minarb_research

read_miniarb_research_html

import bs4

html_text_file = "miniarb_research_20180713.html"

f = open(html_text_file, 'r')
html_text = f.read()
f.close()

soup = bs4.BeautifulSoup(html_text)

for line in soup.find_all('pre'):
    line_text = line.get_text()
    if 'count' in line_text:
        line_lst = line_text.split('\r\n')
        for new_line in line_lst:
            if not new_line: break
            new_line_lst = new_line.split()
            if new_line_lst[0] not in ['big_mid', 'count']:
                print new_line_lst