在两个地方加validate_cert=False
from pyspider.libs.base_handler import *
class Handler(BaseHandler): crawl_config = { }
@every(minutes=24 * 60)
def on_start(self):
self.crawl('https://www.tripadvisor.cn/Attractions-g186338-Activities-London_England.html', callback=self.index_page,validate_cert=False)
@config(age=10 * 24 * 60 * 60)
def index_page(self, response):
for each in response.doc('a[href^="http"]').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,
"title": response.doc('title').text(),
}