ssc_codegen 0.13.2__tar.gz → 0.13.4__tar.gz

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.13.2
+Version: 0.13.4
 Summary: Python-dsl code converter to html parser for web scraping 
 Project-URL: Documentation, https://github.com/vypivshiy/selector_schema_codegen#readme
 Project-URL: Issues, https://github.com/vypivshiy/selector_schema_codegen/issues
@@ -27,7 +27,6 @@ Requires-Dist: cssselect>=1.2.0
 Requires-Dist: httpx>=0.28.1
 Requires-Dist: ichrome>=4.0.4
 Requires-Dist: lxml>=5.3.0
-Requires-Dist: parsel>=1.10.0
 Requires-Dist: soupsieve>=2.6
 Requires-Dist: tinycss2>=1.4.0
 Requires-Dist: typer>=0.15.1

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.13.2"
+version = "0.13.4"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"
@@ -11,7 +11,6 @@ dependencies = [
     "httpx>=0.28.1",
     "ichrome>=4.0.4",
     "lxml>=5.3.0",
-    "parsel>=1.10.0",
     "soupsieve>=2.6",
     "typer>=0.15.1",
     "typing_extensions;python_version<'3.11'",

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/ssc_codegen/__init__.py

@@ -7,7 +7,7 @@ from ssc_codegen.schema import ItemSchema, DictSchema, ListSchema, FlatListSchem
 
 setup_logger()
 
-VERSION = "0.13.2"
+VERSION = "0.13.4"
 
 
 class __MISSING(object):

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/ssc_codegen/cli/ast_grep.py

@@ -4,5 +4,7 @@ from importlib import resources
 RULES_PATH = resources.files("ssc_codegen.ast_grep_rules")
 
 PY_RULES = str(RULES_PATH.joinpath("py_rules.yml"))
-PY_NEW_RM_PREFIX_SUFFIX_SYNTAX = str(RULES_PATH.joinpath("py_drop_prefix_suffix_backport.yml"))
+PY_NEW_RM_PREFIX_SUFFIX_SYNTAX = str(
+    RULES_PATH.joinpath("py_drop_prefix_suffix_backport.yml")
+)
 JS_RULES = str(RULES_PATH.joinpath("js_rules.yml"))

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/ssc_codegen/cli/main.py

@@ -11,7 +11,11 @@ from ichrome.exceptions import ChromeRuntimeError
 from typer import Argument, BadParameter, Option, Typer
 
 from ssc_codegen.ast_build import build_ast_module_parser
-from ssc_codegen.cli.ast_grep import JS_RULES, PY_RULES, PY_NEW_RM_PREFIX_SUFFIX_SYNTAX
+from ssc_codegen.cli.ast_grep import (
+    JS_RULES,
+    PY_RULES,
+    PY_NEW_RM_PREFIX_SUFFIX_SYNTAX,
+)
 from ssc_codegen.cli.cli_callbacks import cb_check_ssc_files, cb_folder_out
 from ssc_codegen.cli.cli_utils import (
     ConverterLike,
@@ -169,8 +173,13 @@ def gen_py(
         bool, Option(help=HELP_DOCSTRING, is_flag=True)
     ] = True,
     fmt_prefix_suffix_backport: Annotated[
-        bool, Option("-frps", '--fmt-remove-prefix-suffix',
-            help="[PY39+]: replace backport funcs to str.removeprefix(...) and str.removesuffix(...)")] = False
+        bool,
+        Option(
+            "-frps",
+            "--fmt-remove-prefix-suffix",
+            help="[PY39+]: replace backport funcs to str.removeprefix(...) and str.removesuffix(...)",
+        ),
+    ] = False,
 ) -> None:
     converter = import_converter(f"py_{lib.value}")
     if fmt:
@@ -180,13 +189,14 @@ def gen_py(
             f"ast-grep scan --rule {PY_RULES} -U " + "{}",
         ]
         if fmt_prefix_suffix_backport:
-            commands.append(f"ast-grep scan --rule {PY_NEW_RM_PREFIX_SUFFIX_SYNTAX} -U " + "{}")
+            commands.append(
+                f"ast-grep scan --rule {PY_NEW_RM_PREFIX_SUFFIX_SYNTAX} -U "
+                + "{}"
+            )
         fmt_cmd = create_fmt_cmd(ssc_files, prefix, suffix, out, commands)
     else:
         fmt_cmd = []
 
-
-
     generate_code(
         converter=converter,
         out=out,
@@ -429,7 +439,7 @@ def parse_from_file(
     ] = None,
 ) -> None:
     from ssc_codegen.compiler import Compiler
-    from ssc_codegen.converters.py_parsel import CONVERTER
+    from ssc_codegen.converters.py_lxml import CONVERTER
 
     cls_target, schema_config = _validate_parser_target(cls_target)
 
@@ -553,7 +563,7 @@ def parse_from_chrome_(
     from ssc_codegen.converters.js_pure import CONVERTER as JS_CONVERTER
     import asyncio
     from ssc_codegen.compiler import Compiler
-    from ssc_codegen.converters.py_parsel import CONVERTER
+    from ssc_codegen.converters.py_lxml import CONVERTER
 
     cls_target, schema_config = _validate_parser_target(cls_target)
 

{ssc_codegen-0.13.2 → ssc_codegen-0.13.4}/ssc_codegen/converters/py_lxml.py

@@ -62,15 +62,38 @@ from ssc_codegen.converters.templates.py_base import IMPORTS_MIN
 
 CONVERTER = BasePyCodeConverter()
 
+"""
+# HtmlElement → сразу принимаем
+if isinstance(document, html.HtmlElement):
+    self._document = document
+    return
+
+# Строка → пробуем парсить
+if isinstance(document, str):
+    try:
+        self._document = html.fromstring(document.strip() or self.FALLBACK_HTML)
+        return
+    except (ParserError, ValueError):
+        pass
+
+# Всё остальное или ошибка → заглушка
+self._document = html.fromstring(self.FALLBACK_HTML)
+"""
+
 
 @CONVERTER(StructInitMethod.kind)
 def pre_init(_node: StructInitMethod) -> str:
-    return (
+    parts = [
         INDENT_METHOD
-        + "def __init__(self, document: Union[str, html.HtmlElement]) -> None:\n"
-        + INDENT_METHOD_BODY
-        + "self._document = html.fromstring(document) if isinstance(document, str) else document"
-    )
+        + "def __init__(self, document: Union[str, html.HtmlElement]) -> None:",
+        INDENT_METHOD * 2 + "if isinstance(document, html.HtmlElement):",
+        INDENT_METHOD * 3 + "self._document = document",
+        INDENT_METHOD * 2 + "elif isinstance(document, str):",
+        INDENT_METHOD * 3
+        + "self._document = html.fromstring(document.strip() or FALLBACK_HTML_STR)",
+        # in codegen, passed only str or html.HtmlElement objects
+    ]
+    return "\n".join(parts)
 
 
 @CONVERTER(StructPreValidateMethod.kind)
@@ -101,7 +124,15 @@ def pre_struct_field_method(node: StructFieldMethod) -> str:
 
 @CONVERTER(ModuleImports.kind)
 def pre_imports(_: ModuleImports) -> str:
-    return IMPORTS_MIN + """from lxml import html, etree"""
+    # lxml throw parse error if passed empty string
+    # most mainsteram html parser libs use `FALLBACK_HTML_STR` stub value
+    return (
+        IMPORTS_MIN
+        + """from lxml import html, etree
+    
+FALLBACK_HTML_STR = "<html><body></body></html>"
+    """
+    )
 
 
 @CONVERTER(ExprCss.kind)