกับนักพยากรณ์หลากหลาย

LINE ดูดวง

ทำบุญ เพิ่มทานบารมี ใส่บาตร สังฆทาน ถวายผ้าไตร ทำง่าย ๆ ผ่านออนไลน์

LINE ดูดวง

ไพ่ไม่ดี เสริมดวงกันต่อ ไหว้พระ ขอพรออนไลน์

LINE ดูดวง
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
Loading...
\ No newline at end of file diff --git a/tests/test_extractor.py b/tests/test_extractor.py new file mode 100644 index 0000000..271edc8 --- /dev/null +++ b/tests/test_extractor.py @@ -0,0 +1,44 @@ +from pathlib import Path + +from linetoday.extractor import extract_article + + +SNAPSHOT_DIR = Path(__file__).resolve().parents[1] / 'data' / 'snapshots' +ARTICLE_FIXTURE = Path(__file__).resolve().parents[0] / 'fixtures' / 'article_RBVxEOM.html' + + +def test_article_fixture_uses_structured_payload(): + html = ARTICLE_FIXTURE.read_text(encoding='utf-8') + url = 'https://today.line.me/th/v3/article/RBVxEOM' + article, links = extract_article(html, url) + + assert article['is_article'] is True + assert article['title'] and 'เปิดดวง' in article['title'] + assert article['body_html'], 'expected body_html extracted from structured payload' + assert len(article['body_text']) > 500 + assert article['published_at'] + assert article['author'] == 'Sanook' + assert any('/th/v3/article/' in link for link in links) + + +def test_snapshots_are_classified_and_sanitised(): + # iterate all html snapshots in data/snapshots + files = sorted([p for p in SNAPSHOT_DIR.iterdir() if p.suffix == '.html']) + assert files, f'No snapshot files found in {SNAPSHOT_DIR}' + + for f in files: + html = f.read_text(encoding='utf-8') + url = f'https://today.line.me/snapshot/{f.name}' + article, links = extract_article(html, url) + + assert isinstance(article, dict) + assert isinstance(links, list) + assert article.get('url') and article['url'].startswith('https://today.line.me') + title = article.get('title') + assert title and isinstance(title, str) and title.strip(), f'missing title for {f.name}' + + if article.get('is_article'): + assert article.get('body_text') and len(article['body_text'].strip()) > 200 + else: + body = article.get('body_text', '') + assert 'loading' not in body.lower() diff --git a/tests/test_frontier.py b/tests/test_frontier.py new file mode 100644 index 0000000..a5bb192 --- /dev/null +++ b/tests/test_frontier.py @@ -0,0 +1,16 @@ +from linetoday.frontier import normalize_url + + +def test_normalize_strip_tracking(): + url = 'https://today.line.me/th/article/ABC?utm_source=foo&x=1&y=2#section' + n = normalize_url(url) + assert 'utm_source' not in n + assert '#' not in n + assert n.startswith('https://') + + +def test_normalize_sort_query(): + url = 'https://today.line.me/th?page=2&b=2&a=1' + n = normalize_url(url) + # query params should be sorted: a then b + assert 'a=1' in n and 'b=2' in n diff --git a/tests/test_metrics.py b/tests/test_metrics.py new file mode 100644 index 0000000..64ba549 --- /dev/null +++ b/tests/test_metrics.py @@ -0,0 +1,18 @@ +from linetoday.metrics import MetricsRecorder + + +def test_metrics_recorder_snapshot_and_format(): + metrics = MetricsRecorder() + metrics.inc('requests') + metrics.inc('requests', 2) + metrics.observe('latency_ms', 100.0) + metrics.observe('latency_ms', 50.0) + + snap = metrics.snapshot() + assert snap['counters']['requests'] == 3 + assert snap['timers']['latency_ms']['count'] == 2 + assert snap['timers']['latency_ms']['avg'] == 75.0 + + formatted = metrics.format_snapshot() + assert 'requests=3' in formatted + assert 'latency_ms' in formatted diff --git a/tools/convert_all_parsed.py b/tools/convert_all_parsed.py new file mode 100644 index 0000000..66a4d3c --- /dev/null +++ b/tools/convert_all_parsed.py @@ -0,0 +1,42 @@ +#!/usr/bin/env python3 +"""Convert all data/parsed/*.json to .md files alongside them.""" +import json +from pathlib import Path + +PARSED = Path.cwd() / 'data' / 'parsed' + + +def article_to_markdown(article: dict) -> str: + parts = [] + title = article.get('title') + if title: + parts.append(f"# {title}") + meta = [] + if article.get('author'): + meta.append(str(article.get('author'))) + if article.get('published_at'): + meta.append(str(article.get('published_at'))) + if meta: + parts.append('_' + ' • '.join(meta) + '_') + if article.get('description'): + parts.append(article.get('description')) + if article.get('image'): + parts.append(f"![image]({article.get('image')})") + body = article.get('body_text') or '' + if body: + parts.append(body) + return '\n\n'.join(parts) + + +if __name__ == '__main__': + PARSED.mkdir(parents=True, exist_ok=True) + files = sorted(PARSED.glob('*.json')) + for f in files: + try: + a = json.loads(f.read_text(encoding='utf-8')) + md = article_to_markdown(a) + out = f.with_suffix('.md') + out.write_text(md, encoding='utf-8') + print('Wrote', out) + except Exception as e: + print('Failed', f, e) diff --git a/tools/run_crawl.py b/tools/run_crawl.py new file mode 100644 index 0000000..a087ae4 --- /dev/null +++ b/tools/run_crawl.py @@ -0,0 +1,75 @@ +#!/usr/bin/env python3 +"""Simple orchestrator: crawl -> fetch -> extract -> store (json + md). + +Usage: tools/run_crawl.py [--limit N] [--dry-run] [--seed URL] +""" +import argparse +import logging +import time +from pathlib import Path + +from linetoday.frontier import Frontier +from linetoday.fetcher import Fetcher +from linetoday.extractor import extract_article +from linetoday.storage import store_snapshot, store_parsed +from linetoday.robots import RobotsManager + + +def main(): + p = argparse.ArgumentParser() + p.add_argument('--limit', type=int, default=10) + p.add_argument('--dry-run', action='store_true') + p.add_argument('--seed', type=str, default='https://today.line.me/th/v3/tab') + p.add_argument('--ignore-robots', action='store_true') + p.add_argument('--verbose', action='store_true') + args = p.parse_args() + + logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO, format='%(asctime)s %(levelname)s %(message)s') + ua = 'LineTodayCrawler/0.1 (+mailto:ops@example.com)' + frontier = Frontier() + frontier.add(args.seed) + fetcher = Fetcher(user_agent=ua) + robots = RobotsManager(user_agent=ua) + + fetched = 0 + origin = 'https://today.line.me' + while fetched < args.limit and len(frontier) > 0: + url = frontier.pop() + if not url: + break + if not url.startswith(origin): + continue + path = url[len(origin):] + if not args.ignore_robots: + allowed = robots.allowed(origin, path) + if not allowed: + logging.info('robots disallow %s', url) + continue + logging.info('fetching %s', url) + res = fetcher.fetch(url) + status = res.get('status') + if status is None: + logging.error('error fetching %s: %s', url, res.get('error')) + if res.get('pause_seconds'): + logging.info('pausing for %s seconds', res['pause_seconds']) + time.sleep(res['pause_seconds']) + continue + if status != 200: + logging.info('skipping non-200 %s status=%s', url, status) + continue + html = res.get('text', '') + snap = store_snapshot(url, html) + article, links = extract_article(html, url) + if not args.dry_run: + parsed_path = store_parsed(article) + logging.info('stored parsed %s', parsed_path) + for link in links: + if link.startswith('/'): + link = origin + link + frontier.add(link) + fetched += 1 + logging.info('done') + + +if __name__ == '__main__': + main() diff --git a/uv.lock b/uv.lock new file mode 100644 index 0000000..aced912 --- /dev/null +++ b/uv.lock @@ -0,0 +1,449 @@ +version = 1 +revision = 3 +requires-python = ">=3.11" + +[[package]] +name = "anyio" +version = "4.11.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "idna" }, + { name = "sniffio" }, + { name = "typing-extensions", marker = "python_full_version < '3.13'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/c6/78/7d432127c41b50bccba979505f272c16cbcadcc33645d5fa3a738110ae75/anyio-4.11.0.tar.gz", hash = "sha256:82a8d0b81e318cc5ce71a5f1f8b5c4e63619620b63141ef8c995fa0db95a57c4", size = 219094, upload-time = "2025-09-23T09:19:12.58Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/15/b3/9b1a8074496371342ec1e796a96f99c82c945a339cd81a8e73de28b4cf9e/anyio-4.11.0-py3-none-any.whl", hash = "sha256:0287e96f4d26d4149305414d4e3bc32f0dcd0862365a4bddea19d7a1ec38c4fc", size = 109097, upload-time = "2025-09-23T09:19:10.601Z" }, +] + +[[package]] +name = "beautifulsoup4" +version = "4.14.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "soupsieve" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/77/e9/df2358efd7659577435e2177bfa69cba6c33216681af51a707193dec162a/beautifulsoup4-4.14.2.tar.gz", hash = "sha256:2a98ab9f944a11acee9cc848508ec28d9228abfd522ef0fad6a02a72e0ded69e", size = 625822, upload-time = "2025-09-29T10:05:42.613Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/94/fe/3aed5d0be4d404d12d36ab97e2f1791424d9ca39c2f754a6285d59a3b01d/beautifulsoup4-4.14.2-py3-none-any.whl", hash = "sha256:5ef6fa3a8cbece8488d66985560f97ed091e22bbc4e9c2338508a9d5de6d4515", size = 106392, upload-time = "2025-09-29T10:05:43.771Z" }, +] + +[[package]] +name = "certifi" +version = "2025.10.5" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/4c/5b/b6ce21586237c77ce67d01dc5507039d444b630dd76611bbca2d8e5dcd91/certifi-2025.10.5.tar.gz", hash = "sha256:47c09d31ccf2acf0be3f701ea53595ee7e0b8fa08801c6624be771df09ae7b43", size = 164519, upload-time = "2025-10-05T04:12:15.808Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e4/37/af0d2ef3967ac0d6113837b44a4f0bfe1328c2b9763bd5b1744520e5cfed/certifi-2025.10.5-py3-none-any.whl", hash = "sha256:0f212c2744a9bb6de0c56639a6f68afe01ecd92d91f14ae897c4fe7bbeeef0de", size = 163286, upload-time = "2025-10-05T04:12:14.03Z" }, +] + +[[package]] +name = "colorama" +version = "0.4.6" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697, upload-time = "2022-10-25T02:36:22.414Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335, upload-time = "2022-10-25T02:36:20.889Z" }, +] + +[[package]] +name = "greenlet" +version = "3.2.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/03/b8/704d753a5a45507a7aab61f18db9509302ed3d0a27ac7e0359ec2905b1a6/greenlet-3.2.4.tar.gz", hash = "sha256:0dca0d95ff849f9a364385f36ab49f50065d76964944638be9691e1832e9f86d", size = 188260, upload-time = "2025-08-07T13:24:33.51Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a4/de/f28ced0a67749cac23fecb02b694f6473f47686dff6afaa211d186e2ef9c/greenlet-3.2.4-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:96378df1de302bc38e99c3a9aa311967b7dc80ced1dcc6f171e99842987882a2", size = 272305, upload-time = "2025-08-07T13:15:41.288Z" }, + { url = "https://files.pythonhosted.org/packages/09/16/2c3792cba130000bf2a31c5272999113f4764fd9d874fb257ff588ac779a/greenlet-3.2.4-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1ee8fae0519a337f2329cb78bd7a8e128ec0f881073d43f023c7b8d4831d5246", size = 632472, upload-time = "2025-08-07T13:42:55.044Z" }, + { url = "https://files.pythonhosted.org/packages/ae/8f/95d48d7e3d433e6dae5b1682e4292242a53f22df82e6d3dda81b1701a960/greenlet-3.2.4-cp311-cp311-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:94abf90142c2a18151632371140b3dba4dee031633fe614cb592dbb6c9e17bc3", size = 644646, upload-time = "2025-08-07T13:45:26.523Z" }, + { url = "https://files.pythonhosted.org/packages/d5/5e/405965351aef8c76b8ef7ad370e5da58d57ef6068df197548b015464001a/greenlet-3.2.4-cp311-cp311-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:4d1378601b85e2e5171b99be8d2dc85f594c79967599328f95c1dc1a40f1c633", size = 640519, upload-time = "2025-08-07T13:53:13.928Z" }, + { url = "https://files.pythonhosted.org/packages/25/5d/382753b52006ce0218297ec1b628e048c4e64b155379331f25a7316eb749/greenlet-3.2.4-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:0db5594dce18db94f7d1650d7489909b57afde4c580806b8d9203b6e79cdc079", size = 639707, upload-time = "2025-08-07T13:18:27.146Z" }, + { url = "https://files.pythonhosted.org/packages/1f/8e/abdd3f14d735b2929290a018ecf133c901be4874b858dd1c604b9319f064/greenlet-3.2.4-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2523e5246274f54fdadbce8494458a2ebdcdbc7b802318466ac5606d3cded1f8", size = 587684, upload-time = "2025-08-07T13:18:25.164Z" }, + { url = "https://files.pythonhosted.org/packages/5d/65/deb2a69c3e5996439b0176f6651e0052542bb6c8f8ec2e3fba97c9768805/greenlet-3.2.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1987de92fec508535687fb807a5cea1560f6196285a4cde35c100b8cd632cc52", size = 1116647, upload-time = "2025-08-07T13:42:38.655Z" }, + { url = "https://files.pythonhosted.org/packages/3f/cc/b07000438a29ac5cfb2194bfc128151d52f333cee74dd7dfe3fb733fc16c/greenlet-3.2.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:55e9c5affaa6775e2c6b67659f3a71684de4c549b3dd9afca3bc773533d284fa", size = 1142073, upload-time = "2025-08-07T13:18:21.737Z" }, + { url = "https://files.pythonhosted.org/packages/d8/0f/30aef242fcab550b0b3520b8e3561156857c94288f0332a79928c31a52cf/greenlet-3.2.4-cp311-cp311-win_amd64.whl", hash = "sha256:9c40adce87eaa9ddb593ccb0fa6a07caf34015a29bf8d344811665b573138db9", size = 299100, upload-time = "2025-08-07T13:44:12.287Z" }, + { url = "https://files.pythonhosted.org/packages/44/69/9b804adb5fd0671f367781560eb5eb586c4d495277c93bde4307b9e28068/greenlet-3.2.4-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:3b67ca49f54cede0186854a008109d6ee71f66bd57bb36abd6d0a0267b540cdd", size = 274079, upload-time = "2025-08-07T13:15:45.033Z" }, + { url = "https://files.pythonhosted.org/packages/46/e9/d2a80c99f19a153eff70bc451ab78615583b8dac0754cfb942223d2c1a0d/greenlet-3.2.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ddf9164e7a5b08e9d22511526865780a576f19ddd00d62f8a665949327fde8bb", size = 640997, upload-time = "2025-08-07T13:42:56.234Z" }, + { url = "https://files.pythonhosted.org/packages/3b/16/035dcfcc48715ccd345f3a93183267167cdd162ad123cd93067d86f27ce4/greenlet-3.2.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:f28588772bb5fb869a8eb331374ec06f24a83a9c25bfa1f38b6993afe9c1e968", size = 655185, upload-time = "2025-08-07T13:45:27.624Z" }, + { url = "https://files.pythonhosted.org/packages/31/da/0386695eef69ffae1ad726881571dfe28b41970173947e7c558d9998de0f/greenlet-3.2.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:5c9320971821a7cb77cfab8d956fa8e39cd07ca44b6070db358ceb7f8797c8c9", size = 649926, upload-time = "2025-08-07T13:53:15.251Z" }, + { url = "https://files.pythonhosted.org/packages/68/88/69bf19fd4dc19981928ceacbc5fd4bb6bc2215d53199e367832e98d1d8fe/greenlet-3.2.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c60a6d84229b271d44b70fb6e5fa23781abb5d742af7b808ae3f6efd7c9c60f6", size = 651839, upload-time = "2025-08-07T13:18:30.281Z" }, + { url = "https://files.pythonhosted.org/packages/19/0d/6660d55f7373b2ff8152401a83e02084956da23ae58cddbfb0b330978fe9/greenlet-3.2.4-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3b3812d8d0c9579967815af437d96623f45c0f2ae5f04e366de62a12d83a8fb0", size = 607586, upload-time = "2025-08-07T13:18:28.544Z" }, + { url = "https://files.pythonhosted.org/packages/8e/1a/c953fdedd22d81ee4629afbb38d2f9d71e37d23caace44775a3a969147d4/greenlet-3.2.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:abbf57b5a870d30c4675928c37278493044d7c14378350b3aa5d484fa65575f0", size = 1123281, upload-time = "2025-08-07T13:42:39.858Z" }, + { url = "https://files.pythonhosted.org/packages/3f/c7/12381b18e21aef2c6bd3a636da1088b888b97b7a0362fac2e4de92405f97/greenlet-3.2.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:20fb936b4652b6e307b8f347665e2c615540d4b42b3b4c8a321d8286da7e520f", size = 1151142, upload-time = "2025-08-07T13:18:22.981Z" }, + { url = "https://files.pythonhosted.org/packages/e9/08/b0814846b79399e585f974bbeebf5580fbe59e258ea7be64d9dfb253c84f/greenlet-3.2.4-cp312-cp312-win_amd64.whl", hash = "sha256:a7d4e128405eea3814a12cc2605e0e6aedb4035bf32697f72deca74de4105e02", size = 299899, upload-time = "2025-08-07T13:38:53.448Z" }, + { url = "https://files.pythonhosted.org/packages/49/e8/58c7f85958bda41dafea50497cbd59738c5c43dbbea5ee83d651234398f4/greenlet-3.2.4-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:1a921e542453fe531144e91e1feedf12e07351b1cf6c9e8a3325ea600a715a31", size = 272814, upload-time = "2025-08-07T13:15:50.011Z" }, + { url = "https://files.pythonhosted.org/packages/62/dd/b9f59862e9e257a16e4e610480cfffd29e3fae018a68c2332090b53aac3d/greenlet-3.2.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd3c8e693bff0fff6ba55f140bf390fa92c994083f838fece0f63be121334945", size = 641073, upload-time = "2025-08-07T13:42:57.23Z" }, + { url = "https://files.pythonhosted.org/packages/f7/0b/bc13f787394920b23073ca3b6c4a7a21396301ed75a655bcb47196b50e6e/greenlet-3.2.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:710638eb93b1fa52823aa91bf75326f9ecdfd5e0466f00789246a5280f4ba0fc", size = 655191, upload-time = "2025-08-07T13:45:29.752Z" }, + { url = "https://files.pythonhosted.org/packages/f2/d6/6adde57d1345a8d0f14d31e4ab9c23cfe8e2cd39c3baf7674b4b0338d266/greenlet-3.2.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:c5111ccdc9c88f423426df3fd1811bfc40ed66264d35aa373420a34377efc98a", size = 649516, upload-time = "2025-08-07T13:53:16.314Z" }, + { url = "https://files.pythonhosted.org/packages/7f/3b/3a3328a788d4a473889a2d403199932be55b1b0060f4ddd96ee7cdfcad10/greenlet-3.2.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d76383238584e9711e20ebe14db6c88ddcedc1829a9ad31a584389463b5aa504", size = 652169, upload-time = "2025-08-07T13:18:32.861Z" }, + { url = "https://files.pythonhosted.org/packages/ee/43/3cecdc0349359e1a527cbf2e3e28e5f8f06d3343aaf82ca13437a9aa290f/greenlet-3.2.4-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:23768528f2911bcd7e475210822ffb5254ed10d71f4028387e5a99b4c6699671", size = 610497, upload-time = "2025-08-07T13:18:31.636Z" }, + { url = "https://files.pythonhosted.org/packages/b8/19/06b6cf5d604e2c382a6f31cafafd6f33d5dea706f4db7bdab184bad2b21d/greenlet-3.2.4-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:00fadb3fedccc447f517ee0d3fd8fe49eae949e1cd0f6a611818f4f6fb7dc83b", size = 1121662, upload-time = "2025-08-07T13:42:41.117Z" }, + { url = "https://files.pythonhosted.org/packages/a2/15/0d5e4e1a66fab130d98168fe984c509249c833c1a3c16806b90f253ce7b9/greenlet-3.2.4-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d25c5091190f2dc0eaa3f950252122edbbadbb682aa7b1ef2f8af0f8c0afefae", size = 1149210, upload-time = "2025-08-07T13:18:24.072Z" }, + { url = "https://files.pythonhosted.org/packages/0b/55/2321e43595e6801e105fcfdee02b34c0f996eb71e6ddffca6b10b7e1d771/greenlet-3.2.4-cp313-cp313-win_amd64.whl", hash = "sha256:554b03b6e73aaabec3745364d6239e9e012d64c68ccd0b8430c64ccc14939a8b", size = 299685, upload-time = "2025-08-07T13:24:38.824Z" }, + { url = "https://files.pythonhosted.org/packages/22/5c/85273fd7cc388285632b0498dbbab97596e04b154933dfe0f3e68156c68c/greenlet-3.2.4-cp314-cp314-macosx_11_0_universal2.whl", hash = "sha256:49a30d5fda2507ae77be16479bdb62a660fa51b1eb4928b524975b3bde77b3c0", size = 273586, upload-time = "2025-08-07T13:16:08.004Z" }, + { url = "https://files.pythonhosted.org/packages/d1/75/10aeeaa3da9332c2e761e4c50d4c3556c21113ee3f0afa2cf5769946f7a3/greenlet-3.2.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:299fd615cd8fc86267b47597123e3f43ad79c9d8a22bebdce535e53550763e2f", size = 686346, upload-time = "2025-08-07T13:42:59.944Z" }, + { url = "https://files.pythonhosted.org/packages/c0/aa/687d6b12ffb505a4447567d1f3abea23bd20e73a5bed63871178e0831b7a/greenlet-3.2.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:c17b6b34111ea72fc5a4e4beec9711d2226285f0386ea83477cbb97c30a3f3a5", size = 699218, upload-time = "2025-08-07T13:45:30.969Z" }, + { url = "https://files.pythonhosted.org/packages/dc/8b/29aae55436521f1d6f8ff4e12fb676f3400de7fcf27fccd1d4d17fd8fecd/greenlet-3.2.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b4a1870c51720687af7fa3e7cda6d08d801dae660f75a76f3845b642b4da6ee1", size = 694659, upload-time = "2025-08-07T13:53:17.759Z" }, + { url = "https://files.pythonhosted.org/packages/92/2e/ea25914b1ebfde93b6fc4ff46d6864564fba59024e928bdc7de475affc25/greenlet-3.2.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:061dc4cf2c34852b052a8620d40f36324554bc192be474b9e9770e8c042fd735", size = 695355, upload-time = "2025-08-07T13:18:34.517Z" }, + { url = "https://files.pythonhosted.org/packages/72/60/fc56c62046ec17f6b0d3060564562c64c862948c9d4bc8aa807cf5bd74f4/greenlet-3.2.4-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:44358b9bf66c8576a9f57a590d5f5d6e72fa4228b763d0e43fee6d3b06d3a337", size = 657512, upload-time = "2025-08-07T13:18:33.969Z" }, + { url = "https://files.pythonhosted.org/packages/e3/a5/6ddab2b4c112be95601c13428db1d8b6608a8b6039816f2ba09c346c08fc/greenlet-3.2.4-cp314-cp314-win_amd64.whl", hash = "sha256:e37ab26028f12dbb0ff65f29a8d3d44a765c61e729647bf2ddfbbed621726f01", size = 303425, upload-time = "2025-08-07T13:32:27.59Z" }, +] + +[[package]] +name = "h11" +version = "0.16.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/01/ee/02a2c011bdab74c6fb3c75474d40b3052059d95df7e73351460c8588d963/h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1", size = 101250, upload-time = "2025-04-24T03:35:25.427Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515, upload-time = "2025-04-24T03:35:24.344Z" }, +] + +[[package]] +name = "httpcore" +version = "1.0.9" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "certifi" }, + { name = "h11" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/06/94/82699a10bca87a5556c9c59b5963f2d039dbd239f25bc2a63907a05a14cb/httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8", size = 85484, upload-time = "2025-04-24T22:06:22.219Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784, upload-time = "2025-04-24T22:06:20.566Z" }, +] + +[[package]] +name = "httpx" +version = "0.28.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "anyio" }, + { name = "certifi" }, + { name = "httpcore" }, + { name = "idna" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406, upload-time = "2024-12-06T15:37:23.222Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" }, +] + +[[package]] +name = "idna" +version = "3.11" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" }, +] + +[[package]] +name = "iniconfig" +version = "2.3.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/72/34/14ca021ce8e5dfedc35312d08ba8bf51fdd999c576889fc2c24cb97f4f10/iniconfig-2.3.0.tar.gz", hash = "sha256:c76315c77db068650d49c5b56314774a7804df16fee4402c1f19d6d15d8c4730", size = 20503, upload-time = "2025-10-18T21:55:43.219Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/cb/b1/3846dd7f199d53cb17f49cba7e651e9ce294d8497c8c150530ed11865bb8/iniconfig-2.3.0-py3-none-any.whl", hash = "sha256:f631c04d2c48c52b84d0d0549c99ff3859c98df65b3101406327ecc7d53fbf12", size = 7484, upload-time = "2025-10-18T21:55:41.639Z" }, +] + +[[package]] +name = "line-today-scrape" +version = "0.1.0" +source = { virtual = "." } +dependencies = [ + { name = "anyio" }, + { name = "beautifulsoup4" }, + { name = "httpx" }, + { name = "lxml" }, + { name = "playwright" }, + { name = "pytest" }, + { name = "ujson" }, +] + +[package.optional-dependencies] +dev = [ + { name = "pytest" }, +] + +[package.metadata] +requires-dist = [ + { name = "anyio", specifier = ">=4.11.0" }, + { name = "beautifulsoup4", specifier = ">=4.14.2" }, + { name = "httpx", specifier = ">=0.28.1" }, + { name = "lxml", specifier = ">=6.0.2" }, + { name = "playwright", specifier = ">=1.55.0" }, + { name = "pytest", specifier = ">=8.4.2" }, + { name = "pytest", marker = "extra == 'dev'", specifier = ">=8.4.2" }, + { name = "ujson", specifier = ">=5.11.0" }, +] +provides-extras = ["dev"] + +[[package]] +name = "lxml" +version = "6.0.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/aa/88/262177de60548e5a2bfc46ad28232c9e9cbde697bd94132aeb80364675cb/lxml-6.0.2.tar.gz", hash = "sha256:cd79f3367bd74b317dda655dc8fcfa304d9eb6e4fb06b7168c5cf27f96e0cd62", size = 4073426, upload-time = "2025-09-22T04:04:59.287Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/77/d5/becbe1e2569b474a23f0c672ead8a29ac50b2dc1d5b9de184831bda8d14c/lxml-6.0.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:13e35cbc684aadf05d8711a5d1b5857c92e5e580efa9a0d2be197199c8def607", size = 8634365, upload-time = "2025-09-22T04:00:45.672Z" }, + { url = "https://files.pythonhosted.org/packages/28/66/1ced58f12e804644426b85d0bb8a4478ca77bc1761455da310505f1a3526/lxml-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3b1675e096e17c6fe9c0e8c81434f5736c0739ff9ac6123c87c2d452f48fc938", size = 4650793, upload-time = "2025-09-22T04:00:47.783Z" }, + { url = "https://files.pythonhosted.org/packages/11/84/549098ffea39dfd167e3f174b4ce983d0eed61f9d8d25b7bf2a57c3247fc/lxml-6.0.2-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:8ac6e5811ae2870953390452e3476694196f98d447573234592d30488147404d", size = 4944362, upload-time = "2025-09-22T04:00:49.845Z" }, + { url = "https://files.pythonhosted.org/packages/ac/bd/f207f16abf9749d2037453d56b643a7471d8fde855a231a12d1e095c4f01/lxml-6.0.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:5aa0fc67ae19d7a64c3fe725dc9a1bb11f80e01f78289d05c6f62545affec438", size = 5083152, upload-time = "2025-09-22T04:00:51.709Z" }, + { url = "https://files.pythonhosted.org/packages/15/ae/bd813e87d8941d52ad5b65071b1affb48da01c4ed3c9c99e40abb266fbff/lxml-6.0.2-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:de496365750cc472b4e7902a485d3f152ecf57bd3ba03ddd5578ed8ceb4c5964", size = 5023539, upload-time = "2025-09-22T04:00:53.593Z" }, + { url = "https://files.pythonhosted.org/packages/02/cd/9bfef16bd1d874fbe0cb51afb00329540f30a3283beb9f0780adbb7eec03/lxml-6.0.2-cp311-cp311-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:200069a593c5e40b8f6fc0d84d86d970ba43138c3e68619ffa234bc9bb806a4d", size = 5344853, upload-time = "2025-09-22T04:00:55.524Z" }, + { url = "https://files.pythonhosted.org/packages/b8/89/ea8f91594bc5dbb879734d35a6f2b0ad50605d7fb419de2b63d4211765cc/lxml-6.0.2-cp311-cp311-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7d2de809c2ee3b888b59f995625385f74629707c9355e0ff856445cdcae682b7", size = 5225133, upload-time = "2025-09-22T04:00:57.269Z" }, + { url = "https://files.pythonhosted.org/packages/b9/37/9c735274f5dbec726b2db99b98a43950395ba3d4a1043083dba2ad814170/lxml-6.0.2-cp311-cp311-manylinux_2_31_armv7l.whl", hash = "sha256:b2c3da8d93cf5db60e8858c17684c47d01fee6405e554fb55018dd85fc23b178", size = 4677944, upload-time = "2025-09-22T04:00:59.052Z" }, + { url = "https://files.pythonhosted.org/packages/20/28/7dfe1ba3475d8bfca3878365075abe002e05d40dfaaeb7ec01b4c587d533/lxml-6.0.2-cp311-cp311-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:442de7530296ef5e188373a1ea5789a46ce90c4847e597856570439621d9c553", size = 5284535, upload-time = "2025-09-22T04:01:01.335Z" }, + { url = "https://files.pythonhosted.org/packages/e7/cf/5f14bc0de763498fc29510e3532bf2b4b3a1c1d5d0dff2e900c16ba021ef/lxml-6.0.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:2593c77efde7bfea7f6389f1ab249b15ed4aa5bc5cb5131faa3b843c429fbedb", size = 5067343, upload-time = "2025-09-22T04:01:03.13Z" }, + { url = "https://files.pythonhosted.org/packages/1c/b0/bb8275ab5472f32b28cfbbcc6db7c9d092482d3439ca279d8d6fa02f7025/lxml-6.0.2-cp311-cp311-musllinux_1_2_armv7l.whl", hash = "sha256:3e3cb08855967a20f553ff32d147e14329b3ae70ced6edc2f282b94afbc74b2a", size = 4725419, upload-time = "2025-09-22T04:01:05.013Z" }, + { url = "https://files.pythonhosted.org/packages/25/4c/7c222753bc72edca3b99dbadba1b064209bc8ed4ad448af990e60dcce462/lxml-6.0.2-cp311-cp311-musllinux_1_2_riscv64.whl", hash = "sha256:2ed6c667fcbb8c19c6791bbf40b7268ef8ddf5a96940ba9404b9f9a304832f6c", size = 5275008, upload-time = "2025-09-22T04:01:07.327Z" }, + { url = "https://files.pythonhosted.org/packages/6c/8c/478a0dc6b6ed661451379447cdbec77c05741a75736d97e5b2b729687828/lxml-6.0.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b8f18914faec94132e5b91e69d76a5c1d7b0c73e2489ea8929c4aaa10b76bbf7", size = 5248906, upload-time = "2025-09-22T04:01:09.452Z" }, + { url = "https://files.pythonhosted.org/packages/2d/d9/5be3a6ab2784cdf9accb0703b65e1b64fcdd9311c9f007630c7db0cfcce1/lxml-6.0.2-cp311-cp311-win32.whl", hash = "sha256:6605c604e6daa9e0d7f0a2137bdc47a2e93b59c60a65466353e37f8272f47c46", size = 3610357, upload-time = "2025-09-22T04:01:11.102Z" }, + { url = "https://files.pythonhosted.org/packages/e2/7d/ca6fb13349b473d5732fb0ee3eec8f6c80fc0688e76b7d79c1008481bf1f/lxml-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e5867f2651016a3afd8dd2c8238baa66f1e2802f44bc17e236f547ace6647078", size = 4036583, upload-time = "2025-09-22T04:01:12.766Z" }, + { url = "https://files.pythonhosted.org/packages/ab/a2/51363b5ecd3eab46563645f3a2c3836a2fc67d01a1b87c5017040f39f567/lxml-6.0.2-cp311-cp311-win_arm64.whl", hash = "sha256:4197fb2534ee05fd3e7afaab5d8bfd6c2e186f65ea7f9cd6a82809c887bd1285", size = 3680591, upload-time = "2025-09-22T04:01:14.874Z" }, + { url = "https://files.pythonhosted.org/packages/f3/c8/8ff2bc6b920c84355146cd1ab7d181bc543b89241cfb1ebee824a7c81457/lxml-6.0.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:a59f5448ba2ceccd06995c95ea59a7674a10de0810f2ce90c9006f3cbc044456", size = 8661887, upload-time = "2025-09-22T04:01:17.265Z" }, + { url = "https://files.pythonhosted.org/packages/37/6f/9aae1008083bb501ef63284220ce81638332f9ccbfa53765b2b7502203cf/lxml-6.0.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e8113639f3296706fbac34a30813929e29247718e88173ad849f57ca59754924", size = 4667818, upload-time = "2025-09-22T04:01:19.688Z" }, + { url = "https://files.pythonhosted.org/packages/f1/ca/31fb37f99f37f1536c133476674c10b577e409c0a624384147653e38baf2/lxml-6.0.2-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:a8bef9b9825fa8bc816a6e641bb67219489229ebc648be422af695f6e7a4fa7f", size = 4950807, upload-time = "2025-09-22T04:01:21.487Z" }, + { url = "https://files.pythonhosted.org/packages/da/87/f6cb9442e4bada8aab5ae7e1046264f62fdbeaa6e3f6211b93f4c0dd97f1/lxml-6.0.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:65ea18d710fd14e0186c2f973dc60bb52039a275f82d3c44a0e42b43440ea534", size = 5109179, upload-time = "2025-09-22T04:01:23.32Z" }, + { url = "https://files.pythonhosted.org/packages/c8/20/a7760713e65888db79bbae4f6146a6ae5c04e4a204a3c48896c408cd6ed2/lxml-6.0.2-cp312-cp312-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c371aa98126a0d4c739ca93ceffa0fd7a5d732e3ac66a46e74339acd4d334564", size = 5023044, upload-time = "2025-09-22T04:01:25.118Z" }, + { url = "https://files.pythonhosted.org/packages/a2/b0/7e64e0460fcb36471899f75831509098f3fd7cd02a3833ac517433cb4f8f/lxml-6.0.2-cp312-cp312-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:700efd30c0fa1a3581d80a748157397559396090a51d306ea59a70020223d16f", size = 5359685, upload-time = "2025-09-22T04:01:27.398Z" }, + { url = "https://files.pythonhosted.org/packages/b9/e1/e5df362e9ca4e2f48ed6411bd4b3a0ae737cc842e96877f5bf9428055ab4/lxml-6.0.2-cp312-cp312-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:c33e66d44fe60e72397b487ee92e01da0d09ba2d66df8eae42d77b6d06e5eba0", size = 5654127, upload-time = "2025-09-22T04:01:29.629Z" }, + { url = "https://files.pythonhosted.org/packages/c6/d1/232b3309a02d60f11e71857778bfcd4acbdb86c07db8260caf7d008b08f8/lxml-6.0.2-cp312-cp312-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:90a345bbeaf9d0587a3aaffb7006aa39ccb6ff0e96a57286c0cb2fd1520ea192", size = 5253958, upload-time = "2025-09-22T04:01:31.535Z" }, + { url = "https://files.pythonhosted.org/packages/35/35/d955a070994725c4f7d80583a96cab9c107c57a125b20bb5f708fe941011/lxml-6.0.2-cp312-cp312-manylinux_2_31_armv7l.whl", hash = "sha256:064fdadaf7a21af3ed1dcaa106b854077fbeada827c18f72aec9346847cd65d0", size = 4711541, upload-time = "2025-09-22T04:01:33.801Z" }, + { url = "https://files.pythonhosted.org/packages/1e/be/667d17363b38a78c4bd63cfd4b4632029fd68d2c2dc81f25ce9eb5224dd5/lxml-6.0.2-cp312-cp312-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:fbc74f42c3525ac4ffa4b89cbdd00057b6196bcefe8bce794abd42d33a018092", size = 5267426, upload-time = "2025-09-22T04:01:35.639Z" }, + { url = "https://files.pythonhosted.org/packages/ea/47/62c70aa4a1c26569bc958c9ca86af2bb4e1f614e8c04fb2989833874f7ae/lxml-6.0.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6ddff43f702905a4e32bc24f3f2e2edfe0f8fde3277d481bffb709a4cced7a1f", size = 5064917, upload-time = "2025-09-22T04:01:37.448Z" }, + { url = "https://files.pythonhosted.org/packages/bd/55/6ceddaca353ebd0f1908ef712c597f8570cc9c58130dbb89903198e441fd/lxml-6.0.2-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:6da5185951d72e6f5352166e3da7b0dc27aa70bd1090b0eb3f7f7212b53f1bb8", size = 4788795, upload-time = "2025-09-22T04:01:39.165Z" }, + { url = "https://files.pythonhosted.org/packages/cf/e8/fd63e15da5e3fd4c2146f8bbb3c14e94ab850589beab88e547b2dbce22e1/lxml-6.0.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:57a86e1ebb4020a38d295c04fc79603c7899e0df71588043eb218722dabc087f", size = 5676759, upload-time = "2025-09-22T04:01:41.506Z" }, + { url = "https://files.pythonhosted.org/packages/76/47/b3ec58dc5c374697f5ba37412cd2728f427d056315d124dd4b61da381877/lxml-6.0.2-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:2047d8234fe735ab77802ce5f2297e410ff40f5238aec569ad7c8e163d7b19a6", size = 5255666, upload-time = "2025-09-22T04:01:43.363Z" }, + { url = "https://files.pythonhosted.org/packages/19/93/03ba725df4c3d72afd9596eef4a37a837ce8e4806010569bedfcd2cb68fd/lxml-6.0.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:6f91fd2b2ea15a6800c8e24418c0775a1694eefc011392da73bc6cef2623b322", size = 5277989, upload-time = "2025-09-22T04:01:45.215Z" }, + { url = "https://files.pythonhosted.org/packages/c6/80/c06de80bfce881d0ad738576f243911fccf992687ae09fd80b734712b39c/lxml-6.0.2-cp312-cp312-win32.whl", hash = "sha256:3ae2ce7d6fedfb3414a2b6c5e20b249c4c607f72cb8d2bb7cc9c6ec7c6f4e849", size = 3611456, upload-time = "2025-09-22T04:01:48.243Z" }, + { url = "https://files.pythonhosted.org/packages/f7/d7/0cdfb6c3e30893463fb3d1e52bc5f5f99684a03c29a0b6b605cfae879cd5/lxml-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:72c87e5ee4e58a8354fb9c7c84cbf95a1c8236c127a5d1b7683f04bed8361e1f", size = 4011793, upload-time = "2025-09-22T04:01:50.042Z" }, + { url = "https://files.pythonhosted.org/packages/ea/7b/93c73c67db235931527301ed3785f849c78991e2e34f3fd9a6663ffda4c5/lxml-6.0.2-cp312-cp312-win_arm64.whl", hash = "sha256:61cb10eeb95570153e0c0e554f58df92ecf5109f75eacad4a95baa709e26c3d6", size = 3672836, upload-time = "2025-09-22T04:01:52.145Z" }, + { url = "https://files.pythonhosted.org/packages/53/fd/4e8f0540608977aea078bf6d79f128e0e2c2bba8af1acf775c30baa70460/lxml-6.0.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:9b33d21594afab46f37ae58dfadd06636f154923c4e8a4d754b0127554eb2e77", size = 8648494, upload-time = "2025-09-22T04:01:54.242Z" }, + { url = "https://files.pythonhosted.org/packages/5d/f4/2a94a3d3dfd6c6b433501b8d470a1960a20ecce93245cf2db1706adf6c19/lxml-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6c8963287d7a4c5c9a432ff487c52e9c5618667179c18a204bdedb27310f022f", size = 4661146, upload-time = "2025-09-22T04:01:56.282Z" }, + { url = "https://files.pythonhosted.org/packages/25/2e/4efa677fa6b322013035d38016f6ae859d06cac67437ca7dc708a6af7028/lxml-6.0.2-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:1941354d92699fb5ffe6ed7b32f9649e43c2feb4b97205f75866f7d21aa91452", size = 4946932, upload-time = "2025-09-22T04:01:58.989Z" }, + { url = "https://files.pythonhosted.org/packages/ce/0f/526e78a6d38d109fdbaa5049c62e1d32fdd70c75fb61c4eadf3045d3d124/lxml-6.0.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:bb2f6ca0ae2d983ded09357b84af659c954722bbf04dea98030064996d156048", size = 5100060, upload-time = "2025-09-22T04:02:00.812Z" }, + { url = "https://files.pythonhosted.org/packages/81/76/99de58d81fa702cc0ea7edae4f4640416c2062813a00ff24bd70ac1d9c9b/lxml-6.0.2-cp313-cp313-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:eb2a12d704f180a902d7fa778c6d71f36ceb7b0d317f34cdc76a5d05aa1dd1df", size = 5019000, upload-time = "2025-09-22T04:02:02.671Z" }, + { url = "https://files.pythonhosted.org/packages/b5/35/9e57d25482bc9a9882cb0037fdb9cc18f4b79d85df94fa9d2a89562f1d25/lxml-6.0.2-cp313-cp313-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:6ec0e3f745021bfed19c456647f0298d60a24c9ff86d9d051f52b509663feeb1", size = 5348496, upload-time = "2025-09-22T04:02:04.904Z" }, + { url = "https://files.pythonhosted.org/packages/a6/8e/cb99bd0b83ccc3e8f0f528e9aa1f7a9965dfec08c617070c5db8d63a87ce/lxml-6.0.2-cp313-cp313-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:846ae9a12d54e368933b9759052d6206a9e8b250291109c48e350c1f1f49d916", size = 5643779, upload-time = "2025-09-22T04:02:06.689Z" }, + { url = "https://files.pythonhosted.org/packages/d0/34/9e591954939276bb679b73773836c6684c22e56d05980e31d52a9a8deb18/lxml-6.0.2-cp313-cp313-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ef9266d2aa545d7374938fb5c484531ef5a2ec7f2d573e62f8ce722c735685fd", size = 5244072, upload-time = "2025-09-22T04:02:08.587Z" }, + { url = "https://files.pythonhosted.org/packages/8d/27/b29ff065f9aaca443ee377aff699714fcbffb371b4fce5ac4ca759e436d5/lxml-6.0.2-cp313-cp313-manylinux_2_31_armv7l.whl", hash = "sha256:4077b7c79f31755df33b795dc12119cb557a0106bfdab0d2c2d97bd3cf3dffa6", size = 4718675, upload-time = "2025-09-22T04:02:10.783Z" }, + { url = "https://files.pythonhosted.org/packages/2b/9f/f756f9c2cd27caa1a6ef8c32ae47aadea697f5c2c6d07b0dae133c244fbe/lxml-6.0.2-cp313-cp313-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:a7c5d5e5f1081955358533be077166ee97ed2571d6a66bdba6ec2f609a715d1a", size = 5255171, upload-time = "2025-09-22T04:02:12.631Z" }, + { url = "https://files.pythonhosted.org/packages/61/46/bb85ea42d2cb1bd8395484fd72f38e3389611aa496ac7772da9205bbda0e/lxml-6.0.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:8f8d0cbd0674ee89863a523e6994ac25fd5be9c8486acfc3e5ccea679bad2679", size = 5057175, upload-time = "2025-09-22T04:02:14.718Z" }, + { url = "https://files.pythonhosted.org/packages/95/0c/443fc476dcc8e41577f0af70458c50fe299a97bb6b7505bb1ae09aa7f9ac/lxml-6.0.2-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:2cbcbf6d6e924c28f04a43f3b6f6e272312a090f269eff68a2982e13e5d57659", size = 4785688, upload-time = "2025-09-22T04:02:16.957Z" }, + { url = "https://files.pythonhosted.org/packages/48/78/6ef0b359d45bb9697bc5a626e1992fa5d27aa3f8004b137b2314793b50a0/lxml-6.0.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:dfb874cfa53340009af6bdd7e54ebc0d21012a60a4e65d927c2e477112e63484", size = 5660655, upload-time = "2025-09-22T04:02:18.815Z" }, + { url = "https://files.pythonhosted.org/packages/ff/ea/e1d33808f386bc1339d08c0dcada6e4712d4ed8e93fcad5f057070b7988a/lxml-6.0.2-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:fb8dae0b6b8b7f9e96c26fdd8121522ce5de9bb5538010870bd538683d30e9a2", size = 5247695, upload-time = "2025-09-22T04:02:20.593Z" }, + { url = "https://files.pythonhosted.org/packages/4f/47/eba75dfd8183673725255247a603b4ad606f4ae657b60c6c145b381697da/lxml-6.0.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:358d9adae670b63e95bc59747c72f4dc97c9ec58881d4627fe0120da0f90d314", size = 5269841, upload-time = "2025-09-22T04:02:22.489Z" }, + { url = "https://files.pythonhosted.org/packages/76/04/5c5e2b8577bc936e219becb2e98cdb1aca14a4921a12995b9d0c523502ae/lxml-6.0.2-cp313-cp313-win32.whl", hash = "sha256:e8cd2415f372e7e5a789d743d133ae474290a90b9023197fd78f32e2dc6873e2", size = 3610700, upload-time = "2025-09-22T04:02:24.465Z" }, + { url = "https://files.pythonhosted.org/packages/fe/0a/4643ccc6bb8b143e9f9640aa54e38255f9d3b45feb2cbe7ae2ca47e8782e/lxml-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:b30d46379644fbfc3ab81f8f82ae4de55179414651f110a1514f0b1f8f6cb2d7", size = 4010347, upload-time = "2025-09-22T04:02:26.286Z" }, + { url = "https://files.pythonhosted.org/packages/31/ef/dcf1d29c3f530577f61e5fe2f1bd72929acf779953668a8a47a479ae6f26/lxml-6.0.2-cp313-cp313-win_arm64.whl", hash = "sha256:13dcecc9946dca97b11b7c40d29fba63b55ab4170d3c0cf8c0c164343b9bfdcf", size = 3671248, upload-time = "2025-09-22T04:02:27.918Z" }, + { url = "https://files.pythonhosted.org/packages/03/15/d4a377b385ab693ce97b472fe0c77c2b16ec79590e688b3ccc71fba19884/lxml-6.0.2-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:b0c732aa23de8f8aec23f4b580d1e52905ef468afb4abeafd3fec77042abb6fe", size = 8659801, upload-time = "2025-09-22T04:02:30.113Z" }, + { url = "https://files.pythonhosted.org/packages/c8/e8/c128e37589463668794d503afaeb003987373c5f94d667124ffd8078bbd9/lxml-6.0.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:4468e3b83e10e0317a89a33d28f7aeba1caa4d1a6fd457d115dd4ffe90c5931d", size = 4659403, upload-time = "2025-09-22T04:02:32.119Z" }, + { url = "https://files.pythonhosted.org/packages/00/ce/74903904339decdf7da7847bb5741fc98a5451b42fc419a86c0c13d26fe2/lxml-6.0.2-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:abd44571493973bad4598a3be7e1d807ed45aa2adaf7ab92ab7c62609569b17d", size = 4966974, upload-time = "2025-09-22T04:02:34.155Z" }, + { url = "https://files.pythonhosted.org/packages/1f/d3/131dec79ce61c5567fecf82515bd9bc36395df42501b50f7f7f3bd065df0/lxml-6.0.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:370cd78d5855cfbffd57c422851f7d3864e6ae72d0da615fca4dad8c45d375a5", size = 5102953, upload-time = "2025-09-22T04:02:36.054Z" }, + { url = "https://files.pythonhosted.org/packages/3a/ea/a43ba9bb750d4ffdd885f2cd333572f5bb900cd2408b67fdda07e85978a0/lxml-6.0.2-cp314-cp314-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:901e3b4219fa04ef766885fb40fa516a71662a4c61b80c94d25336b4934b71c0", size = 5055054, upload-time = "2025-09-22T04:02:38.154Z" }, + { url = "https://files.pythonhosted.org/packages/60/23/6885b451636ae286c34628f70a7ed1fcc759f8d9ad382d132e1c8d3d9bfd/lxml-6.0.2-cp314-cp314-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:a4bf42d2e4cf52c28cc1812d62426b9503cdb0c87a6de81442626aa7d69707ba", size = 5352421, upload-time = "2025-09-22T04:02:40.413Z" }, + { url = "https://files.pythonhosted.org/packages/48/5b/fc2ddfc94ddbe3eebb8e9af6e3fd65e2feba4967f6a4e9683875c394c2d8/lxml-6.0.2-cp314-cp314-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:b2c7fdaa4d7c3d886a42534adec7cfac73860b89b4e5298752f60aa5984641a0", size = 5673684, upload-time = "2025-09-22T04:02:42.288Z" }, + { url = "https://files.pythonhosted.org/packages/29/9c/47293c58cc91769130fbf85531280e8cc7868f7fbb6d92f4670071b9cb3e/lxml-6.0.2-cp314-cp314-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:98a5e1660dc7de2200b00d53fa00bcd3c35a3608c305d45a7bbcaf29fa16e83d", size = 5252463, upload-time = "2025-09-22T04:02:44.165Z" }, + { url = "https://files.pythonhosted.org/packages/9b/da/ba6eceb830c762b48e711ded880d7e3e89fc6c7323e587c36540b6b23c6b/lxml-6.0.2-cp314-cp314-manylinux_2_31_armv7l.whl", hash = "sha256:dc051506c30b609238d79eda75ee9cab3e520570ec8219844a72a46020901e37", size = 4698437, upload-time = "2025-09-22T04:02:46.524Z" }, + { url = "https://files.pythonhosted.org/packages/a5/24/7be3f82cb7990b89118d944b619e53c656c97dc89c28cfb143fdb7cd6f4d/lxml-6.0.2-cp314-cp314-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:8799481bbdd212470d17513a54d568f44416db01250f49449647b5ab5b5dccb9", size = 5269890, upload-time = "2025-09-22T04:02:48.812Z" }, + { url = "https://files.pythonhosted.org/packages/1b/bd/dcfb9ea1e16c665efd7538fc5d5c34071276ce9220e234217682e7d2c4a5/lxml-6.0.2-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9261bb77c2dab42f3ecd9103951aeca2c40277701eb7e912c545c1b16e0e4917", size = 5097185, upload-time = "2025-09-22T04:02:50.746Z" }, + { url = "https://files.pythonhosted.org/packages/21/04/a60b0ff9314736316f28316b694bccbbabe100f8483ad83852d77fc7468e/lxml-6.0.2-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:65ac4a01aba353cfa6d5725b95d7aed6356ddc0a3cd734de00124d285b04b64f", size = 4745895, upload-time = "2025-09-22T04:02:52.968Z" }, + { url = "https://files.pythonhosted.org/packages/d6/bd/7d54bd1846e5a310d9c715921c5faa71cf5c0853372adf78aee70c8d7aa2/lxml-6.0.2-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:b22a07cbb82fea98f8a2fd814f3d1811ff9ed76d0fc6abc84eb21527596e7cc8", size = 5695246, upload-time = "2025-09-22T04:02:54.798Z" }, + { url = "https://files.pythonhosted.org/packages/fd/32/5643d6ab947bc371da21323acb2a6e603cedbe71cb4c99c8254289ab6f4e/lxml-6.0.2-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:d759cdd7f3e055d6bc8d9bec3ad905227b2e4c785dc16c372eb5b5e83123f48a", size = 5260797, upload-time = "2025-09-22T04:02:57.058Z" }, + { url = "https://files.pythonhosted.org/packages/33/da/34c1ec4cff1eea7d0b4cd44af8411806ed943141804ac9c5d565302afb78/lxml-6.0.2-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:945da35a48d193d27c188037a05fec5492937f66fb1958c24fc761fb9d40d43c", size = 5277404, upload-time = "2025-09-22T04:02:58.966Z" }, + { url = "https://files.pythonhosted.org/packages/82/57/4eca3e31e54dc89e2c3507e1cd411074a17565fa5ffc437c4ae0a00d439e/lxml-6.0.2-cp314-cp314-win32.whl", hash = "sha256:be3aaa60da67e6153eb15715cc2e19091af5dc75faef8b8a585aea372507384b", size = 3670072, upload-time = "2025-09-22T04:03:38.05Z" }, + { url = "https://files.pythonhosted.org/packages/e3/e0/c96cf13eccd20c9421ba910304dae0f619724dcf1702864fd59dd386404d/lxml-6.0.2-cp314-cp314-win_amd64.whl", hash = "sha256:fa25afbadead523f7001caf0c2382afd272c315a033a7b06336da2637d92d6ed", size = 4080617, upload-time = "2025-09-22T04:03:39.835Z" }, + { url = "https://files.pythonhosted.org/packages/d5/5d/b3f03e22b3d38d6f188ef044900a9b29b2fe0aebb94625ce9fe244011d34/lxml-6.0.2-cp314-cp314-win_arm64.whl", hash = "sha256:063eccf89df5b24e361b123e257e437f9e9878f425ee9aae3144c77faf6da6d8", size = 3754930, upload-time = "2025-09-22T04:03:41.565Z" }, + { url = "https://files.pythonhosted.org/packages/5e/5c/42c2c4c03554580708fc738d13414801f340c04c3eff90d8d2d227145275/lxml-6.0.2-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:6162a86d86893d63084faaf4ff937b3daea233e3682fb4474db07395794fa80d", size = 8910380, upload-time = "2025-09-22T04:03:01.645Z" }, + { url = "https://files.pythonhosted.org/packages/bf/4f/12df843e3e10d18d468a7557058f8d3733e8b6e12401f30b1ef29360740f/lxml-6.0.2-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:414aaa94e974e23a3e92e7ca5b97d10c0cf37b6481f50911032c69eeb3991bba", size = 4775632, upload-time = "2025-09-22T04:03:03.814Z" }, + { url = "https://files.pythonhosted.org/packages/e4/0c/9dc31e6c2d0d418483cbcb469d1f5a582a1cd00a1f4081953d44051f3c50/lxml-6.0.2-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:48461bd21625458dd01e14e2c38dd0aea69addc3c4f960c30d9f59d7f93be601", size = 4975171, upload-time = "2025-09-22T04:03:05.651Z" }, + { url = "https://files.pythonhosted.org/packages/e7/2b/9b870c6ca24c841bdd887504808f0417aa9d8d564114689266f19ddf29c8/lxml-6.0.2-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:25fcc59afc57d527cfc78a58f40ab4c9b8fd096a9a3f964d2781ffb6eb33f4ed", size = 5110109, upload-time = "2025-09-22T04:03:07.452Z" }, + { url = "https://files.pythonhosted.org/packages/bf/0c/4f5f2a4dd319a178912751564471355d9019e220c20d7db3fb8307ed8582/lxml-6.0.2-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5179c60288204e6ddde3f774a93350177e08876eaf3ab78aa3a3649d43eb7d37", size = 5041061, upload-time = "2025-09-22T04:03:09.297Z" }, + { url = "https://files.pythonhosted.org/packages/12/64/554eed290365267671fe001a20d72d14f468ae4e6acef1e179b039436967/lxml-6.0.2-cp314-cp314t-manylinux_2_26_i686.manylinux_2_28_i686.whl", hash = "sha256:967aab75434de148ec80597b75062d8123cadf2943fb4281f385141e18b21338", size = 5306233, upload-time = "2025-09-22T04:03:11.651Z" }, + { url = "https://files.pythonhosted.org/packages/7a/31/1d748aa275e71802ad9722df32a7a35034246b42c0ecdd8235412c3396ef/lxml-6.0.2-cp314-cp314t-manylinux_2_26_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:d100fcc8930d697c6561156c6810ab4a508fb264c8b6779e6e61e2ed5e7558f9", size = 5604739, upload-time = "2025-09-22T04:03:13.592Z" }, + { url = "https://files.pythonhosted.org/packages/8f/41/2c11916bcac09ed561adccacceaedd2bf0e0b25b297ea92aab99fd03d0fa/lxml-6.0.2-cp314-cp314t-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2ca59e7e13e5981175b8b3e4ab84d7da57993eeff53c07764dcebda0d0e64ecd", size = 5225119, upload-time = "2025-09-22T04:03:15.408Z" }, + { url = "https://files.pythonhosted.org/packages/99/05/4e5c2873d8f17aa018e6afde417c80cc5d0c33be4854cce3ef5670c49367/lxml-6.0.2-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:957448ac63a42e2e49531b9d6c0fa449a1970dbc32467aaad46f11545be9af1d", size = 4633665, upload-time = "2025-09-22T04:03:17.262Z" }, + { url = "https://files.pythonhosted.org/packages/0f/c9/dcc2da1bebd6275cdc723b515f93edf548b82f36a5458cca3578bc899332/lxml-6.0.2-cp314-cp314t-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:b7fc49c37f1786284b12af63152fe1d0990722497e2d5817acfe7a877522f9a9", size = 5234997, upload-time = "2025-09-22T04:03:19.14Z" }, + { url = "https://files.pythonhosted.org/packages/9c/e2/5172e4e7468afca64a37b81dba152fc5d90e30f9c83c7c3213d6a02a5ce4/lxml-6.0.2-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:e19e0643cc936a22e837f79d01a550678da8377d7d801a14487c10c34ee49c7e", size = 5090957, upload-time = "2025-09-22T04:03:21.436Z" }, + { url = "https://files.pythonhosted.org/packages/a5/b3/15461fd3e5cd4ddcb7938b87fc20b14ab113b92312fc97afe65cd7c85de1/lxml-6.0.2-cp314-cp314t-musllinux_1_2_armv7l.whl", hash = "sha256:1db01e5cf14345628e0cbe71067204db658e2fb8e51e7f33631f5f4735fefd8d", size = 4764372, upload-time = "2025-09-22T04:03:23.27Z" }, + { url = "https://files.pythonhosted.org/packages/05/33/f310b987c8bf9e61c4dd8e8035c416bd3230098f5e3cfa69fc4232de7059/lxml-6.0.2-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:875c6b5ab39ad5291588aed6925fac99d0097af0dd62f33c7b43736043d4a2ec", size = 5634653, upload-time = "2025-09-22T04:03:25.767Z" }, + { url = "https://files.pythonhosted.org/packages/70/ff/51c80e75e0bc9382158133bdcf4e339b5886c6ee2418b5199b3f1a61ed6d/lxml-6.0.2-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:cdcbed9ad19da81c480dfd6dd161886db6096083c9938ead313d94b30aadf272", size = 5233795, upload-time = "2025-09-22T04:03:27.62Z" }, + { url = "https://files.pythonhosted.org/packages/56/4d/4856e897df0d588789dd844dbed9d91782c4ef0b327f96ce53c807e13128/lxml-6.0.2-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:80dadc234ebc532e09be1975ff538d154a7fa61ea5031c03d25178855544728f", size = 5257023, upload-time = "2025-09-22T04:03:30.056Z" }, + { url = "https://files.pythonhosted.org/packages/0f/85/86766dfebfa87bea0ab78e9ff7a4b4b45225df4b4d3b8cc3c03c5cd68464/lxml-6.0.2-cp314-cp314t-win32.whl", hash = "sha256:da08e7bb297b04e893d91087df19638dc7a6bb858a954b0cc2b9f5053c922312", size = 3911420, upload-time = "2025-09-22T04:03:32.198Z" }, + { url = "https://files.pythonhosted.org/packages/fe/1a/b248b355834c8e32614650b8008c69ffeb0ceb149c793961dd8c0b991bb3/lxml-6.0.2-cp314-cp314t-win_amd64.whl", hash = "sha256:252a22982dca42f6155125ac76d3432e548a7625d56f5a273ee78a5057216eca", size = 4406837, upload-time = "2025-09-22T04:03:34.027Z" }, + { url = "https://files.pythonhosted.org/packages/92/aa/df863bcc39c5e0946263454aba394de8a9084dbaff8ad143846b0d844739/lxml-6.0.2-cp314-cp314t-win_arm64.whl", hash = "sha256:bb4c1847b303835d89d785a18801a883436cdfd5dc3d62947f9c49e24f0f5a2c", size = 3822205, upload-time = "2025-09-22T04:03:36.249Z" }, + { url = "https://files.pythonhosted.org/packages/0b/11/29d08bc103a62c0eba8016e7ed5aeebbf1e4312e83b0b1648dd203b0e87d/lxml-6.0.2-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:1c06035eafa8404b5cf475bb37a9f6088b0aca288d4ccc9d69389750d5543700", size = 3949829, upload-time = "2025-09-22T04:04:45.608Z" }, + { url = "https://files.pythonhosted.org/packages/12/b3/52ab9a3b31e5ab8238da241baa19eec44d2ab426532441ee607165aebb52/lxml-6.0.2-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:c7d13103045de1bdd6fe5d61802565f1a3537d70cd3abf596aa0af62761921ee", size = 4226277, upload-time = "2025-09-22T04:04:47.754Z" }, + { url = "https://files.pythonhosted.org/packages/a0/33/1eaf780c1baad88224611df13b1c2a9dfa460b526cacfe769103ff50d845/lxml-6.0.2-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:0a3c150a95fbe5ac91de323aa756219ef9cf7fde5a3f00e2281e30f33fa5fa4f", size = 4330433, upload-time = "2025-09-22T04:04:49.907Z" }, + { url = "https://files.pythonhosted.org/packages/7a/c1/27428a2ff348e994ab4f8777d3a0ad510b6b92d37718e5887d2da99952a2/lxml-6.0.2-pp311-pypy311_pp73-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:60fa43be34f78bebb27812ed90f1925ec99560b0fa1decdb7d12b84d857d31e9", size = 4272119, upload-time = "2025-09-22T04:04:51.801Z" }, + { url = "https://files.pythonhosted.org/packages/f0/d0/3020fa12bcec4ab62f97aab026d57c2f0cfd480a558758d9ca233bb6a79d/lxml-6.0.2-pp311-pypy311_pp73-manylinux_2_26_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:21c73b476d3cfe836be731225ec3421fa2f048d84f6df6a8e70433dff1376d5a", size = 4417314, upload-time = "2025-09-22T04:04:55.024Z" }, + { url = "https://files.pythonhosted.org/packages/6c/77/d7f491cbc05303ac6801651aabeb262d43f319288c1ea96c66b1d2692ff3/lxml-6.0.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:27220da5be049e936c3aca06f174e8827ca6445a4353a1995584311487fc4e3e", size = 3518768, upload-time = "2025-09-22T04:04:57.097Z" }, +] + +[[package]] +name = "packaging" +version = "25.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a1/d4/1fc4078c65507b51b96ca8f8c3ba19e6a61c8253c72794544580a7b6c24d/packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f", size = 165727, upload-time = "2025-04-19T11:48:59.673Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469, upload-time = "2025-04-19T11:48:57.875Z" }, +] + +[[package]] +name = "playwright" +version = "1.55.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "greenlet" }, + { name = "pyee" }, +] +wheels = [ + { url = "https://files.pythonhosted.org/packages/80/3a/c81ff76df266c62e24f19718df9c168f49af93cabdbc4608ae29656a9986/playwright-1.55.0-py3-none-macosx_10_13_x86_64.whl", hash = "sha256:d7da108a95001e412effca4f7610de79da1637ccdf670b1ae3fdc08b9694c034", size = 40428109, upload-time = "2025-08-28T15:46:20.357Z" }, + { url = "https://files.pythonhosted.org/packages/cf/f5/bdb61553b20e907196a38d864602a9b4a461660c3a111c67a35179b636fa/playwright-1.55.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:8290cf27a5d542e2682ac274da423941f879d07b001f6575a5a3a257b1d4ba1c", size = 38687254, upload-time = "2025-08-28T15:46:23.925Z" }, + { url = "https://files.pythonhosted.org/packages/4a/64/48b2837ef396487807e5ab53c76465747e34c7143fac4a084ef349c293a8/playwright-1.55.0-py3-none-macosx_11_0_universal2.whl", hash = "sha256:25b0d6b3fd991c315cca33c802cf617d52980108ab8431e3e1d37b5de755c10e", size = 40428108, upload-time = "2025-08-28T15:46:27.119Z" }, + { url = "https://files.pythonhosted.org/packages/08/33/858312628aa16a6de97839adc2ca28031ebc5391f96b6fb8fdf1fcb15d6c/playwright-1.55.0-py3-none-manylinux1_x86_64.whl", hash = "sha256:c6d4d8f6f8c66c483b0835569c7f0caa03230820af8e500c181c93509c92d831", size = 45905643, upload-time = "2025-08-28T15:46:30.312Z" }, + { url = "https://files.pythonhosted.org/packages/83/83/b8d06a5b5721931aa6d5916b83168e28bd891f38ff56fe92af7bdee9860f/playwright-1.55.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:29a0777c4ce1273acf90c87e4ae2fe0130182100d99bcd2ae5bf486093044838", size = 45296647, upload-time = "2025-08-28T15:46:33.221Z" }, + { url = "https://files.pythonhosted.org/packages/06/2e/9db64518aebcb3d6ef6cd6d4d01da741aff912c3f0314dadb61226c6a96a/playwright-1.55.0-py3-none-win32.whl", hash = "sha256:29e6d1558ad9d5b5c19cbec0a72f6a2e35e6353cd9f262e22148685b86759f90", size = 35476046, upload-time = "2025-08-28T15:46:36.184Z" }, + { url = "https://files.pythonhosted.org/packages/46/4f/9ba607fa94bb9cee3d4beb1c7b32c16efbfc9d69d5037fa85d10cafc618b/playwright-1.55.0-py3-none-win_amd64.whl", hash = "sha256:7eb5956473ca1951abb51537e6a0da55257bb2e25fc37c2b75af094a5c93736c", size = 35476048, upload-time = "2025-08-28T15:46:38.867Z" }, + { url = "https://files.pythonhosted.org/packages/21/98/5ca173c8ec906abde26c28e1ecb34887343fd71cc4136261b90036841323/playwright-1.55.0-py3-none-win_arm64.whl", hash = "sha256:012dc89ccdcbd774cdde8aeee14c08e0dd52ddb9135bf10e9db040527386bd76", size = 31225543, upload-time = "2025-08-28T15:46:41.613Z" }, +] + +[[package]] +name = "pluggy" +version = "1.6.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412, upload-time = "2025-05-15T12:30:07.975Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538, upload-time = "2025-05-15T12:30:06.134Z" }, +] + +[[package]] +name = "pyee" +version = "13.0.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/95/03/1fd98d5841cd7964a27d729ccf2199602fe05eb7a405c1462eb7277945ed/pyee-13.0.0.tar.gz", hash = "sha256:b391e3c5a434d1f5118a25615001dbc8f669cf410ab67d04c4d4e07c55481c37", size = 31250, upload-time = "2025-03-17T18:53:15.955Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/9b/4d/b9add7c84060d4c1906abe9a7e5359f2a60f7a9a4f67268b2766673427d8/pyee-13.0.0-py3-none-any.whl", hash = "sha256:48195a3cddb3b1515ce0695ed76036b5ccc2ef3a9f963ff9f77aec0139845498", size = 15730, upload-time = "2025-03-17T18:53:14.532Z" }, +] + +[[package]] +name = "pygments" +version = "2.19.2" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631, upload-time = "2025-06-21T13:39:12.283Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217, upload-time = "2025-06-21T13:39:07.939Z" }, +] + +[[package]] +name = "pytest" +version = "8.4.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "colorama", marker = "sys_platform == 'win32'" }, + { name = "iniconfig" }, + { name = "packaging" }, + { name = "pluggy" }, + { name = "pygments" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/a3/5c/00a0e072241553e1a7496d638deababa67c5058571567b92a7eaa258397c/pytest-8.4.2.tar.gz", hash = "sha256:86c0d0b93306b961d58d62a4db4879f27fe25513d4b969df351abdddb3c30e01", size = 1519618, upload-time = "2025-09-04T14:34:22.711Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a8/a4/20da314d277121d6534b3a980b29035dcd51e6744bd79075a6ce8fa4eb8d/pytest-8.4.2-py3-none-any.whl", hash = "sha256:872f880de3fc3a5bdc88a11b39c9710c3497a547cfa9320bc3c5e62fbf272e79", size = 365750, upload-time = "2025-09-04T14:34:20.226Z" }, +] + +[[package]] +name = "sniffio" +version = "1.3.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a2/87/a6771e1546d97e7e041b6ae58d80074f81b7d5121207425c964ddf5cfdbd/sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc", size = 20372, upload-time = "2024-02-25T23:20:04.057Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235, upload-time = "2024-02-25T23:20:01.196Z" }, +] + +[[package]] +name = "soupsieve" +version = "2.8" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/6d/e6/21ccce3262dd4889aa3332e5a119a3491a95e8f60939870a3a035aabac0d/soupsieve-2.8.tar.gz", hash = "sha256:e2dd4a40a628cb5f28f6d4b0db8800b8f581b65bb380b97de22ba5ca8d72572f", size = 103472, upload-time = "2025-08-27T15:39:51.78Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/14/a0/bb38d3b76b8cae341dad93a2dd83ab7462e6dbcdd84d43f54ee60a8dc167/soupsieve-2.8-py3-none-any.whl", hash = "sha256:0cc76456a30e20f5d7f2e14a98a4ae2ee4e5abdc7c5ea0aafe795f344bc7984c", size = 36679, upload-time = "2025-08-27T15:39:50.179Z" }, +] + +[[package]] +name = "typing-extensions" +version = "4.15.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" }, +] + +[[package]] +name = "ujson" +version = "5.11.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/43/d9/3f17e3c5773fb4941c68d9a37a47b1a79c9649d6c56aefbed87cc409d18a/ujson-5.11.0.tar.gz", hash = "sha256:e204ae6f909f099ba6b6b942131cee359ddda2b6e4ea39c12eb8b991fe2010e0", size = 7156583, upload-time = "2025-08-20T11:57:02.452Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/da/ea/80346b826349d60ca4d612a47cdf3533694e49b45e9d1c07071bb867a184/ujson-5.11.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d7c46cb0fe5e7056b9acb748a4c35aa1b428025853032540bb7e41f46767321f", size = 55248, upload-time = "2025-08-20T11:55:19.033Z" }, + { url = "https://files.pythonhosted.org/packages/57/df/b53e747562c89515e18156513cc7c8ced2e5e3fd6c654acaa8752ffd7cd9/ujson-5.11.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d8951bb7a505ab2a700e26f691bdfacf395bc7e3111e3416d325b513eea03a58", size = 53156, upload-time = "2025-08-20T11:55:20.174Z" }, + { url = "https://files.pythonhosted.org/packages/41/b8/ab67ec8c01b8a3721fd13e5cb9d85ab2a6066a3a5e9148d661a6870d6293/ujson-5.11.0-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:952c0be400229940248c0f5356514123d428cba1946af6fa2bbd7503395fef26", size = 57657, upload-time = "2025-08-20T11:55:21.296Z" }, + { url = "https://files.pythonhosted.org/packages/7b/c7/fb84f27cd80a2c7e2d3c6012367aecade0da936790429801803fa8d4bffc/ujson-5.11.0-cp311-cp311-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:94fcae844f1e302f6f8095c5d1c45a2f0bfb928cccf9f1b99e3ace634b980a2a", size = 59779, upload-time = "2025-08-20T11:55:22.772Z" }, + { url = "https://files.pythonhosted.org/packages/5d/7c/48706f7c1e917ecb97ddcfb7b1d756040b86ed38290e28579d63bd3fcc48/ujson-5.11.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7e0ec1646db172beb8d3df4c32a9d78015e671d2000af548252769e33079d9a6", size = 57284, upload-time = "2025-08-20T11:55:24.01Z" }, + { url = "https://files.pythonhosted.org/packages/ec/ce/48877c6eb4afddfd6bd1db6be34456538c07ca2d6ed233d3f6c6efc2efe8/ujson-5.11.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:da473b23e3a54448b008d33f742bcd6d5fb2a897e42d1fc6e7bf306ea5d18b1b", size = 1036395, upload-time = "2025-08-20T11:55:25.725Z" }, + { url = "https://files.pythonhosted.org/packages/8b/7a/2c20dc97ad70cd7c31ad0596ba8e2cf8794d77191ba4d1e0bded69865477/ujson-5.11.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:aa6b3d4f1c0d3f82930f4cbd7fe46d905a4a9205a7c13279789c1263faf06dba", size = 1195731, upload-time = "2025-08-20T11:55:27.915Z" }, + { url = "https://files.pythonhosted.org/packages/15/f5/ca454f2f6a2c840394b6f162fff2801450803f4ff56c7af8ce37640b8a2a/ujson-5.11.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4843f3ab4fe1cc596bb7e02228ef4c25d35b4bb0809d6a260852a4bfcab37ba3", size = 1088710, upload-time = "2025-08-20T11:55:29.426Z" }, + { url = "https://files.pythonhosted.org/packages/fe/d3/9ba310e07969bc9906eb7548731e33a0f448b122ad9705fed699c9b29345/ujson-5.11.0-cp311-cp311-win32.whl", hash = "sha256:e979fbc469a7f77f04ec2f4e853ba00c441bf2b06720aa259f0f720561335e34", size = 39648, upload-time = "2025-08-20T11:55:31.194Z" }, + { url = "https://files.pythonhosted.org/packages/57/f7/da05b4a8819f1360be9e71fb20182f0bb3ec611a36c3f213f4d20709e099/ujson-5.11.0-cp311-cp311-win_amd64.whl", hash = "sha256:683f57f0dd3acdd7d9aff1de0528d603aafcb0e6d126e3dc7ce8b020a28f5d01", size = 43717, upload-time = "2025-08-20T11:55:32.241Z" }, + { url = "https://files.pythonhosted.org/packages/9a/cc/f3f9ac0f24f00a623a48d97dc3814df5c2dc368cfb00031aa4141527a24b/ujson-5.11.0-cp311-cp311-win_arm64.whl", hash = "sha256:7855ccea3f8dad5e66d8445d754fc1cf80265a4272b5f8059ebc7ec29b8d0835", size = 38402, upload-time = "2025-08-20T11:55:33.641Z" }, + { url = "https://files.pythonhosted.org/packages/b9/ef/a9cb1fce38f699123ff012161599fb9f2ff3f8d482b4b18c43a2dc35073f/ujson-5.11.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7895f0d2d53bd6aea11743bd56e3cb82d729980636cd0ed9b89418bf66591702", size = 55434, upload-time = "2025-08-20T11:55:34.987Z" }, + { url = "https://files.pythonhosted.org/packages/b1/05/dba51a00eb30bd947791b173766cbed3492269c150a7771d2750000c965f/ujson-5.11.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12b5e7e22a1fe01058000d1b317d3b65cc3daf61bd2ea7a2b76721fe160fa74d", size = 53190, upload-time = "2025-08-20T11:55:36.384Z" }, + { url = "https://files.pythonhosted.org/packages/03/3c/fd11a224f73fbffa299fb9644e425f38b38b30231f7923a088dd513aabb4/ujson-5.11.0-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0180a480a7d099082501cad1fe85252e4d4bf926b40960fb3d9e87a3a6fbbc80", size = 57600, upload-time = "2025-08-20T11:55:37.692Z" }, + { url = "https://files.pythonhosted.org/packages/55/b9/405103cae24899df688a3431c776e00528bd4799e7d68820e7ebcf824f92/ujson-5.11.0-cp312-cp312-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:fa79fdb47701942c2132a9dd2297a1a85941d966d8c87bfd9e29b0cf423f26cc", size = 59791, upload-time = "2025-08-20T11:55:38.877Z" }, + { url = "https://files.pythonhosted.org/packages/17/7b/2dcbc2bbfdbf68f2368fb21ab0f6735e872290bb604c75f6e06b81edcb3f/ujson-5.11.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8254e858437c00f17cb72e7a644fc42dad0ebb21ea981b71df6e84b1072aaa7c", size = 57356, upload-time = "2025-08-20T11:55:40.036Z" }, + { url = "https://files.pythonhosted.org/packages/d1/71/fea2ca18986a366c750767b694430d5ded6b20b6985fddca72f74af38a4c/ujson-5.11.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1aa8a2ab482f09f6c10fba37112af5f957689a79ea598399c85009f2f29898b5", size = 1036313, upload-time = "2025-08-20T11:55:41.408Z" }, + { url = "https://files.pythonhosted.org/packages/a3/bb/d4220bd7532eac6288d8115db51710fa2d7d271250797b0bfba9f1e755af/ujson-5.11.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a638425d3c6eed0318df663df44480f4a40dc87cc7c6da44d221418312f6413b", size = 1195782, upload-time = "2025-08-20T11:55:43.357Z" }, + { url = "https://files.pythonhosted.org/packages/80/47/226e540aa38878ce1194454385701d82df538ccb5ff8db2cf1641dde849a/ujson-5.11.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7e3cff632c1d78023b15f7e3a81c3745cd3f94c044d1e8fa8efbd6b161997bbc", size = 1088817, upload-time = "2025-08-20T11:55:45.262Z" }, + { url = "https://files.pythonhosted.org/packages/7e/81/546042f0b23c9040d61d46ea5ca76f0cc5e0d399180ddfb2ae976ebff5b5/ujson-5.11.0-cp312-cp312-win32.whl", hash = "sha256:be6b0eaf92cae8cdee4d4c9e074bde43ef1c590ed5ba037ea26c9632fb479c88", size = 39757, upload-time = "2025-08-20T11:55:46.522Z" }, + { url = "https://files.pythonhosted.org/packages/44/1b/27c05dc8c9728f44875d74b5bfa948ce91f6c33349232619279f35c6e817/ujson-5.11.0-cp312-cp312-win_amd64.whl", hash = "sha256:b7b136cc6abc7619124fd897ef75f8e63105298b5ca9bdf43ebd0e1fa0ee105f", size = 43859, upload-time = "2025-08-20T11:55:47.987Z" }, + { url = "https://files.pythonhosted.org/packages/22/2d/37b6557c97c3409c202c838aa9c960ca3896843b4295c4b7bb2bbd260664/ujson-5.11.0-cp312-cp312-win_arm64.whl", hash = "sha256:6cd2df62f24c506a0ba322d5e4fe4466d47a9467b57e881ee15a31f7ecf68ff6", size = 38361, upload-time = "2025-08-20T11:55:49.122Z" }, + { url = "https://files.pythonhosted.org/packages/1c/ec/2de9dd371d52c377abc05d2b725645326c4562fc87296a8907c7bcdf2db7/ujson-5.11.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:109f59885041b14ee9569bf0bb3f98579c3fa0652317b355669939e5fc5ede53", size = 55435, upload-time = "2025-08-20T11:55:50.243Z" }, + { url = "https://files.pythonhosted.org/packages/5b/a4/f611f816eac3a581d8a4372f6967c3ed41eddbae4008d1d77f223f1a4e0a/ujson-5.11.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a31c6b8004438e8c20fc55ac1c0e07dad42941db24176fe9acf2815971f8e752", size = 53193, upload-time = "2025-08-20T11:55:51.373Z" }, + { url = "https://files.pythonhosted.org/packages/e9/c5/c161940967184de96f5cbbbcce45b562a4bf851d60f4c677704b1770136d/ujson-5.11.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:78c684fb21255b9b90320ba7e199780f653e03f6c2528663768965f4126a5b50", size = 57603, upload-time = "2025-08-20T11:55:52.583Z" }, + { url = "https://files.pythonhosted.org/packages/2b/d6/c7b2444238f5b2e2d0e3dab300b9ddc3606e4b1f0e4bed5a48157cebc792/ujson-5.11.0-cp313-cp313-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:4c9f5d6a27d035dd90a146f7761c2272cf7103de5127c9ab9c4cd39ea61e878a", size = 59794, upload-time = "2025-08-20T11:55:53.69Z" }, + { url = "https://files.pythonhosted.org/packages/fe/a3/292551f936d3d02d9af148f53e1bc04306b00a7cf1fcbb86fa0d1c887242/ujson-5.11.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:837da4d27fed5fdc1b630bd18f519744b23a0b5ada1bbde1a36ba463f2900c03", size = 57363, upload-time = "2025-08-20T11:55:54.843Z" }, + { url = "https://files.pythonhosted.org/packages/90/a6/82cfa70448831b1a9e73f882225980b5c689bf539ec6400b31656a60ea46/ujson-5.11.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:787aff4a84da301b7f3bac09bc696e2e5670df829c6f8ecf39916b4e7e24e701", size = 1036311, upload-time = "2025-08-20T11:55:56.197Z" }, + { url = "https://files.pythonhosted.org/packages/84/5c/96e2266be50f21e9b27acaee8ca8f23ea0b85cb998c33d4f53147687839b/ujson-5.11.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:6dd703c3e86dc6f7044c5ac0b3ae079ed96bf297974598116aa5fb7f655c3a60", size = 1195783, upload-time = "2025-08-20T11:55:58.081Z" }, + { url = "https://files.pythonhosted.org/packages/8d/20/78abe3d808cf3bb3e76f71fca46cd208317bf461c905d79f0d26b9df20f1/ujson-5.11.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3772e4fe6b0c1e025ba3c50841a0ca4786825a4894c8411bf8d3afe3a8061328", size = 1088822, upload-time = "2025-08-20T11:55:59.469Z" }, + { url = "https://files.pythonhosted.org/packages/d8/50/8856e24bec5e2fc7f775d867aeb7a3f137359356200ac44658f1f2c834b2/ujson-5.11.0-cp313-cp313-win32.whl", hash = "sha256:8fa2af7c1459204b7a42e98263b069bd535ea0cd978b4d6982f35af5a04a4241", size = 39753, upload-time = "2025-08-20T11:56:01.345Z" }, + { url = "https://files.pythonhosted.org/packages/5b/d8/1baee0f4179a4d0f5ce086832147b6cc9b7731c24ca08e14a3fdb8d39c32/ujson-5.11.0-cp313-cp313-win_amd64.whl", hash = "sha256:34032aeca4510a7c7102bd5933f59a37f63891f30a0706fb46487ab6f0edf8f0", size = 43866, upload-time = "2025-08-20T11:56:02.552Z" }, + { url = "https://files.pythonhosted.org/packages/a9/8c/6d85ef5be82c6d66adced3ec5ef23353ed710a11f70b0b6a836878396334/ujson-5.11.0-cp313-cp313-win_arm64.whl", hash = "sha256:ce076f2df2e1aa62b685086fbad67f2b1d3048369664b4cdccc50707325401f9", size = 38363, upload-time = "2025-08-20T11:56:03.688Z" }, + { url = "https://files.pythonhosted.org/packages/28/08/4518146f4984d112764b1dfa6fb7bad691c44a401adadaa5e23ccd930053/ujson-5.11.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:65724738c73645db88f70ba1f2e6fb678f913281804d5da2fd02c8c5839af302", size = 55462, upload-time = "2025-08-20T11:56:04.873Z" }, + { url = "https://files.pythonhosted.org/packages/29/37/2107b9a62168867a692654d8766b81bd2fd1e1ba13e2ec90555861e02b0c/ujson-5.11.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:29113c003ca33ab71b1b480bde952fbab2a0b6b03a4ee4c3d71687cdcbd1a29d", size = 53246, upload-time = "2025-08-20T11:56:06.054Z" }, + { url = "https://files.pythonhosted.org/packages/9b/f8/25583c70f83788edbe3ca62ce6c1b79eff465d78dec5eb2b2b56b3e98b33/ujson-5.11.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c44c703842024d796b4c78542a6fcd5c3cb948b9fc2a73ee65b9c86a22ee3638", size = 57631, upload-time = "2025-08-20T11:56:07.374Z" }, + { url = "https://files.pythonhosted.org/packages/ed/ca/19b3a632933a09d696f10dc1b0dfa1d692e65ad507d12340116ce4f67967/ujson-5.11.0-cp314-cp314-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:e750c436fb90edf85585f5c62a35b35082502383840962c6983403d1bd96a02c", size = 59877, upload-time = "2025-08-20T11:56:08.534Z" }, + { url = "https://files.pythonhosted.org/packages/55/7a/4572af5324ad4b2bfdd2321e898a527050290147b4ea337a79a0e4e87ec7/ujson-5.11.0-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f278b31a7c52eb0947b2db55a5133fbc46b6f0ef49972cd1a80843b72e135aba", size = 57363, upload-time = "2025-08-20T11:56:09.758Z" }, + { url = "https://files.pythonhosted.org/packages/7b/71/a2b8c19cf4e1efe53cf439cdf7198ac60ae15471d2f1040b490c1f0f831f/ujson-5.11.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ab2cb8351d976e788669c8281465d44d4e94413718af497b4e7342d7b2f78018", size = 1036394, upload-time = "2025-08-20T11:56:11.168Z" }, + { url = "https://files.pythonhosted.org/packages/7a/3e/7b98668cba3bb3735929c31b999b374ebc02c19dfa98dfebaeeb5c8597ca/ujson-5.11.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:090b4d11b380ae25453100b722d0609d5051ffe98f80ec52853ccf8249dfd840", size = 1195837, upload-time = "2025-08-20T11:56:12.6Z" }, + { url = "https://files.pythonhosted.org/packages/a1/ea/8870f208c20b43571a5c409ebb2fe9b9dba5f494e9e60f9314ac01ea8f78/ujson-5.11.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:80017e870d882d5517d28995b62e4e518a894f932f1e242cbc802a2fd64d365c", size = 1088837, upload-time = "2025-08-20T11:56:14.15Z" }, + { url = "https://files.pythonhosted.org/packages/63/b6/c0e6607e37fa47929920a685a968c6b990a802dec65e9c5181e97845985d/ujson-5.11.0-cp314-cp314-win32.whl", hash = "sha256:1d663b96eb34c93392e9caae19c099ec4133ba21654b081956613327f0e973ac", size = 41022, upload-time = "2025-08-20T11:56:15.509Z" }, + { url = "https://files.pythonhosted.org/packages/4e/56/f4fe86b4c9000affd63e9219e59b222dc48b01c534533093e798bf617a7e/ujson-5.11.0-cp314-cp314-win_amd64.whl", hash = "sha256:849e65b696f0d242833f1df4182096cedc50d414215d1371fca85c541fbff629", size = 45111, upload-time = "2025-08-20T11:56:16.597Z" }, + { url = "https://files.pythonhosted.org/packages/0a/f3/669437f0280308db4783b12a6d88c00730b394327d8334cc7a32ef218e64/ujson-5.11.0-cp314-cp314-win_arm64.whl", hash = "sha256:e73df8648c9470af2b6a6bf5250d4744ad2cf3d774dcf8c6e31f018bdd04d764", size = 39682, upload-time = "2025-08-20T11:56:17.763Z" }, + { url = "https://files.pythonhosted.org/packages/6e/cd/e9809b064a89fe5c4184649adeb13c1b98652db3f8518980b04227358574/ujson-5.11.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:de6e88f62796372fba1de973c11138f197d3e0e1d80bcb2b8aae1e826096d433", size = 55759, upload-time = "2025-08-20T11:56:18.882Z" }, + { url = "https://files.pythonhosted.org/packages/1b/be/ae26a6321179ebbb3a2e2685b9007c71bcda41ad7a77bbbe164005e956fc/ujson-5.11.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:49e56ef8066f11b80d620985ae36869a3ff7e4b74c3b6129182ec5d1df0255f3", size = 53634, upload-time = "2025-08-20T11:56:20.012Z" }, + { url = "https://files.pythonhosted.org/packages/ae/e9/fb4a220ee6939db099f4cfeeae796ecb91e7584ad4d445d4ca7f994a9135/ujson-5.11.0-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1a325fd2c3a056cf6c8e023f74a0c478dd282a93141356ae7f16d5309f5ff823", size = 58547, upload-time = "2025-08-20T11:56:21.175Z" }, + { url = "https://files.pythonhosted.org/packages/bd/f8/fc4b952b8f5fea09ea3397a0bd0ad019e474b204cabcb947cead5d4d1ffc/ujson-5.11.0-cp314-cp314t-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:a0af6574fc1d9d53f4ff371f58c96673e6d988ed2b5bf666a6143c782fa007e9", size = 60489, upload-time = "2025-08-20T11:56:22.342Z" }, + { url = "https://files.pythonhosted.org/packages/2e/e5/af5491dfda4f8b77e24cf3da68ee0d1552f99a13e5c622f4cef1380925c3/ujson-5.11.0-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:10f29e71ecf4ecd93a6610bd8efa8e7b6467454a363c3d6416db65de883eb076", size = 58035, upload-time = "2025-08-20T11:56:23.92Z" }, + { url = "https://files.pythonhosted.org/packages/c4/09/0945349dd41f25cc8c38d78ace49f14c5052c5bbb7257d2f466fa7bdb533/ujson-5.11.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:1a0a9b76a89827a592656fe12e000cf4f12da9692f51a841a4a07aa4c7ecc41c", size = 1037212, upload-time = "2025-08-20T11:56:25.274Z" }, + { url = "https://files.pythonhosted.org/packages/49/44/8e04496acb3d5a1cbee3a54828d9652f67a37523efa3d3b18a347339680a/ujson-5.11.0-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:b16930f6a0753cdc7d637b33b4e8f10d5e351e1fb83872ba6375f1e87be39746", size = 1196500, upload-time = "2025-08-20T11:56:27.517Z" }, + { url = "https://files.pythonhosted.org/packages/64/ae/4bc825860d679a0f208a19af2f39206dfd804ace2403330fdc3170334a2f/ujson-5.11.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:04c41afc195fd477a59db3a84d5b83a871bd648ef371cf8c6f43072d89144eef", size = 1089487, upload-time = "2025-08-20T11:56:29.07Z" }, + { url = "https://files.pythonhosted.org/packages/30/ed/5a057199fb0a5deabe0957073a1c1c1c02a3e99476cd03daee98ea21fa57/ujson-5.11.0-cp314-cp314t-win32.whl", hash = "sha256:aa6d7a5e09217ff93234e050e3e380da62b084e26b9f2e277d2606406a2fc2e5", size = 41859, upload-time = "2025-08-20T11:56:30.495Z" }, + { url = "https://files.pythonhosted.org/packages/aa/03/b19c6176bdf1dc13ed84b886e99677a52764861b6cc023d5e7b6ebda249d/ujson-5.11.0-cp314-cp314t-win_amd64.whl", hash = "sha256:48055e1061c1bb1f79e75b4ac39e821f3f35a9b82de17fce92c3140149009bec", size = 46183, upload-time = "2025-08-20T11:56:31.574Z" }, + { url = "https://files.pythonhosted.org/packages/5d/ca/a0413a3874b2dc1708b8796ca895bf363292f9c70b2e8ca482b7dbc0259d/ujson-5.11.0-cp314-cp314t-win_arm64.whl", hash = "sha256:1194b943e951092db611011cb8dbdb6cf94a3b816ed07906e14d3bc6ce0e90ab", size = 40264, upload-time = "2025-08-20T11:56:32.773Z" }, + { url = "https://files.pythonhosted.org/packages/50/17/30275aa2933430d8c0c4ead951cc4fdb922f575a349aa0b48a6f35449e97/ujson-5.11.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:abae0fb58cc820092a0e9e8ba0051ac4583958495bfa5262a12f628249e3b362", size = 51206, upload-time = "2025-08-20T11:56:48.797Z" }, + { url = "https://files.pythonhosted.org/packages/c3/15/42b3924258eac2551f8f33fa4e35da20a06a53857ccf3d4deb5e5d7c0b6c/ujson-5.11.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:fac6c0649d6b7c3682a0a6e18d3de6857977378dce8d419f57a0b20e3d775b39", size = 48907, upload-time = "2025-08-20T11:56:50.136Z" }, + { url = "https://files.pythonhosted.org/packages/94/7e/0519ff7955aba581d1fe1fb1ca0e452471250455d182f686db5ac9e46119/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4b42c115c7c6012506e8168315150d1e3f76e7ba0f4f95616f4ee599a1372bbc", size = 50319, upload-time = "2025-08-20T11:56:51.63Z" }, + { url = "https://files.pythonhosted.org/packages/74/cf/209d90506b7d6c5873f82c5a226d7aad1a1da153364e9ebf61eff0740c33/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:86baf341d90b566d61a394869ce77188cc8668f76d7bb2c311d77a00f4bdf844", size = 56584, upload-time = "2025-08-20T11:56:52.89Z" }, + { url = "https://files.pythonhosted.org/packages/e9/97/bd939bb76943cb0e1d2b692d7e68629f51c711ef60425fa5bb6968037ecd/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4598bf3965fc1a936bd84034312bcbe00ba87880ef1ee33e33c1e88f2c398b49", size = 51588, upload-time = "2025-08-20T11:56:54.054Z" }, + { url = "https://files.pythonhosted.org/packages/52/5b/8c5e33228f7f83f05719964db59f3f9f276d272dc43752fa3bbf0df53e7b/ujson-5.11.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:416389ec19ef5f2013592f791486bef712ebce0cd59299bf9df1ba40bb2f6e04", size = 43835, upload-time = "2025-08-20T11:56:55.237Z" }, +]