2
我試圖用Scrapy做遞歸解析腳本,但Request()
函數不調用回調函數suppose_to_parse()
,也沒有提供回調函數中的任何函數。我嘗試了不同的變化,但他們都沒有工作。在哪裏挖?scrapy無法發出請求()回調
from scrapy.http import Request
from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
class joomler(BaseSpider):
name = "scrapy"
allowed_domains = ["scrapy.org"]
start_urls = ["http://blog.scrapy.org/"]
def parse(self, response):
print "Working... "+response.url
hxs = HtmlXPathSelector(response)
for link in hxs.select('//a/@href').extract():
if not link.startswith('http://') and not link.startswith('#'):
url=""
url=(self.start_urls[0]+link).replace('//','/')
print url
yield Request(url, callback=self.suppose_to_parse)
def suppose_to_parse(self, response):
print "asdasd"
print response.url