lhpapi 1.0.2__tar.gz → 1.0.3__tar.gz

{lhpapi-1.0.2 → lhpapi-1.0.3}/.gitignore

@@ -1,4 +1,4 @@
-/.pytest_cache
-/dist
-/src/lhpapi/__pycache__
-/tests/__pycache__
+/.pytest_cache
+/dist
+/src/lhpapi/__pycache__
+/tests/__pycache__

{lhpapi-1.0.2 → lhpapi-1.0.3}/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 1.0.3 (2024-10-02)
+### Fixed
+- Fix BE encoding
+
 ## 1.0.2 (2024-03-03)
 ### Fixed
 - Update minimum required Python version to 3.11 due to usage of datetime.UTC

{lhpapi-1.0.2 → lhpapi-1.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: lhpapi
-Version: 1.0.2
+Version: 1.0.3
 Summary: API to retrieve data from the Länderübergreifendes Hochwasser Portal (LHP)
 Project-URL: Homepage, https://github.com/stephan192/lhpapi
 Project-URL: Issues, https://github.com/stephan192/lhpapi/issues

{lhpapi-1.0.2 → lhpapi-1.0.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "lhpapi"
-version = "1.0.2"
+version = "1.0.3"
 authors = [
     { name="stephan192", email="stephan192@outlook.com" },
 ]

{lhpapi-1.0.2 → lhpapi-1.0.3}/src/lhpapi/api_utils.py

@@ -52,24 +52,6 @@ def fetch_json(url: str, timeout: float = 10.0) -> Any:
     return json_data
 
 
-def fetch_soup(
-    url: str, timeout: float = 10.0, remove_xml: bool = False
-) -> BeautifulSoup:
-    """Fetch data via soup."""
-    response = get(url=url, timeout=timeout)
-    # Override encoding by real educated guess (required for e.g. SH)
-    response.encoding = response.apparent_encoding
-    response.raise_for_status()
-    if remove_xml and (
-        (response.text.find('<?xml version="1.0" encoding="ISO-8859-15" ?>')) == 0
-    ):
-        text = response.text[response.text.find("<!DOCTYPE html>") :]
-        soup = BeautifulSoup(text, "lxml")
-    else:
-        soup = BeautifulSoup(response.text, "lxml")
-    return soup
-
-
 def fetch_text(url: str, timeout: float = 10.0, forced_encoding: str = None) -> str:
     """Fetch data via text."""
     response = get(url=url, timeout=timeout)
@@ -82,6 +64,15 @@ def fetch_text(url: str, timeout: float = 10.0, forced_encoding: str = None) ->
     return response.text
 
 
+def fetch_soup(
+    url: str, timeout: float = 10.0, forced_encoding: str = None
+) -> BeautifulSoup:
+    """Fetch data via soup."""
+    text = fetch_text(url=url, timeout=timeout, forced_encoding=forced_encoding)
+    soup = BeautifulSoup(text, "lxml")
+    return soup
+
+
 def calc_stage(level: float, stage_levels: list[float]) -> int:
     """Calc stage from level and stage levels."""
     if (level is None) or all(sl is None for sl in stage_levels):

{lhpapi-1.0.2 → lhpapi-1.0.3}/src/lhpapi/bb_api.py

@@ -107,6 +107,7 @@ def update_BB(static_data: StaticData) -> DynamicData:  # pylint: disable=invali
         lines = page.split("\n")
         # Parse data
         start_found = False
+        stage_valid = False
         prev_line = None
         for line in lines:
             line = line.strip()

{lhpapi-1.0.2 → lhpapi-1.0.3}/src/lhpapi/be_api.py

@@ -21,7 +21,7 @@ def init_BE(ident: str) -> StaticData:  # pylint: disable=invalid-name
         # Get data
         page = fetch_soup(
             "https://wasserportal.berlin.de/start.php?anzeige=tabelle_ow&messanzeige=ms_ow_berlin",
-            remove_xml=True,
+            forced_encoding="ISO-8859-15",
         )
         # Parse data
         table = page.find("table", id="pegeltab")