MN, CO Bills Fixes for broken dates

Author: showerst

scrapers/co/bills.py

@@ -47,6 +47,9 @@ class COBillScraper(Scraper, LXMLMixin):
     max_pages = 2
 
     def scrape(self, chamber=None, session=None):
+        # If you need to scrape an individual bill for testing
+        # yield from self.scrape_bill("https://leg.colorado.gov/bills/HB26-1362", "2026")
+
         # TODO: there's a better way to do this
         for i in self.jurisdiction.legislative_sessions:
             if i["identifier"] == session:
@@ -212,9 +215,12 @@ def scrape_documents(self, bill: Bill, page: lxml.html.HtmlElement):
 
     def scrape_laws(self, bill: Bill, page: lxml.html.HtmlElement):
         for row in page.cssselect("div#bill-activity-session-laws tbody tr"):
-            effective = dateutil.parser.parse(
-                self.clean(row.xpath("td[1]/span"))
-            ).date()
+            if self.clean(row.xpath("td[1]/span")):
+                effective = dateutil.parser.parse(
+                    self.clean(row.xpath("td[1]/span"))
+                ).date()
+            else:
+                effective = None
             chapter = self.clean(row.xpath("td[2]/span"))
             title = self.clean(row.xpath("td[3]/span"))
             chapter = f"Chapter: {chapter} {title}"

scrapers/mn/bills.py

@@ -458,7 +458,11 @@ def parse_inline_action_date(self, text):
     def parse_dates(self, datestr):
         # Fixing a typo in source data on following URL
         # https://www.revisor.mn.gov/bills/bill.php?b=House&f=HF2184&ssn=0&y=2025
-        datestr = datestr.replace("/225", "/2025").replace("/226", "2026")
+        datestr = (
+            datestr.replace("/225", "/2025")
+            .replace("/226", "2026")
+            .replace("05/272026", "05/27/2026")
+        )
         date_formats = ["%m/%d/%Y", "%m/%d/%y"]
         for fmt in date_formats:
             try: