ttml_sub_extract.py

import csv
import string
import sys
from collections import Counter
from pathlib import Path

from bs4 import BeautifulSoup


file_a, style_a = sys.argv[1], sys.argv[2]

sub_p = Path(__file__).parent / file_a
with sub_p.open(mode="r", encoding="utf-8") as f:
    html = f.read()

soup = BeautifulSoup(html, "html.parser")
body = soup.body
paragraphs_html = body.find_all("p")
paragraphs = []
for p in paragraphs_html:
    begin, end = p.get("begin"), p.get("end")
    spans_html = p.find_all("span")
    styles = [s.get("style") for s in spans_html]
    if style_a in styles:
        text = " ".join(s.get_text() for s in spans_html
                        if s.get("style") == style_a)
        paragraphs.append((begin, end, text))

field_headers = ["begin", "end", "text"]
csv_path = Path(__file__).parent / Path(f"{file_a}_{style_a}.csv")
with csv_path.open("w", encoding="utf-8", newline="") as csv_file:
    writer = csv.writer(csv_file, quoting=csv.QUOTE_NONNUMERIC)
    writer.writerow(field_headers)
    for p in paragraphs:
        begin, end, text = p[0], p[1], p[2]
        writer.writerow([begin, end, text])

c = Counter()
for p in paragraphs:
    text = p[2]
    words_raw = text.split()
    words = [w.strip(string.punctuation).lower() for w in words_raw]
    for w in words:
        c[w] += 1

print(c.most_common())