http-content-parser 0.0.21__tar.gz → 0.0.22__tar.gz

{http_content_parser-0.0.21 → http_content_parser-0.0.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: http_content_parser
-Version: 0.0.21
+Version: 0.0.22
 Summary: parse http's payload and response
 Author-email: leo <suleiabc@gmail.com>
 License-File: LICENSE

{http_content_parser-0.0.21 → http_content_parser-0.0.22}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "http_content_parser"
-version = "0.0.21"
+version = "0.0.22"
 authors = [{ name = "leo", email = "suleiabc@gmail.com" }]
 description = "parse http's payload and response"
 readme = "README.md"

{http_content_parser-0.0.21 → http_content_parser-0.0.22}/src/http_content_parser/curl_parser.py

@@ -64,7 +64,7 @@ class CurlParser(object):
                 line_num_array.append([start_num, num])
         return line_num_array
 
-    def split_curl_to_struct(self, lines, s, e, url_filter=None) -> dict:
+    def split_curl_to_struct_old(self, lines, s, e, url_filter=None) -> dict:
         req_data = {}
         header = {}
         reduced_lines = self.reduce_curl_data_part(lines=lines, s=s, e=e)
@@ -109,7 +109,6 @@ class CurlParser(object):
                 else:
                     curl_data = line_i_list[0]
                 body = re.sub(r"\n\s*", "", curl_data.replace(" \\\n", ""))
-                # body = re.sub(r"\s*", "", curl_data.replace(" \\\n", ""))
                 req_data["body"] = body[:-1]
 
                 if not req_data.get("method"):
@@ -120,3 +119,82 @@ class CurlParser(object):
             req_data["method"] = "get"
 
         return req_data
+
+    def split_curl_to_struct(self, lines, s, e, url_filter=None) -> dict:
+        req_data = {}
+        header = {}
+
+        reduced_lines = self.reduce_curl_data_part(lines=lines, s=s, e=e)
+
+        for line in reduced_lines:
+            line = str(line).strip()
+
+            # ---------------------------
+            # 解析 method 和 URL
+            # ---------------------------
+            if line.startswith("curl"):
+                parts = line.split()
+
+                for part in parts:
+                    p = part.strip("'\"")
+
+                    # method
+                    if p.lower() in ["get", "post", "put", "delete"]:
+                        req_data["method"] = p.lower()
+
+                    # URL
+                    elif p.startswith("http"):
+                        req_data["original_url"] = p
+                    elif "/" in p and "://" not in p:  # Postman 样式
+                        req_data["original_url"] = p
+
+                # url_filter
+                if url_filter and url_filter not in line:
+                    continue
+
+            # ---------------------------
+            # -X METHOD
+            # ---------------------------
+            elif line.startswith("-X") or " -X " in line:
+                # 例如：-X POST
+                parts = line.replace("\\", "").split()
+                if len(parts) >= 2:
+                    req_data["method"] = parts[1].strip("'\"").lower()
+
+            # ---------------------------
+            # Header 解析
+            # ---------------------------
+            elif line.startswith("-H") or "--header" in line:
+                # 支持各种写法
+                m = re.search(r"'(.+?):\s*(.+?)'", line)
+                if m:
+                    key = m.group(1)
+                    val = m.group(2)
+                    header[key] = val
+
+            # ---------------------------
+            # Body 解析
+            # ---------------------------
+            elif "--data" in line or "--data-raw" in line:
+                # 去掉行尾的转义符
+                clean = line.replace("\\\n", "").strip()
+
+                # 提取单引号内容
+                m = re.search(r"'(.*)'$", clean)
+                if m:
+                    req_data["body"] = m.group(1)
+                else:
+                    # 兼容无引号情况
+                    req_data["body"] = clean.split("--data")[-1].strip()
+
+                # 如果没有 method，则默认 POST
+                req_data.setdefault("method", "post")
+
+        # ---------------------------
+        # 最终补齐数据
+        # ---------------------------
+        req_data.setdefault("method", "get")
+        req_data["header"] = header
+        req_data.setdefault("original_url", "")
+
+        return req_data

{http_content_parser-0.0.21 → http_content_parser-0.0.22}/tests/test_api_model_parser.py

@@ -1,3 +1,4 @@
+import json
 from http_content_parser.api_parser import ApiModelParser
 
 
@@ -7,4 +8,4 @@ api_parser = ApiModelParser()
 def test_curl_parser():
     curl_file = "./tmp"
     api_info = api_parser.get_api_list_for_curl(curl_file=curl_file)
-    print(api_info)
+    print(json.dumps(api_info, indent=4))