scrape_english_proverbs.py

import urllib.request
from bs4 import BeautifulSoup

start = 2801
# only_trs = SoupStrainer('tbody')
end = 2832
for i in range(start, end):
    with urllib.request.urlopen(f'https://www.mechon-mamre.org/p/pt/pt{i}.htm') as response:
        html = response.read()
        soup = BeautifulSoup(html, 'html.parser')
        # print(soup.prettify())
        tb = soup.find_all('table')
        rows = tb[1].find_all('tr')
        for r in rows:
            p = r.find_all('td')
            line = p[1].extract()
            with open("proverbs.txt", "a") as myfile:
                myfile.write(line.contents[2].strip() + '\n')