More initial commits

src/hdx/scraper/gdacs/__main__.py

@@ -16,11 +16,13 @@
 )
 from hdx.utilities.retriever import Retrieve
 
+from src.hdx.scraper.gdacs.gdacs import GDACS
+
 logger = logging.getLogger(__name__)
 
 _USER_AGENT_LOOKUP = "hdx-scraper-gdacs"
 _SAVED_DATA_DIR = "saved_data"  # Keep in repo to avoid deletion in /tmp
-_UPDATED_BY_SCRIPT = "HDX Scraper: gdacs"
+_UPDATED_BY_SCRIPT = "HDX Scraper: GDACS"
 
 
 def main(
@@ -48,9 +50,10 @@ def main(
                 use_saved=use_saved,
             )
             configuration = Configuration.read()
-            #
-            # Steps to generate dataset
-            #
+            gdacs = GDACS(configuration, retriever)
+            gdacs.get_data()
+
+            dataset = gdacs.generate_dataset()
             dataset.update_from_yaml(
                 path=join(
                     dirname(__file__), "config", "hdx_dataset_static.yaml"
@@ -72,5 +75,6 @@ def main(
         user_agent_config_yaml=join(expanduser("~"), ".useragents.yaml"),
         user_agent_lookup=_USER_AGENT_LOOKUP,
         project_config_yaml=join(
-            dirname(__file__), "config", "project_configuration.yaml"),
+            dirname(__file__), "config", "project_configuration.yaml"
+        ),
     )

src/hdx/scraper/gdacs/config/project_configuration.yaml

@@ -1 +1,3 @@
 # Collector specific configuration
+
+base_url: "https://www.gdacs.org/XML/RSS.xml"

src/hdx/scraper/gdacs/gdacs.py

@@ -2,9 +2,9 @@
 """gdacs scraper"""
 
 import logging
-from typing import List, Optional
-
+from typing import Optional
 
+from feedparser import parse
 from hdx.api.configuration import Configuration
 from hdx.data.dataset import Dataset
 from hdx.data.hdxobject import HDXError
@@ -13,18 +13,18 @@
 logger = logging.getLogger(__name__)
 
 
-class gdacs:
-
-    def __init__(
-        self, configuration: Configuration, retriever: Retrieve, temp_dir: str
-    ):
+class GDACS:
+    def __init__(self, configuration: Configuration, retriever: Retrieve):
         self._configuration = configuration
         self._retriever = retriever
-        self._temp_dir = temp_dir
+        self.data = {}
 
+    def get_data(self) -> None:
+        text = self._retriever.download_text(self._configuration["base_url"])
+        feed = parse(text)
+        return
 
     def generate_dataset(self) -> Optional[Dataset]:
-
         # To be generated
         dataset_name = None
         dataset_title = None
@@ -41,13 +41,15 @@ def generate_dataset(self) -> Optional[Dataset]:
         )
 
         dataset.set_time_period(dataset_time_period)
-        dataset.add_tagsa(dataset_tags)
+        dataset.add_tags(dataset_tags)
         # Only if needed
         dataset.set_subnational(True)
         try:
             dataset.add_country_location(dataset_country_iso3)
         except HDXError:
-            logger.error(f"Couldn't find country {dataset_country_iso3}, skipping")
+            logger.error(
+                f"Couldn't find country {dataset_country_iso3}, skipping"
+            )
             return
 
         # Add resources here