Skip to content

Commit e5b8bb0

Browse files
authored
LA: Bills: scrape missing actions (#5726)
1 parent 2977d56 commit e5b8bb0

1 file changed

Lines changed: 7 additions & 2 deletions

File tree

scrapers/la/bills.py

Lines changed: 7 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -142,6 +142,12 @@ def scrape(self, chamber=None, session=None):
142142
session_id = self._session_ids[session]
143143
# Scan bill abbreviation list if necessary.
144144
self._bill_abbreviations = self._get_bill_abbreviations(session_id)
145+
146+
# If you want to test scrape a specific bill.
147+
# yield from self.scrape_bill_page(
148+
# "lower", session, "https://www.legis.la.gov/Legis/BillInfo.aspx?i=250628", "HB"
149+
# )
150+
145151
# there are duplicates we need to skip
146152
seen_bill_urls = set()
147153
for chamber in chambers:
@@ -294,7 +300,6 @@ def sbp(x):
294300

295301
title = page.xpath("//span[@id='ctl00_PageBody_LabelShortTitle']/text()")[0]
296302
title = title.replace("\u00a0\u00a0", " ")
297-
these_actions = page.xpath("//tr[contains(@class, 'ResultsListDark')]")
298303

299304
bill_id = page.xpath("//span[@id='ctl00_PageBody_LabelBillID']/text()")[0]
300305

@@ -346,7 +351,7 @@ def sbp(x):
346351
# Some bills don't have any votes
347352
pass
348353

349-
for action in these_actions:
354+
for action in page.xpath("//table[.//th[contains(text(),'Journal')]]//tr")[1:]:
350355
date, chamber, page, text, *_ = [x.text for x in action.xpath(".//td")]
351356
# Session is April -> June. Prefiles look like they're in
352357
# January at earliest.

0 commit comments

Comments
 (0)