ssc_codegen 0.19.3__tar.gz → 0.19.4__tar.gz

{ssc_codegen-0.19.3 → ssc_codegen-0.19.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.19.3
+Version: 0.19.4
 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

{ssc_codegen-0.19.3 → ssc_codegen-0.19.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.19.3"
+version = "0.19.4"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"

{ssc_codegen-0.19.3 → ssc_codegen-0.19.4}/ssc_codegen/parsers/spec.py

@@ -146,6 +146,9 @@ def parse_to_spec(payload: str) -> RequestSpec:
             body = kwargs[
                 "data"
             ]  # dict with original values (may have placeholders)
+        elif "application/x-www-form-urlencoded" in content_type:
+            body_kind = "form"
+            body = _parse_urlencoded_body(raw_body)
         else:
             body_kind = "raw"
             body = raw_body
@@ -180,6 +183,25 @@ def _curl_raw_body(payload: str) -> str:
     return ""
 
 
+def _parse_urlencoded_body(raw: str) -> dict[str, str]:
+    """Split an application/x-www-form-urlencoded body into a dict.
+
+    Preserves ``{{placeholders}}`` intact; URL-decodes everything else so the
+    target HTTP client can re-encode without double-encoding.
+    """
+    from urllib.parse import unquote_plus
+
+    out: dict[str, str] = {}
+    if not raw:
+        return out
+    for pair in raw.split("&"):
+        if not pair:
+            continue
+        key, sep, value = pair.partition("=")
+        out[unquote_plus(key)] = unquote_plus(value) if sep else ""
+    return out
+
+
 def _http_raw_body(payload: str) -> str:
     lines = payload.strip().splitlines()
     i = 1