notoecd 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

notoecd/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 
 from .calls import get_df
 from .structure import get_structure

notoecd/datasets.py

@@ -18,43 +18,51 @@ NS = {
 _ws_re = re.compile(r"\s+")
 _tag_re = re.compile(r"<[^>]+>")
 
-def _clean_text(s: str | None) -> str | None:
+def _clean(s: str | None) -> str | None:
     if s is None: return None
     s = html.unescape(s)
     s = _tag_re.sub("", s)
     s = _ws_re.sub(" ", s).strip()
     return s or None
 
-headers = {
-    "Accept": "application/vnd.sdmx.structure+xml;version=2.1"
-}
+# Cache
+_datasets: pd.DataFrame | None = None
+
+def _load_datasets() -> pd.DataFrame:
+    """
+    Loads OECD datasets and keeps them in memory.
+    """
+    global _datasets
+    if _datasets is not None: return _datasets
+
+    headers = {"Accept": "application/vnd.sdmx.structure+xml;version=2.1"}
+    r = requests.get(url, headers=headers, timeout=30)
+    r.raise_for_status()
+    root = ET.fromstring(r.content)
+
+    rows = []
+    for df in root.findall(".//structure:Dataflow", NS):
+        dataflow_id = df.attrib.get("id")
+        agency_id = df.attrib.get("agencyID")
+
+        name_elem = df.find("common:Name[@xml:lang='en']", NS)
+        desc_elem = df.find("common:Description[@xml:lang='en']", NS)
+
+        name = _clean("".join(name_elem.itertext())) if name_elem is not None else None
+        desc_raw = "".join(desc_elem.itertext()) if desc_elem is not None else None
+        desc = _clean(desc_raw)
+
+        rows.append(
+            {
+                "dataflowID": dataflow_id,
+                "agencyID": agency_id,
+                "name": name,
+                "description": desc,
+            }
+        )
 
-r = requests.get(url, headers=headers, timeout=30)
-r.raise_for_status()
-root = ET.fromstring(r.content)
-
-rows = []
-for df in root.findall(".//structure:Dataflow", NS):
-    dataflow_id = df.attrib.get("id")
-    agency_id = df.attrib.get("agencyID")
-
-    name_elem = df.find("common:Name[@xml:lang='en']", NS)
-    desc_elem = df.find("common:Description[@xml:lang='en']", NS)
-
-    name = _clean_text("".join(name_elem.itertext())) if name_elem is not None else None
-    desc_raw = "".join(desc_elem.itertext()) if desc_elem is not None else None
-    desc = _clean_text(desc_raw)
-
-    rows.append(
-        {
-            "dataflowID": dataflow_id,
-            "agencyID": agency_id,
-            "name": name,
-            "description": desc,
-        }
-    )
-    
-datasets = pd.DataFrame(rows)
+    _datasets = pd.DataFrame(rows)
+    return _datasets
 
 def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     """
@@ -66,6 +74,7 @@ def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     Returns:
         pd.DataFrame: Matching rows.
     """
+    datasets = _load_datasets()
 
     # Normalize keywords input
     if isinstance(keywords, str): keywords = [keywords]
@@ -78,10 +87,8 @@ def search_keywords(keywords: Union[str, List[str]]) -> pd.DataFrame:
     def _normalize_series(s: pd.Series) -> pd.Series:
         s = s.fillna("").astype(str).str.lower()
         return s.map(
-            lambda x: "".join(
-                ch for ch in unicodedata.normalize("NFKD", x)
-                if not unicodedata.combining(ch)
-            )
+            lambda x: "".join(ch for ch in unicodedata.normalize("NFKD", x)
+                if not unicodedata.combining(ch))
         )
 
     # Combined normalized text for each row

{notoecd-0.1.1.dist-info → notoecd-0.1.2.dist-info}/METADATA

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: notoecd
-Version: 0.1.1
-Summary: Library for interacting with the OECD Data Explorer through Python
+Version: 0.1.2
+Summary: Unofficial library for interacting with the OECD Data Explorer through Python.
 Author-email: Daniel Vegara Balsa <daniel.vegarabalsa@oecd.org>
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/dani-37/notoecd
@@ -15,6 +15,7 @@ Requires-Dist: requests>=2.31
 ⚠️ **Unofficial package, not endorsed by the OECD.**
 
 A lightweight Python interface for exploring OECD SDMX structures and downloading OECD datasets.  
+
 The package provides utilities for:
 
 - Discovering dataset metadata  
@@ -110,4 +111,3 @@ The returned object is a pandas DataFrame containing the requested subset of OEC
 ## Examples
 
 You can see this full example as a notebook called example.ipynb.
-

notoecd-0.1.2.dist-info/RECORD

@@ -0,0 +1,8 @@
+notoecd/__init__.py,sha256=J3-DA__Z9hHzp6eOszRMFh4VE6tk1YtSNigW7el4qDM,189
+notoecd/calls.py,sha256=CDx-1wJ4myXtoihIfTvjHoXBvIwylvv7AdN_UL5gnF4,1492
+notoecd/datasets.py,sha256=a1L45vie6q4cjNXAued2gQ4oE4Fbpk25kdhDTexMuAI,4158
+notoecd/structure.py,sha256=sq6HrjNLfK-UWr9Cuqxun_DhHLPdegX7j7pKYcEYcJM,7169
+notoecd-0.1.2.dist-info/METADATA,sha256=kt6OjNXdlGpn5K-_WQm-z-GLKbbPLgF3mq0C7YSGNho,3192
+notoecd-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+notoecd-0.1.2.dist-info/top_level.txt,sha256=GrcbH10OAguGh5dkpzst216N_C-NtZ-QF1nlXiUpeLs,8
+notoecd-0.1.2.dist-info/RECORD,,

notoecd-0.1.1.dist-info/RECORD

@@ -1,8 +0,0 @@
-notoecd/__init__.py,sha256=134t-qMBmEQN_mtpGOSfQ5zr128wWT68J0e5RIBzN0g,189
-notoecd/calls.py,sha256=CDx-1wJ4myXtoihIfTvjHoXBvIwylvv7AdN_UL5gnF4,1492
-notoecd/datasets.py,sha256=nxLNP0L28mXTKYpdR6BQN5Tk6CKoQS7dygm8twnIVSg,3845
-notoecd/structure.py,sha256=sq6HrjNLfK-UWr9Cuqxun_DhHLPdegX7j7pKYcEYcJM,7169
-notoecd-0.1.1.dist-info/METADATA,sha256=YphZ-il5WvyxK0u1w3cI_vdH2uUdCLaWd3ms981SovI,3180
-notoecd-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-notoecd-0.1.1.dist-info/top_level.txt,sha256=GrcbH10OAguGh5dkpzst216N_C-NtZ-QF1nlXiUpeLs,8
-notoecd-0.1.1.dist-info/RECORD,,