Brandenburg download

04_brandenburg.py

+import re
+from datetime import datetime
+
+from citygml_download import TMP_DIR, Bundesland, CityGMLWithDate, download_all_files, download_file
+
+BRANDENBURG = Bundesland(
+    "Brandenburg",
+    source="https://data.geobasis-bb.de/geobasis/daten/3d_gebaeude/lod2_gml/",
+    info="https://geoportal.brandenburg.de/detailansichtdienst/render?url=https://geoportal.brandenburg.de/gs-json/xml?fileid=0414a37a-a749-4ee6-9f59-a41226919c58",
+    license="dl-de/by-2-0",
+    kontakt="<kundenservice@geobasis-bb.de> Landesvermessung und Geobasisinformation Brandenburg (LGB)",
+)
+
+#  <tr class="even"><td class="indexcolicon"><img src="/style/icons/file-zip.svg" alt="[   ]" width="16" height="16" /></td><td class="indexcolname"><a href="lod2_33250-5890.zip">lod2_33250-5890.zip</a></td><td class="indexcollastmod">2024-11-07 20:03  </td><td class="indexcolsize"> 56K</td><td class="indexcoldesc">3D-Gebäudemodelle LoD2</td></tr>
+# It's supposedly wrong, but funny, to parse HTML with regexen
+# ZIP_AND_DATE = re.compile(r"(lod2_\d+-\d+\.zip).*?(20\d+-\d+\d+ \d+:\d+)", re.IGNORECASE)
+ZIP_AND_DATE = re.compile(r"(lod2_\d+-\d+\.zip).*?(20\d+-\d+-\d+ \d+:\d+)", re.IGNORECASE)
+
+if __name__ == "__main__":
+    html_path = TMP_DIR / f"{BRANDENBURG}_lod2.html"
+    if not html_path.exists():
+        download_file(BRANDENBURG.source, TMP_DIR / html_path)
+
+    citygmls = []
+
+    with open(html_path) as html:
+        for line in html:
+            if m := ZIP_AND_DATE.search(line):
+                name, date = m.groups()
+                print(date)
+                citygmls.append(
+                    CityGMLWithDate(
+                        url=BRANDENBURG.source + name,
+                        bundesland=BRANDENBURG,
+                        source_date=datetime.strptime(date, "%Y-%m-%d %H:%M"),
+                    )
+                )
+
+    download_all_files(citygmls)