contribs.py 文件源码

def get_section(html_file, section_name, possible_next_sections):

    h = html.parse(html_file)
    pars = h.xpath("//p")

    begin = end = -1
    for i, par in enumerate(pars) :

        if (begin>0) and (end>0) :
            break

        par_text = par.text_content().lower()
        if begin<0 and (par_text.find(section_name, 0, 20) >= 0) :
            begin = i

        if begin>=0 :
            for next_section in possible_next_sections :
                if (par_text.find(next_section, 0, 20) >= 0) :
                    end = i

    text = ""
    if (begin<0) or (end<0) :
        raise SectionNotFound("Section %s not found."%section_name)

        text = "".join([par.text_content() for par in pars[begin:end]])

    return text