def start_requests(self):
headers={
“user-agent”:“Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.0.0 Safari/537.36”
};
browser = uc.Chrome();
browser.get(‘https://account.cnblogs.com/signin’);
input(“回车继续：”);
cookies = browser.get_cookies();
cookie_dict = {};
for cookie in cookies:
cookie_dict[cookie[‘name’]] = cookie[‘value’];
for url in self.start_urls:
yield Request(url,headers=headers,dont_filter=True);

def parse(self, response):   
    post_nodes=response.xpath('//div[@id="news_list"]/div[@class="news_block"]')[:1];
    print(post_nodes);
    for post_node in post_nodes:
        image_url=post_node.xpath('//div[@class="entry_summary"]/a/img/@src').extract_first("");
        post_url=post_node.css('h2 a::attr(href)').extract_first("");
        yield Request(url=parse.urljoin("http://news.cnblogs.com/",post_url),meta={"from_image_url":image_url},callback=self.parse_detail)
        
def parse_detail(self,response):
    match_re=re.match(".*?(\d+)",response.url);  这边response.url报错!