From 6ba3826af1d9f2607db5400f85387c536168464b Mon Sep 17 00:00:00 2001
From: Samuel Pei <samuel.pei@jmaconsulting.biz>
Date: Fri, 8 Nov 2024 14:26:18 -0500
Subject: [PATCH] Re-implemented scraper using preceding-sibling

---
 ca_qc_sainte_anne_de_bellevue/people.py | 49 +++++++------------------
 1 file changed, 13 insertions(+), 36 deletions(-)

diff --git a/ca_qc_sainte_anne_de_bellevue/people.py b/ca_qc_sainte_anne_de_bellevue/people.py
index 5b6ba033..376a0baf 100644
--- a/ca_qc_sainte_anne_de_bellevue/people.py
+++ b/ca_qc_sainte_anne_de_bellevue/people.py
@@ -6,51 +6,28 @@
 
 class SainteAnneDeBellevuePersonScraper(CanadianScraper):
     def scrape(self):
-        def decode_email(e):
-            de = ""
-            k = int(e[:2], 16)
-
-            for i in range(2, len(e) - 1, 2):
-                de += chr(int(e[i : i + 2], 16) ^ k)
-
-            return de
-
         page = self.lxmlize(COUNCIL_PAGE)
 
-        councillors = page.xpath('//div[@class="col-md-12"]')[0]
+        councillors = page.xpath('//p[a[contains(@href, "@")]]')
         assert len(councillors), "No councillors found"
 
-        roles_and_districts = councillors.xpath(".//h2/text()")
-        roles = []
-        districts = []
-        names = []
-        emails = []
+        for councillor in councillors:
+            role = councillor.xpath("./preceding-sibling::h2[1]/text()")[0]
 
-        # Fill in roles and districts via h2 tags
-        for role in roles_and_districts:
-            role_and_district = role.split()
-
-            roles.append(role_and_district[0])
-
-            if len(role_and_district) == 1:
-                districts.append("Sainte-Anne-de-Bellevue")
+            if role == "Maire":
+                district = "Sainte-Anne-de-Bellevue"
             else:
-                districts.append("District " + role_and_district[2])
+                district = "District " + role.split()[2]
+                role = "Conseiller"
 
-        # Fill in contact info via p tags.
-        contact_info = councillors.xpath('.//p[a[contains(@href, "@")]]')
-        for contact in contact_info:
-            contact = contact.text_content().split()
-            name = " ".join(contact[:2])
-            names.append(name)
+            councillor = councillor.text_content().split()
 
-            email = contact[3]
+            name = " ".join(councillor[:2])
+            email = councillor[3]
             email = email.replace("Président", "")
-            emails.append(email)
 
-        assert len(roles) == len(districts) == len(names) == len(emails), "Lists are not of equal length"
-        for i in range(len(roles)):
-            p = Person(primary_org="legislature", name=names[i], district=districts[i], role=roles[i])
+            p = Person(primary_org="legislature", name=name, district=district, role=role)
             p.add_source(COUNCIL_PAGE)
-            p.add_contact("email", emails[i])
+            p.add_contact("email", email)
+
             yield p