URL testing

lciafmt/data/methods.json

@@ -25,7 +25,7 @@
                 "ReCiPe 2016 - Midpoint/E":"ReCiPe 2016 v1.1 midpoint method, Egalitarian version. The typical ReCiPe midpoint method used is the Hierarchist version."},
     "path": "recipe",
     "case_insensitivity": "True",
-    "url": "http://www.rivm.nl/sites/default/files/2018-11/ReCiPe2016_CFs_v1.1_20180117.xlsx",
+    "url": "https://www.rivm.nl/sites/default/files/2024-10/ReCiPe2016_CFs_v1.1_20180117.xlsx",
     "bib_id": "huijbregts_recipe_2017",
     "citation": "Huijbregts 2017",
     "source_type": "Excel file"
@@ -49,7 +49,7 @@
                 "ImpactWorld+ - Endpoint":"This method includes all global endpoint flows and their attributes."},
     "path": "impactworld",
     "case_insensitivity": "False",
-    "url": "http://www.impactworldplus.org/en/writeToFile.php",
+    "url": "https://www.dropbox.com/sh/2sdgbqf08yn91bc/AABIGLlb_OwfNy6oMMDZNrm0a/IWplus_public_v1.3.accdb?dl=1",
     "citation": "Bulle, Cecile, Manuele Margni, Laure Patouillard, Anne-Marie Boulay, Guillaume Bourgault, Vincent De Bruille, Viet Cao, et al. IMPACT World+: A Globally Regionalized Life Cycle Impact Assessment Method. The International Journal of Life Cycle Assessment 24, no. 9 (September 2019), 1653–74. https://doi.org/10.1007/s11367-019-01583-0",
     "source_type": "Access file"
   },

lciafmt/iw.py

@@ -6,6 +6,7 @@
 """
 
 import pandas as pd
+import lciafmt
 import lciafmt.cache as cache
 import lciafmt.df as dfutil
 from lciafmt.util import log, format_cas
@@ -38,13 +39,10 @@ def get(file=None, url=None, region=None) -> pd.DataFrame:
             "Please install drivers to remotely connect to Access Database. "
             "Drivers only available on windows platform. For instructions visit: "
             "https://github.com/mkleehammer/pyodbc/wiki/Connecting-to-Microsoft-Access")
-
+    method_meta = lciafmt.Method.ImpactWorld.get_metadata()
     f = file
     if f is None:
-        fname = "Impact_World.accdb"
-        if url is None:
-            url = "https://www.dropbox.com/sh/2sdgbqf08yn91bc/AABIGLlb_OwfNy6oMMDZNrm0a/IWplus_public_v1.3.accdb?dl=1"
-        f = cache.get_or_download(fname, url)
+        f = _get_file(method_meta, url)
     df = _read(f, region)
 
     # Identify midpoint and endpoint records and differentiate in data frame.
@@ -58,6 +56,12 @@ def get(file=None, url=None, region=None) -> pd.DataFrame:
 
     return df
 
+def _get_file(method_meta, url=None):
+    fname = "Impact_World.accdb"
+    if url is None:
+        url = method_meta['url']
+    f = cache.get_or_download(fname, url)
+    return f
 
 def _read(access_file: str, region) -> pd.DataFrame:
     """Read the Access database at passed access_file into DataFrame."""

lciafmt/recipe.py

@@ -9,6 +9,7 @@
 import pandas as pd
 import openpyxl
 
+import lciafmt
 import lciafmt.cache as cache
 import lciafmt.df as dfutil
 import lciafmt.xls as xls
@@ -52,13 +53,10 @@ def get(add_factors_for_missing_contexts=True, endpoint=True,
     :return: DataFrame of method in standard format
     """
     log.info("getting method ReCiPe 2016")
+    method_meta = lciafmt.Method.RECIPE_2016.get_metadata()
     f = file
     if f is None:
-        fname = "recipe_2016.xlsx"
-        if url is None:
-            url = ("http://www.rivm.nl/sites/default/files/2018-11/" +
-                   "ReCiPe2016_CFs_v1.1_20180117.xlsx")
-        f = cache.get_or_download(fname, url)
+        f = _get_file(method_meta, url)
     df = _read(f)
     if add_factors_for_missing_contexts:
         log.info("adding average factors for primary contexts")
@@ -135,6 +133,14 @@ def get(add_factors_for_missing_contexts=True, endpoint=True,
     return df
 
 
+def _get_file(method_meta, url=None):
+    fname = "recipe_2016.xlsx"
+    if url is None:
+        url = method_meta['url']
+    f = cache.get_or_download(fname, url)
+    return f
+
+
 def _read(file: str) -> pd.DataFrame:
     log.info(f"read ReCiPe 2016 from file {file}")
     wb = openpyxl.load_workbook(file, read_only=True, data_only=True)

lciafmt/traci.py

@@ -38,10 +38,7 @@ def get(add_factors_for_missing_contexts=True, file=None,
     method_meta = lciafmt.Method.TRACI.get_metadata()
     f = file
     if f is None:
-        fname = "traci_2.1.xlsx"
-        if url is None:
-            url = method_meta['url']
-        f = cache.get_or_download(fname, url)
+        f = _get_file(method_meta, url)
     df = _read(f)
     if add_factors_for_missing_contexts:
         log.info("adding average factors for primary contexts")
@@ -72,6 +69,12 @@ def get(add_factors_for_missing_contexts=True, file=None,
 
     return df
 
+def _get_file(method_meta, url=None):
+    fname = "traci_2.1.xlsx"
+    if url is None:
+        url = method_meta['url']
+    f = cache.get_or_download(fname, url)
+    return f
 
 def _read(xls_file: str) -> pd.DataFrame:
     """Read the data from Excel with given path into a DataFrame."""

tests/test_generate_methods.py

@@ -23,6 +23,12 @@ def test_generate_methods():
     assert not error_list
 
 
+def test_url_access():
+    import lciafmt.iw as impactworld
+    f = lciafmt.recipe._get_file(lciafmt.Method.RECIPE_2016.get_metadata())
+    f = lciafmt.traci._get_file(lciafmt.Method.TRACI.get_metadata())
+    f = impactworld._get_file(lciafmt.Method.ImpactWorld.get_metadata())
+
 def test_endpoint_method():
     method = lciafmt.generate_endpoints('Weidema_valuation',
                                         name='Weidema Valuation',
@@ -63,4 +69,5 @@ def test_compilation_method():
 if __name__ == "__main__":
     # test_generate_methods()
     # test_method_write_json()
+    # test_url_access()
     test_compilation_method()