newsevent.py 文件源码

def _guba_content(url):
    try:
        html = lxml.html.parse(url)
        res = html.xpath('//div[@class=\"ilt_p\"]/p')
        if ct.PY3:
            sarr = [etree.tostring(node).decode('utf-8') for node in res]
        else:
            sarr = [etree.tostring(node) for node in res]
        sarr = ''.join(sarr).replace('　', '')#.replace('\n\n', '\n').
        html_content = lxml.html.fromstring(sarr)
        content = html_content.text_content()
        ptime = html.xpath('//div[@class=\"fl_left iltp_time\"]/span/text()')[0]
        rcounts = html.xpath('//div[@class=\"fl_right iltp_span\"]/span[2]/text()')[0]
        reg = re.compile(r'\((.*?)\)') 
        rcounts = reg.findall(rcounts)[0]
        return [content, ptime, rcounts]
    except Exception:
        return ['', '', '0']