wip

juriscraper/opinions/united_states/state/mont.py

@@ -8,22 +8,25 @@
 
 
 class Site(OpinionSiteLinear):
+    base_url = "https://juddocumentservice.mt.gov"
+    download_base = f"{base_url}/getDocByCTrackId?DocId="
+    cite_regex = r"((19|20)\d{2}\sMT\s\d{1,3}[A-Z]?)"    
+
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self.court_id = self.__module__
-        self.base = "https://juddocumentservice.mt.gov"
-        self.url = f"{self.base}/getDailyOrders"
-        self.download_base = f"{self.base}/getDocByCTrackId?DocId="
+        self.url = f"{self.base_url}/getDailyOrders"
         self.expected_content_types = None
-        self.cite_regex = r"((19|20)\d{2}\sMT\s\d{1,3}[A-Z]?)"
 
     def _process_html(self):
         for row in self.html:
             summary = row["documentDescription"]
             if not summary.startswith("Opinion"):
                 # skip orders and just do opinions
                 continue
+
             status = "Published" if "Published" in summary else "Unpublished"
+
             docket = row["caseNumber"]
             if docket.startswith("DA"):
                 nature = "Direct Appeal"
@@ -36,6 +39,10 @@ def _process_html(self):
             else:
                 nature = "Unknown"
 
+            # TODO: parse disp?
+            # Opinion - Noncite/Memorandum  Chief Justice McGrath authored, Affirmed.
+            # Opinion - Noncite/Memorandum - Justice Baker - Affirmed and Remanded
+            # Opinion - Noncite/Memorandum; Justice Rice Author - Affirmed in part, reversed in part and remanded.
             m = re.search(
                 r"Justice (?P<author>.*?)\s*(?:author|,|-)", summary, re.I
             )
@@ -47,7 +54,6 @@ def _process_html(self):
                     "date": row["fileDate"],
                     "name": row["title"],
                     "docket": docket,
-                    "summary": summary,
                     "nature_of_suit": nature,
                     "author": author,
                 }
@@ -63,3 +69,7 @@ def extract_from_text(self, scraped_text: str) -> dict:
         if match := re.search(self.cite_regex, first_text):
             return {"Citation": match.group(0)}
         return {}
+
+    def cleanup_content(content: str):
+        """"""
+        pass