ssc_codegen 0.19.2__tar.gz → 0.19.4__tar.gz

{ssc_codegen-0.19.2 → ssc_codegen-0.19.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.19.2
+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-0.19.2 → ssc_codegen-0.19.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.19.2"
+version = "0.19.4"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"

{ssc_codegen-0.19.2 → ssc_codegen-0.19.4}/ssc_codegen/parsers/curl.py

@@ -97,10 +97,10 @@ def parse_curl_to_httpx_kwargs(
                 raise ValueError(f"Invalid header format: {header}")
             key, value = header.split(":", 1)
             headers[key.strip()] = value.strip()
-        elif part in ("-d", "--data"):
+        elif part in ("-d", "--data", "--data-raw"):
             i += 1
             if i >= len(parts):
-                raise ValueError("Missing data after -d/--data")
+                raise ValueError("Missing data after -d/--data/--data-raw")
             data = parts[i]
         elif part == "--json":
             i += 1

{ssc_codegen-0.19.2 → 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
@@ -174,12 +177,31 @@ def _curl_raw_body(payload: str) -> str:
     parts = shlex.split(payload.strip())[1:]  # drop "curl"
     i = 0
     while i < len(parts):
-        if parts[i] in ("-d", "--data", "--json") and i + 1 < len(parts):
+        if parts[i] in ("-d", "--data", "--data-raw", "--json") and i + 1 < len(parts):
             return parts[i + 1]
         i += 1
     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