def parse(self, response):
#print '=========================', response.url
pattern_list = re.compile(r'http://www.mogujie.com/book/\w+/\d+')
#print '+++++++++++++++++++++++++', pattern_list.findall(response.body)
'''
for item_list in pattern_list.findall(response.body):
req = Request(url = item_list, callback = self.parse_list)
yield req
'''
'''
req = Request(url = 'http://www.mogujie.com/book/clothing/50249/', callback = self.parse_list, meta={
'splash': {
'endpoint': 'render.html'
},
#'dont_send_headers': True,
})
'''
for item_list in pattern_list.findall(response.body):
#req = SplashRequest(url = 'http://www.mogujie.com/book/clothing/50249/', callback = self.parse_list)
req = SplashRequest(url = item_list, callback = self.parse_list)
yield req
评论列表
文章目录