parse_html_2.py

for a in sect.find_all('a'):

        # i'm looking for an <a> tag in the <section> that starts with the string "&nbsp;in"
        if (len(a.text) > 4 and a.text[0].isspace() and a.text[1:3] == "in"):

            # The publication name is inside the <a> tag following the substring "&nbsp;in"
            pub_name = a.text[4:]
            if pub_name in pubs:
                pub_count[pubs.index(pub_name)] += 1
            else:
                pubs.append(pub_name)
                pub_count.append(1)