quickquery 0.1.1__tar.gz → 0.1.3__tar.gz

{quickquery-0.1.1 → quickquery-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quickquery
-Version: 0.1.1
+Version: 0.1.3
 Summary: 自分用・非汎用
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -13,66 +13,14 @@ Requires-Dist: camoufox>=0.4
 Requires-Dist: loguru>=0.7
 Requires-Dist: tqdm>=4.66
 
-# QuickQuery
-
 自分用・非汎用
 
 ## インストール
 `uv add quickquery`  
 
-※ `open_patchright` を使うとき：Google ChromeをPCにインストールしておく。  
-※ `open_camoufox` を使うとき：`uv run camoufox fetch`  
-
-## 実装機能
-
-### quickquery
-
-- `quick_page(page: Page) -> QuickPage`
-- `quick_element(page: Page, elem: ElementHandle | None) -> QuickElement`
-- `quick_element_group(page: Page, elems: list[QuickElement]) -> QuickElementGroup`
-- `quick_frame(page: Page, frame: Frame | None) -> QuickFrame`
-- `quick_shadow_root(page: Page, host: ElementHandle | None) -> QuickShadowRoot`
-- `quick_parser(parser: LexborHTMLParser) -> QuickParser`
-- `quick_node(node: LexborNode | None) -> QuickNode`
-- `quick_node_group(nodes: list[QuickNode]) -> QuickNodeGroup`
-- `QuickPage`
-- `QuickElement`
-- `QuickElementGroup`
-- `ElementScan`
-- `QuickFrame`
-- `QuickShadowRoot`
-- `QuickParser`
-- `QuickNode`
-- `QuickNodeGroup`
-- `NodeScan`
-
-### quickquery.utils
-
-- `parse_html(path: Path) -> LexborHTMLParser | None`
-- `meta_html(meta: Mapping[str, object | None]) -> str`
-- `from_here(file: str) -> Callable[[str], Path]`
-- `append_csv(path: Path, row: dict) -> None`
-- `write_csv(path: Path, rows: list[dict]) -> None`
-- `write_parquet(path: Path, rows: list[dict]) -> None`
-- `hash_name(key: str) -> str`
-- `write_text(path: Path, data: str) -> bool`
-- `write_bytes(path: Path, data: bytes) -> bool`
-- `save_log(path: Path, level: str = 'WARNING') -> None`
-- `process_map[T, R](worker: Callable[[T], R], items: Iterable[T], workers: int | None = None, *, chunksize: int | None = None) -> list[R | None]`
-- `glob_paths(dir_path: Path, pattern: str = '*.html') -> list[str]`
-- `counter(start: int = 1) -> Iterator[int]`
-
-### quickquery.live
-
-- `RecycleEvery`
-- `PatchrightSession`
-- `CamoufoxSession`
-- `open_patchright(*, browser_options: dict | None = None, context_options: dict | None = None, recycle: RecycleEvery | None = None) -> PatchrightSession`
-- `open_camoufox(*, browser_options: dict | None = None, context_options: dict | None = None, recycle: RecycleEvery | None = None) -> CamoufoxSession`
-- `PatchrightSession.page() -> Page`
-- `CamoufoxSession.page() -> Page`
-
-`browser_options` / `context_options` は Playwright へ渡す起動オプション。`recycle` は quickquery の再生成間隔（`page()` 呼び出し回数ごとに独立して効く。省略時は再生成しない）。`page()` を呼ぶたびに内部カウントが 1 進む。
+`open_patchright` を使うとき：Google ChromeをPCにインストールしておく。  
+`open_camoufox` を使うとき：`uv run camoufox fetch`  
+
 
 ## 使用例
 
@@ -163,8 +111,10 @@ with open_patchright(
             append_csv(here('csv/failed.csv'), {
                 'url_index': url_index,
                 'request_url': request_url,
+                'final_url': page.url,
                 'reason': 'write_text',
             })
+            continue
 
         page.screenshot(path=here(f'media/{url_index}-full-page.png'), full_page=True)
 
@@ -198,7 +148,7 @@ def main():
     write_parquet(here('parquet/extract.parquet'), results)
 
 def extract(file_path: str) -> dict | None:
-    if not (parser := parse_html(Path(file_path))):
+    if not (parser := parse_html(Path(file_path).read_bytes())):
         return None
     p = quick_parser(parser)
     dt_scan = p.ii('dt').scan

{quickquery-0.1.1 → quickquery-0.1.3}/README.md

@@ -1,63 +1,11 @@
-# QuickQuery
-
 自分用・非汎用
 
 ## インストール
 `uv add quickquery`  
 
-※ `open_patchright` を使うとき：Google ChromeをPCにインストールしておく。  
-※ `open_camoufox` を使うとき：`uv run camoufox fetch`  
-
-## 実装機能
-
-### quickquery
-
-- `quick_page(page: Page) -> QuickPage`
-- `quick_element(page: Page, elem: ElementHandle | None) -> QuickElement`
-- `quick_element_group(page: Page, elems: list[QuickElement]) -> QuickElementGroup`
-- `quick_frame(page: Page, frame: Frame | None) -> QuickFrame`
-- `quick_shadow_root(page: Page, host: ElementHandle | None) -> QuickShadowRoot`
-- `quick_parser(parser: LexborHTMLParser) -> QuickParser`
-- `quick_node(node: LexborNode | None) -> QuickNode`
-- `quick_node_group(nodes: list[QuickNode]) -> QuickNodeGroup`
-- `QuickPage`
-- `QuickElement`
-- `QuickElementGroup`
-- `ElementScan`
-- `QuickFrame`
-- `QuickShadowRoot`
-- `QuickParser`
-- `QuickNode`
-- `QuickNodeGroup`
-- `NodeScan`
-
-### quickquery.utils
-
-- `parse_html(path: Path) -> LexborHTMLParser | None`
-- `meta_html(meta: Mapping[str, object | None]) -> str`
-- `from_here(file: str) -> Callable[[str], Path]`
-- `append_csv(path: Path, row: dict) -> None`
-- `write_csv(path: Path, rows: list[dict]) -> None`
-- `write_parquet(path: Path, rows: list[dict]) -> None`
-- `hash_name(key: str) -> str`
-- `write_text(path: Path, data: str) -> bool`
-- `write_bytes(path: Path, data: bytes) -> bool`
-- `save_log(path: Path, level: str = 'WARNING') -> None`
-- `process_map[T, R](worker: Callable[[T], R], items: Iterable[T], workers: int | None = None, *, chunksize: int | None = None) -> list[R | None]`
-- `glob_paths(dir_path: Path, pattern: str = '*.html') -> list[str]`
-- `counter(start: int = 1) -> Iterator[int]`
-
-### quickquery.live
-
-- `RecycleEvery`
-- `PatchrightSession`
-- `CamoufoxSession`
-- `open_patchright(*, browser_options: dict | None = None, context_options: dict | None = None, recycle: RecycleEvery | None = None) -> PatchrightSession`
-- `open_camoufox(*, browser_options: dict | None = None, context_options: dict | None = None, recycle: RecycleEvery | None = None) -> CamoufoxSession`
-- `PatchrightSession.page() -> Page`
-- `CamoufoxSession.page() -> Page`
-
-`browser_options` / `context_options` は Playwright へ渡す起動オプション。`recycle` は quickquery の再生成間隔（`page()` 呼び出し回数ごとに独立して効く。省略時は再生成しない）。`page()` を呼ぶたびに内部カウントが 1 進む。
+`open_patchright` を使うとき：Google ChromeをPCにインストールしておく。  
+`open_camoufox` を使うとき：`uv run camoufox fetch`  
+
 
 ## 使用例
 
@@ -148,8 +96,10 @@ with open_patchright(
             append_csv(here('csv/failed.csv'), {
                 'url_index': url_index,
                 'request_url': request_url,
+                'final_url': page.url,
                 'reason': 'write_text',
             })
+            continue
 
         page.screenshot(path=here(f'media/{url_index}-full-page.png'), full_page=True)
 
@@ -183,7 +133,7 @@ def main():
     write_parquet(here('parquet/extract.parquet'), results)
 
 def extract(file_path: str) -> dict | None:
-    if not (parser := parse_html(Path(file_path))):
+    if not (parser := parse_html(Path(file_path).read_bytes())):
         return None
     p = quick_parser(parser)
     dt_scan = p.ii('dt').scan

{quickquery-0.1.1 → quickquery-0.1.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "quickquery"
-version = "0.1.1"
+version = "0.1.3"
 description = "自分用・非汎用"
 readme = "README.md"
 requires-python = ">=3.12"

{quickquery-0.1.1 → quickquery-0.1.3}/quickquery/live.py

@@ -36,8 +36,8 @@ class _SessionBase:
         recycle: RecycleEvery | None = None,
     ) -> None:
         self._recycle = recycle or RecycleEvery()
-        self._browser_options = dict(browser_options or {})
-        self._context_options = dict(context_options or {})
+        self._browser_options = browser_options or {}
+        self._context_options = context_options or {}
         self._browser = None
         self._context = None
         self._page: Page | None = None
@@ -47,7 +47,7 @@ class _SessionBase:
     def page(self) -> Page:
         if not self._entered:
             raise RuntimeError('with ブロックの外で page() を呼べません')
-        if self._page is None:
+        if self._browser is None:
             self._open_browser()
         elif (b := self._recycle.browser) and self._page_calls % b == 0:
             self._close_browser()
@@ -67,7 +67,7 @@ class _SessionBase:
     def _close_page(self) -> None:
         if self._page is not None:
             self._page.close()
-            self._page = None
+        self._page = None
 
     def _open_context(self) -> None:
         self._context = self._browser.new_context(**self._context_options)
@@ -77,7 +77,7 @@ class _SessionBase:
         self._close_page()
         if self._context is not None:
             self._context.close()
-            self._context = None
+        self._context = None
 
 
 class PatchrightSession(_SessionBase):
@@ -111,8 +111,8 @@ class PatchrightSession(_SessionBase):
         self._close_browser()
         self._pw.stop()
         self._pw = None
-        self._entered = False
         self._page_calls = 0
+        self._entered = False
 
     def _open_browser(self) -> None:
         self._browser = self._pw.chromium.launch(**self._browser_options)
@@ -153,19 +153,20 @@ class CamoufoxSession(_SessionBase):
         if not self._entered:
             return
         self._close_browser()
-        self._entered = False
         self._page_calls = 0
+        self._entered = False
 
     def _open_browser(self) -> None:
+        fox = Camoufox(**self._browser_options)
         self._stack = ExitStack()
-        self._browser = self._stack.enter_context(Camoufox(**self._browser_options))
+        self._browser = self._stack.enter_context(fox)
         self._open_context()
 
     def _close_browser(self) -> None:
         self._close_context()
         if self._stack is not None:
             self._stack.close()
-            self._stack = None
+        self._stack = None
         self._browser = None
 
 

{quickquery-0.1.1 → quickquery-0.1.3}/quickquery/utils.py

@@ -16,11 +16,11 @@ def _ensure_parent(path: Path) -> None:
     path.parent.mkdir(parents=True, exist_ok=True)
 
 
-def parse_html(path: Path) -> LexborHTMLParser | None:
+def parse_html(html: str | bytes) -> LexborHTMLParser | None:
     try:
-        return LexborHTMLParser(path.read_bytes())
+        return LexborHTMLParser(html)
     except Exception as e:
-        logger.error(f'[parse_html] {path} {type(e).__name__}: {e}')
+        logger.error(f'[parse_html] {type(e).__name__}: {e}')
         return None