Support DMVE, DMUE, DCE, DEFE. Closes #137

providers/sigrefdata/dce.py

@@ -0,0 +1,42 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import SIGRefType
+from data.sig_ref import SIGRef
+from providers.sigrefdata.file_download_sig_ref_data_provider import FileDownloadSIGRefDataProvider
+
+
+class DCE(FileDownloadSIGRefDataProvider):
+    """SIG ref data provider for Diploma Castillos de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    SIG = "DCE"
+    DATA_URL = "https://www.acracb.org/dce/descargas/General/directorio_referencias_dce.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.SIG, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        df = pd.read_excel(file_stream, engine="xlrd", header=None)
+
+        for index, row in df.iterrows():
+            if row.iloc[0] and row.iloc[2]:
+                new_data.append(
+                    SIGRef(sig=self.SIG, id=row.iloc[0].strip(), name=row.iloc[2].strip(), ref_type=SIGRefType.CASTLE)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle sig refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/sigrefdata/defe.py

@@ -0,0 +1,46 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import SIGRefType
+from data.sig_ref import SIGRef
+from providers.sigrefdata.file_download_sig_ref_data_provider import FileDownloadSIGRefDataProvider
+
+
+class DEFE(FileDownloadSIGRefDataProvider):
+    """SIG ref data provider for Diploma Estationes de Ferrocarril de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    SIG = "DEFE"
+    DATA_URL = "https://www.acracb.org/defe/descargas/General/directorio_referencias_defe.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.SIG, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        df = pd.read_excel(file_stream, engine="xlrd", header=None)
+
+        for index, row in df.iterrows():
+            # Skip the header row
+            if str(row.iloc[0]) == "NºDEFE":
+                continue
+
+            if row.iloc[0] and row.iloc[1]:
+                new_data.append(
+                    SIGRef(sig=self.SIG, id=row.iloc[0].strip(), name=row.iloc[1].strip(), ref_type=SIGRefType.BUILDING)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle sig refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/sigrefdata/dmue.py

@@ -0,0 +1,37 @@
+import csv
+from time import sleep
+
+from core.enums import SIGRefType
+from data.sig_ref import SIGRef
+from providers.sigrefdata.file_download_sig_ref_data_provider import FileDownloadSIGRefDataProvider
+
+
+class DMUE(FileDownloadSIGRefDataProvider):
+    """SIG ref data provider for Diploma Museos de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    SIG = "DMUE"
+    DATA_URL = "https://dmue.radiogalena.es/nom_dmue.csv"
+
+    def __init__(self, provider_config):
+        super().__init__(self.SIG, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        for row in csv.reader(http_response.content.decode("utf-8-sig").splitlines(), delimiter=";"):
+            if len(row) > 1 and row[0] and row[1]:
+                new_data.append(
+                    SIGRef(sig=self.SIG, id=row[0].strip(), name=row[1].strip(), ref_type=SIGRefType.BUILDING)
+                )
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle sig refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data

providers/sigrefdata/dmve.py

@@ -0,0 +1,50 @@
+import io
+from time import sleep
+
+import pandas as pd
+
+from core.enums import SIGRefType
+from data.sig_ref import SIGRef
+from providers.sigrefdata.file_download_sig_ref_data_provider import FileDownloadSIGRefDataProvider
+
+
+class DMVE(FileDownloadSIGRefDataProvider):
+    """SIG ref data provider for Diploma Monumentos y Vestigios de España"""
+
+    POLL_INTERVAL_DAYS = 365
+    SIG = "DMVE"
+    DATA_URL = "https://www.acracb.org/dmve/descargas/General/directorio_referencias_dmve.xls"
+
+    def __init__(self, provider_config):
+        super().__init__(self.SIG, provider_config, self.DATA_URL, self.POLL_INTERVAL_DAYS)
+
+    def _http_response_to_data(self, http_response):
+        new_data = []
+
+        file_stream = io.BytesIO(http_response.content)
+        # Despide the .xls extension this is actually an xlsx file, so we need openpyxl not xlrd
+        df = pd.read_excel(file_stream, engine="openpyxl", header=None)
+
+        for index, row in df.iterrows():
+            ref = row.iloc[0]
+            name = row.iloc[1]
+
+            # Skip the header row and blank rows
+            if str(ref) == "REF.":
+                continue
+            if pd.isna(ref) or pd.isna(name):
+                continue
+
+            if ref and name:
+                new_data.append(SIGRef(sig=self.SIG, id=ref.strip(), name=name.strip(), ref_type=SIGRefType.BUILDING))
+
+            # Bail out if a stop has been requested, i.e. the program is shutting down - no need to parse the rest of
+            # the data in this case
+            if self._stop_event.is_set():
+                break
+
+            # Very short pause. This will extend the time to handle sig refs by a few seconds but will ensure some time
+            # is available for other threads e.g. the web server.
+            sleep(0.001)
+
+        return new_data