ii

def download_css(self,html):      
      
      
        liResult = re.findall('(".*?")',html)      
      
        if liResult:      
            print('>>>>>>>>>>>>>>>>>>>>>>>>>正在下载css文件>>>>>>>>>>>>>>>>>>>>>>>>>')      
            for on_url in liResult:      
      
                if on_url.endswith('.css"') or 'css?' in on_url:      
      
                    css_link = re.sub('["]','',on_url)      
      
                    if 'http:' not in css_link or 'https:' not in css_link:      
                        css_link = urljoin(self.site_url,css_link)      
      
                    if css_link:      
                        css_name = re.sub('(.*//)', '', css_link)      
                        f_index = css_name.find('/')      
                        l_index = css_name.rfind('/')      
                        dir_path = self.spath+css_name[f_index:l_index]      
      
                        if '/$' in dir_path:      
                            dir_path = re.sub('(/\$)','/',dir_path)      
      
                        if not os.path.exists(dir_path):      
      
                            os.system('mkdir -p %s'%dir_path)      
      
                        css_name = re.sub('(.*/)', '', css_link)      
                        if css_name[0] == '$':      
                            css_name = css_name.replace('$','')      
                        print('正在下载css文件：',css_link)      
                        css_file = requests.get(css_link).content      
      
                        with open('./%s'%(dir_path+'/'+css_name) ,'wb') as f:      
      
                            f.write(css_file)      
      
            print('===========================css文件下载完毕===========================')      
      
    def download_html(self,html):      
        print('>>>>>>>>>>>>>>>>>>>>>>>>>正在下载网页源码>>>>>>>>>>>>>>>>>>>>>>>>>')      
        if not os.path.exists(self.spath+'/htmls'):      
            print(self.base_path+'/htmls', '已经将html文件存在对应目录')      
            os.system('mkdir -p %s' % self.spath+'/htmls')      
      
        else:      
      
            print(self.base_path+'/htmls', '已经存在此htmls目录')      
      
        if html:      
      
            with open('./%s' % (self.spath+'/htmls/'+self.spath+'.html'), 'w', encoding='utf-8') as f:      
      
                    f.write(html)      
      
        print('===========================下载网页源码完毕===========================')      
      
    def gs_runner(self,html):      
      
        self.download_html(html)      
        self.download_imgs(html)      
        self.download_css(html)      
        self.download_js(html)      
         
      
if __name__ == '__main__':      
    gs = GovSpider()      
    gs.start_page()