《2018年8月23日》【连续325天】
标题:pyspider实例2;
内容:
尝试用pyspider爬取了一个网站的视频排行,非常便利:
class Handler(BaseHandler):
crawl_config = {
}
@every(minutes=24 * 60)
def on_start(self):
self.crawl('https://www.bilibili.com/ranking/origin/0/0/3', callback=self.index_page,validate_cert=False)
@config(age=10 * 24 * 60 * 60)
def index_page(self, response):
for each in response.doc('.title').items():
self.crawl(each.attr.href,
callback=self.detail_page,validate_cert=False)
@config(priority=2)
def detail_page(self, response):
return {
"url": response.url,
"up": response.doc('.user > .name').text(),
"title":response.doc('h1 > span').text(),
}