Skip to content

Instantly share code, notes, and snippets.

@cavedave
Created August 12, 2023 16:39
Show Gist options
  • Save cavedave/41576ac0813efc5140fc5b30fcbc67ff to your computer and use it in GitHub Desktop.
Save cavedave/41576ac0813efc5140fc5b30fcbc67ff to your computer and use it in GitHub Desktop.
Code to parse a pdf of the only Irish-Irish dictionary of the 20th century. Croidhe Cainnte Chiarraighe. Foclóir Gaeilge-Gaeilge (pdf) 1942. PDF is at https://www.forasnagaeilge.ie/wp-content/uploads/2016/06/8fddae92ae307b022d964ebe73d45df6.pdf . I took a few pages using https://smallpdf.com/split-pdf to speed up experiments but that can be done…
import pdfplumber
def is_bold_font(char):
return "bold" in char['fontname'].lower()
def parse_pdf_to_dictionary(pdf_path):
term_definition_dict = {}
term = ""
next_term = ""
definition = ""
#this code gets all bold. We need bold at start of line and ending in:
with pdfplumber.open(pdf_path) as pdf:
for page in pdf.pages:
for element in page.chars:
text = element['text']
if is_bold_font(element):#text.endswith(":") and
#print(element['x0']) could check if char is at the start
#but bold can be at start anyway
if firstBold:
if ":" in term:#dictionary terms have a :
term=term.strip()
print("term is "+term)
term_definition_dict[term] = definition
#else:
# definition += text
#if not true we are bolded but with out :
#we shold keep the bold as it tells us about the word
#but for the moment lets not
term = ""
definition = ""
firstBold=False
term += text
else:
firstBold=True
definition += text
return term_definition_dict
pdf_path = "/content/8fddae92ae307b022d964ebe73d45df6-pages-40-44.pdf"
term_definition_dict = parse_pdf_to_dictionary(pdf_path)
for term, definition in term_definition_dict.items():
print(f"Term: {term}\n Definition: {definition}\n")
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment