Last active
January 19, 2022 21:02
-
-
Save LouisdeBruijn/25e7957aa7b6ad68a213fa08dbcda540 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def fonts(doc, granularity=False): | |
"""Extracts fonts and their usage in PDF documents. | |
:param doc: PDF document to iterate through | |
:type doc: <class 'fitz.fitz.Document'> | |
:param granularity: also use 'font', 'flags' and 'color' to discriminate text | |
:type granularity: bool | |
:rtype: [(font_size, count), (font_size, count}], dict | |
:return: most used fonts sorted by count, font style information | |
""" | |
styles = {} | |
font_counts = {} | |
for page in doc: | |
blocks = page.getText("dict")["blocks"] | |
for b in blocks: # iterate through the text blocks | |
if b['type'] == 0: # block contains text | |
for l in b["lines"]: # iterate through the text lines | |
for s in l["spans"]: # iterate through the text spans | |
if granularity: | |
identifier = "{0}_{1}_{2}_{3}".format(s['size'], s['flags'], s['font'], s['color']) | |
styles[identifier] = {'size': s['size'], 'flags': s['flags'], 'font': s['font'], | |
'color': s['color']} | |
else: | |
identifier = "{0}".format(s['size']) | |
styles[identifier] = {'size': s['size'], 'font': s['font']} | |
font_counts[identifier] = font_counts.get(identifier, 0) + 1 # count the fonts usage | |
font_counts = sorted(font_counts.items(), key=itemgetter(1), reverse=True) | |
if len(font_counts) < 1: | |
raise ValueError("Zero discriminating fonts found!") | |
return font_counts, styles |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment