This spider is supposed to loop through http://www.saylor.org/site/syllabus.php?cid=NUMBER, where NUMBER is 1 to 404 and extract each page. But for some reason it skips pages in the loop. Many pages. For example, it skips 1 through 16. Can someone tell me what's going on?
Here's the code:
from scrapy.spider import BaseSpider
from scrapy.http import Request
from opensyllabi.items import OpensyllabiItem
import boto
class OpensyllabiSpider(BaseSpider):
name = 'saylor'
allowed_domains = ['saylor.org']
max_cid = 405
i = 1
def start_requests(self):
for self.i in range(1, self.max_cid):
yield Request('http://www.saylor.org/site/syllabus.php?cid=%d' % self.i, callback=self.parse_Opensyllabi)
def parse_Opensyllabi(self, response):
Opensyllabi = OpensyllabiItem()
Opensyllabi['url'] = response.url
Opensyllabi['body'] = response.body
filename = ("/root/opensyllabi/data/saylor" + '%d' % self.i)
syllabi = open(filename, "w")
syllabi.write(response.body)
return Opensyllabi