scrapy 初探(css)

初始化项目及项目配置同scrapy 初探(xpath)一样

新建zwblog/spiders/lianjia_spider.py内容如下：

# -*- coding: utf-8 -*-
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from LjCrwaler.items import LianjiaItem

class LJCrwalerSpider(CrawlSpider):
    name = 'ljcrwaler'
    allowed_domains = ['lianjia.com']
    start_urls = ['https://qd.lianjia.com/ershoufang/']

    # 设置抓取规则
    rules = {
        # 房产详情链接
        Rule(LinkExtractor(
            restrict_xpaths="//ul[@class='sellListContent']/li/div[@class='info clear']/div[@class='title']/a"),
             follow=True, callback="process_item"),
        # 翻页链接
        Rule(LinkExtractor(restrict_xpaths="//div[@class='pagination_group_a']/a"), follow=True)