Merge pull request #84 from City-Bureau/fix-cle-metro-sd

🕷️ Fix spider: Cleveland Metropolitan School District

city_scrapers/spiders/cle_metro_school_district.py

@@ -11,6 +11,7 @@ class CleMetroSchoolDistrictSpider(CityScrapersSpider):
     agency = "Cleveland Metropolitan School District"
     timezone = "America/Detroit"
     start_urls = ["https://www.boarddocs.com/oh/cmsd/board.nsf/XML-ActiveMeetings"]
+    custom_settings = {"ROBOTSTXT_OBEY": False}
 
     def parse(self, response):
         """
@@ -70,12 +71,14 @@ def _parse_start(self, item):
 
     def _parse_location(self, item):
         """Parse or generate location."""
-        loc_item = (
-            item.xpath("./category[@order='1']/agendaitems/item/name/text()")
-            .extract_first()
-            .strip()
-        )
-        loc_str = re.sub(r"^\d{1,2}\.\d{1,2} ?", "", loc_item)
+        loc_item = item.xpath("./category[@order='1']/agendaitems/item/name/text()")
+        if not loc_item:
+            return {
+                "address": "",
+                "name": "TBD",
+            }
+        loc_raw_str = loc_item.extract_first().strip()
+        loc_str = re.sub(r"^\d{1,2}\.\d{1,2} ?", "", loc_raw_str)
         loc_parts = re.split(r", ?(?=\d{2})", loc_str, 1)
         if len(loc_parts) == 2:
             return {