Merge pull request #13 from alexandrainst/scrape-date

Scrape date

pyproject.toml

@@ -65,6 +65,9 @@ extend-select = [
     "I",
     "D",
 ]
+exclude = [
+    "src/doms_databasen/_xpaths.py",
+]
 
 [tool.ruff.pydocstyle]
 convention = "google"

src/doms_databasen/_xpaths.py

@@ -7,6 +7,7 @@
     "Accept cookies": "//a[@id='CybotCookiebotDialogBodyLevelButtonLevelOptinAllowAll']",
     "Øvrige sagsoplysninger": "//span[@class='accordion-title'][contains(text(), 'Øvrige sagsoplysninger')]",
     "Sagen er ikke tilgængelig": "//h1[contains(text(), 'Sagen er ikke tilgængelig')]",
+    "Dato": "//tr[@tabindex='0']//td[1]",
 }
 XPATHS_TABULAR_DATA = {
     "Overskrift": "//h4[contains(text(), 'Overskrift')]/following-sibling::span[1]/p",

src/doms_databasen/scraper.py

@@ -2,6 +2,7 @@
 
 import logging
 import os
+import re
 import shutil
 import time
 from pathlib import Path
@@ -255,8 +256,27 @@ def _get_tabular_data(self) -> dict:
             element = self.driver.find_element(By.XPATH, xpath)
             tabular_data[key] = element.text.strip()
 
+        # Not part of the tabular data table, but
+        # we will include the date of the case here.
+        tabular_data["Dato"] = self._get_date()
+
         return tabular_data
 
+    def _get_date(self) -> str:
+        """Gets the date of the case.
+
+        Returns:
+            date (str):
+                Date of the case
+        """
+        date = ""
+        element = self.driver.find_element(By.XPATH, XPATHS["Dato"])
+        # Datetime is on format "dd-mm-yyyy"
+        found = re.search(r"\d{2}-\d{2}-\d{4}", element.text.strip())
+        if found:
+            date = found.group()
+        return date
+
     def _accept_cookies(self) -> None:
         """Accepts cookies on the page."""
         element = WebDriverWait(self.driver, self.config.scrape.sleep).until(