IL, ID Misc fixes (#5730)

* ID: catch line item vetos and session laws

* IL: Bills: change in action table selector

Author: showerst

scrapers/de/actions.py

@@ -1,7 +1,6 @@
 import re
 from utils.actions import Rule, BaseCategorizer
 
-
 rules = (
     Rule([r"Amendment (?P<bills>.+?) -\s+Laid On Table"], ["amendment-deferral"]),
     Rule(["Favorable"], ["committee-passage-favorable"]),
@@ -19,9 +18,7 @@
     Rule(["unfavorable"], ["committee-passage-unfavorable"]),
     Rule([r"Reported Out of Committee \((?P<committees>.+?)\)"], ["committee-passage"]),
     Rule(["Vetoed by Governor"], ["executive-veto"]),
-    Rule(
-        [r"Amendment (?P<bills>.+?)\s+-\s+Introduced"], ["amendment-introduction"]
-    ),
+    Rule([r"Amendment (?P<bills>.+?)\s+-\s+Introduced"], ["amendment-introduction"]),
     Rule([r"Amendment (?P<bills>[\w\s]+?) Passed"], ["amendment-passage"]),
     Rule(
         [r"Amendment (?P<bills>.+?) -  Defeated by House of .+?\. Votes: Defeated"],

scrapers/id/actions.py

@@ -56,6 +56,8 @@
     Rule(r"[Ee]nrolling", "enrolled"),
     Rule(r"Read third time in full – PASSED", "passage"),
     Rule(r"Read third time in full – FAILED", "failure"),
+    Rule(r"Session Law Chapter", "became-law"),
+    Rule(r"Line item vetoed", "executive-veto-line-item"),
 )
 
 

scrapers/id/bills.py

@@ -106,6 +106,10 @@ def scrape(self, chamber=None, session=None):
                 self.warning("Unable to load subjects.")
                 self._subjects = defaultdict(list)
 
+        # if you need to scrape a single bill
+        # yield from self.scrape_bill("lower", "2026", "H 0978")
+        # return
+
         chambers = [chamber] if chamber else ["upper", "lower"]
         for chamber in chambers:
             yield from self.scrape_bill_url(chamber, session)

scrapers/il/bills.py

@@ -555,7 +555,7 @@ def scrape_bill(self, chamber, session, doc_type, url, bill_type=None):
         )
         # don't add just yet; we can make them better using action data
         # actions
-        action_tds = doc.xpath('//h5[text()="Actions"]/../table//td')
+        action_tds = doc.xpath('//h2[text()="Actions"]/../table//td')
         for date, actor, action_elem in group(action_tds, 3):
             date = datetime.datetime.strptime(date.text_content().strip(), "%m/%d/%Y")
             date = date.date()