# -*- coding: utf-8 -*-  
import scrapy  
import re  
class JobboleSpider(scrapy.Spider):  
    name = 'jobbole'  
    allowed_domains = ['blog.jobbole.com']  
    start_urls = ['http://blog.jobbole.com/113549/']  
    def parse(self, response):  
        # title = response.xpath('//div[@class = "entry-header"]/h1/text()').extract()[0]  
        # create_date = response.xpath("//p[@class = 'entry-meta-hide-on-mobile']/text()").extract()[0].strip().replace("·","").strip()  
        # praise_numbers = response.xpath("//span[contains(@class,'vote-post-up')]/h10/text()").extract()[0]  
        # fav_nums = response.xpath("//span[contains(@class,'bookmark-btn')]/text()").extract()[0]  
        # match_re = re.match(".*?(\d+).*",fav_nums)  
        # if match_re:  
        #     fav_nums = match_re.group(1)  
        # comment_nums = response.xpath("//a[@href='#article-comment']/span").extract()[0]  
        # match_re = re.match(".*?(\d+).*", comment_nums)  
        # if match_re:  
        #     comment_nums = match_re.group(1)  
        # content = response.xpath("//div[@class='entry']").extract()[0]  
#通过CSS选择器提取字段  
        title = response.css(".entry-header h1::text").extract()[0]  
        create_date = response.css(".entry-meta-hide-on-mobile::text").extract()[0].strip().replace("·","").strip()  
        praise_numbers = response.css(".vote-post-up h10::text").extract()[0]  
        fav_nums = response.css("span.bookmark-btn::text").extract()[0]  
        match_re = re.match(".*?(\d+).*", fav_nums)  
        if match_re:  
            fav_nums = match_re.group(1)  
        comment_nums = response.css("a[href='#article-comment'] span::text").extract()[0]  
        match_re = re.match(".*?(\d+).*", comment_nums)  
        if match_re:  
            comment_nums = match_re.group(1)  
        content = response.css("div.entry").extract()[0]  
        tags = response.css("p.entry-meta-hide-on-mobile a::text").extract()[0]  
        pass