wabi.py 文件源码

def link_parse(self, response):
        deeps = get_project_settings()['SPIDER_DEEP']
        # ???????????
        links = response.xpath("//li[@class='pbox clr']/div[@class='word']/a/@href").extract()
        if len(links) > 0:
            for link in links:
                yield Request(DOMAIN + link, callback=self.parse_content)
        page_url = response.url
        page_size = page_url.split("page_")
        # ???size=2???????
        if len(page_size) == 2:
            page_index = page_url.split("page_")[1].replace('.html', '')
            if 1 < int(page_index) < deeps:
                yield Request(page_url, callback=self.link_parse)

    # ?????????