Код: Выделить всё
from openbar_index.items import OpenBarIndexItem
from scrapy.contrib.spiders import CrawlSpider, Rule
from scrapy.contrib.linkextractors.sgml import SgmlLinkExtractor
class OpenBarSpider(CrawlSpider):
"""
scrapes website URLs from educational websites and commits urls/webpage names/text to a document
"""
name = 'openbar'
allowed_domains = 'khanacademy.org'
start_urls = [
"https://www.khanacademy.org"
]
rules = [
Rule(SgmlLinkExtractor(allow = ['/math/']), callback='parse_item', follow = True),
Rule(SgmlLinkExtractor(allow = ['/science/']), callback='parse_item', follow=True),
Rule(SgmlLinkExtractor(allow = ['/economics-finance-domain/']), callback='parse_item', follow=True)
]
def parse_item(self, response):
item = OpenBarIndexItem()
url = response.url
item['url'] = url
item['title'] = response.xpath('/html/head/title/text()').extract()
yield item
Подробнее здесь: https://stackoverflow.com/questions/309 ... en-bracket