pz.py 文件源码

def getsearchresult_url(ip, url):  # ??????????????
    try:
        html = gethtml(url)
        if not html:
            print '??????url:%s' % url
            return 'error'
        if html == 'error':  # ??????
            return 'error'
        root = etree.HTML(html)
        lines = root.xpath('//*[@id="b_results"]')  # ????
        if not lines:
            return 'error'
        else:
            lines = lines[0]
        urlandtitle = []
        for l in lines:
            url = l.xpath('.//h2/a/@href')
            title = l.xpath('.//h2/a/text()')
            if url and title:
                url = url[0]
                parser = urlparse(url)
                netloc = parser.netloc
                if netloc == 'ip.chinaz.com':
                    pass
                else:
                    title = title[0]
                    urlandtitle.append({'url': url, 'title': title})
            else:
                pass
        urls_temp = {}
        urls_temp = urlandtitle

        for u in urls_temp:
            title = u['title']
            parser = urlparse(u['url'])
            url = parser.scheme + '://' + parser.netloc + '/'
            if url not in check:
                end.append({'url': url, 'title': title})
                check.append(url)
        next_page = lines.xpath('.//*[@class="sb_pagN"]/@href')
        # time.sleep(1)

        if len(next_page) > 0:
            url = 'https://www.bing.com'+next_page[0]
            return 0,url,end
        else:
            return 1,None,end
    except Exception, e:
        print e
        return 'error'