Commit e9a72ff93a8a99a5107bbc6118235cc0f27c15a8
1 parent
5867e020
Exists in
master
Tune to CentOS
Showing
1 changed file
with
2 additions
and
2 deletions
Show diff stats
crawler/crawler/spiders/ImgCrawler.py
| 1 | -from scrapy.spider import Spider | 1 | +from scrapy.spider import BaseSpider |
| 2 | from scrapy.http import Request | 2 | from scrapy.http import Request |
| 3 | from crawler.items import CrawlerItem | 3 | from crawler.items import CrawlerItem |
| 4 | import re | 4 | import re |
| 5 | 5 | ||
| 6 | -class Crawler(Spider): | 6 | +class Crawler(BaseSpider): |
| 7 | name = 'img' | 7 | name = 'img' |
| 8 | allowed_domains = ['www.cs.tsinghua.edu.cn'] | 8 | allowed_domains = ['www.cs.tsinghua.edu.cn'] |
| 9 | start_urls = ['http://www.cs.tsinghua.edu.cn'] | 9 | start_urls = ['http://www.cs.tsinghua.edu.cn'] |