scrape_docs refactor heading tag lists definitions

JOJ0 · Sep 10, 2024 · 5a853cd · 5a853cd
1 parent ff8e381
commit 5a853cd
Showing 1 changed file with 6 additions and 4 deletions.
diff --git a/scrape_docs.py b/scrape_docs.py
@@ -22,16 +22,18 @@ def scrape(output, url):
  apidoc = requests.get(chapter).text
  soup = BeautifulSoup(apidoc, 'html.parser')
 
+ any_heading_tag = ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']
+
  elements = soup.find_all(
- ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'a'],
+ [*any_heading_tag, 'a'],
  )
 
  for e in elements:
- if e.name in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
- if output in ['default', 'rst']:
+ if e.name in any_heading_tag:
+ if output in ['default']:
  print(f'{e.name}: {e.text}')
  if e.name == 'a':
- if e.parent.name in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']:
+ if e.parent.name in any_heading_tag:
  link = e['href']
  if output == 'default':
  print(f'{e.text} {link}')