From 464d617ecccc901435a9f2874388e4ea44e85f3a Mon Sep 17 00:00:00 2001
From: Kim Taylor <kmtaylor@gmx.com>
Date: Wed, 13 Nov 2024 07:24:05 +1100
Subject: [PATCH] Add parser to scrape winning candidates from VEC site.

---
 results/fetch.sh  |  5 +++++
 results/parser.py | 24 ++++++++++++++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100755 results/fetch.sh
 create mode 100644 results/parser.py

diff --git a/results/fetch.sh b/results/fetch.sh
new file mode 100755
index 0000000..6184537
--- /dev/null
+++ b/results/fetch.sh
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+council_name=boroondara-city-council
+
+wget https://www.vec.vic.gov.au/voting/2024-local-council-elections/$council_name/results -O $council_name
diff --git a/results/parser.py b/results/parser.py
new file mode 100644
index 0000000..734e593
--- /dev/null
+++ b/results/parser.py
@@ -0,0 +1,24 @@
+from bs4 import BeautifulSoup, Tag as HTMLTag
+
+with open("boroondara-city-council", 'r') as results_fp:
+    html_doc = results_fp.read()
+
+soup = BeautifulSoup(html_doc, 'html.parser')
+candidates0 = soup.find_all(string="Successful candidates")
+candidates1 = soup.find_all(string="Elected candidates")
+
+def get_candidate_name(candidate):
+    for sibling in candidate.parent.next_siblings:
+        if not isinstance(sibling, HTMLTag):
+            continue
+        if not (block := sibling.find('td', class_="list-item-body")):
+            continue
+        return block.text.strip()
+
+names = []
+for candidate in candidates0:
+    names.append(get_candidate_name(candidate))
+for candidate in candidates1:
+    names.append(get_candidate_name(candidate))
+
+print(names)