add header parsing

This commit is contained in:
Anish Lakhwara 2022-01-30 21:30:40 +10:00
parent 9cb1aa61e3
commit b6e9d1605d

View file

@ -254,6 +254,18 @@ def get_date(page):
#print(f"Could not parse date") #print(f"Could not parse date")
return None return None
def parse_headings(page):
try:
# TODO for some reason this one isn't being parsed by the regex
if '= Kitaab =' in page:
print(page)
page = re.sub(r'= [\[\]a-zA-Z0-9 ]* =',
lambda x: x.group().replace('=','#', 1).strip('='),
page)
return page
except Exception as e:
print(f"Could not parse headers {e}")
return page
# From the list of files, creates the main array of entries that will be processed later # From the list of files, creates the main array of entries that will be processed later
def create_entries(pages): def create_entries(pages):
@ -278,6 +290,7 @@ def create_entries(pages):
markdown_text = remove_tags(markdown_text) markdown_text = remove_tags(markdown_text)
markdown_text = remove_title(markdown_text) markdown_text = remove_title(markdown_text)
markdown_text = remove_date(markdown_text) markdown_text = remove_date(markdown_text)
markdown_text = parse_headings(markdown_text)
pageContent = markdown(markdown_text) pageContent = markdown(markdown_text)
# Create the page object with all the informations we need # Create the page object with all the informations we need
@ -286,11 +299,11 @@ def create_entries(pages):
tempPage['folder'] = path["folder"] tempPage['folder'] = path["folder"]
tempPage['parent_url'] = path['parent_url'] tempPage['parent_url'] = path['parent_url']
tempPage['parent_text'] = path['parent_text'] tempPage['parent_text'] = path['parent_text']
tempPage['date'] = path['date'] tempPage['iso_date'] = path['date']
if date: if date:
tempPage['iso_date'] = date tempPage['date'] = date
else: else:
tempPage['iso_date'] = path['iso_date'] tempPage['date'] = path['iso_date']
tempPage['title'] = fix_amp(title) tempPage['title'] = fix_amp(title)
tempPage['pageContent'] = pageContent tempPage['pageContent'] = pageContent
tempPage['tags'] = tags tempPage['tags'] = tags