I have this code
def parse(self, response):
hxs = HtmlXPathSelector(response)
sites = hxs.select('//div[@class="headline_area"]')
items = []
for site in sites[:5]:
item = StackItem()
log.msg(' LOOP' +str(ivar)+ '', level=log.ERROR)
item['title'] ="yoo ma"
request = Request("blabla", callback=self.test1)
request.meta['item'] = item
page_number = nextlink.split("&")[-1].split("=")[-1]
if int(page_number) > 500:
raise CloseSpider('Search Exceeded 500')
ivar = ivar + 1
yield request
mylinks= soup.find_all('a')
if mylinks:
nextlink = mylinks[0].get('href')
page_number = nextlink.split("&")[-3].split("=")[-1]
request = Request(urljoin(response.url, nextlink), callback=self.parse)
request.meta['page'] = page_number
yield request
Now my problem is that suppose i want to stop at page_number = 5
now scrappy goes to that page before the all items from page 1 , page 2 etc are downloaded and stops when it first reaches there.
How can get rid of that porblem that it prcess all links before going to page = 5