Merge pull request openstates#1125 from showerst/nm-mimetype

Added check for PDF mimetype instead of assuming text/html
showerst · May 19, 2016 · dd4cf5c · dd4cf5c
2 parents 1e94c2e + c1a7092
commit dd4cf5c
Showing 1 changed file with 9 additions and 5 deletions.
diff --git a/openstates/nm/bills.py b/openstates/nm/bills.py
@@ -233,6 +233,8 @@ def check_docs(url, doc_type):
                 match = re.match('([A-Z]+)0*(\d{1,4})', fname)
                 if match:
                     bill_type, bill_num = match.groups()
+                    mimetype = "application/pdf" if fname.lower().endswith("pdf") else "text/html"    
+
                     if (chamber == "upper" and bill_type[0] == "S") or (chamber == "lower" and bill_type[0] == "H"):
                         bill_id = bill_type.replace('B', '') + bill_num
                         try:
@@ -242,9 +244,9 @@ def check_docs(url, doc_type):
                         else:
                             if doc_type == 'Final Version':
                                 bill.add_version(
-                                    'Final Version', url + fname, mimetype='text/html')
+                                    'Final Version', url + fname, mimetype=mimetype)
                             else:
-                                bill.add_document(doc_type, url + fname)
+                                bill.add_document(doc_type, url + fname, mimetype=mimetype)
 
         check_docs(firs_url, 'Fiscal Impact Report')
         check_docs(lesc_url, 'LESC Analysis')
@@ -442,11 +444,13 @@ def scrape_documents(self, session, doctype, chamber, chamber_name=None):
             except KeyError:
                 self.warning('document for unknown bill %s' % fname)
                 continue
+
+            mimetype = "application/pdf" if fname.lower().endswith("pdf") else "text/html"    
 
             # no suffix = just the bill
             if suffix == '':
                 bill.add_version('introduced version', doc_path + fname,
-                                 mimetype='text/html')
+                                 mimetype=mimetype)
 
             # floor amendments
             elif re.match('F(S|H)\d', suffix):
@@ -459,7 +463,7 @@ def scrape_documents(self, session, doctype, chamber, chamber_name=None):
             elif suffix.endswith('S'):
                 committee_name = suffix[:-1]
                 bill.add_version('%s substitute' % committee_name,
-                                 doc_path + fname, mimetype='text/html')
+                                 doc_path + fname, mimetype=mimetype)
             # votes
             elif 'SVOTE' in suffix:
                 vote = self.parse_senate_vote(doc_path + fname)
@@ -477,7 +481,7 @@ def scrape_documents(self, session, doctype, chamber, chamber_name=None):
             elif re.match('\w{2,3,4}\d', suffix):
                 committee_name = re.match('[A-Z]+', suffix).group()
                 bill.add_document('%s committee report' % committee_name,
-                                  doc_path + fname)
+                                  doc_path + fname, mimetype=mimetype)
 
             # ignore list, mostly typos reuploaded w/ proper name
             elif suffix in ('HEC', 'HOVTE', 'GUI'):