ubuntu上scrapy安装

2016 年 11 月 04 日

4730 次浏览

1355字数

安装scrapy出现错误，解决方法为安装openssl

error: command 'x86_64-linux-gnu-gcc' failed with exit status 1

pip3 install setuptools
sudo python3 -m pip install pyopenssl
sudo apt-get install python3-openssl

官方例子：

import scrapy

class BlogSpider(scrapy.Spider):
    name = 'blogspider'
    start_urls = ['https://blog.scrapinghub.com']

    def parse(self, response):
        for title in response.css('h2.entry-title'):
            yield {'title': title.css('a ::text').extract_first()}

        next_page = response.css('div.prev-post &gt; a ::attr(href)').extract_first()
        if next_page:
            yield scrapy.Request(response.urljoin(next_page), callback=self.parse)

获取moozik的标题和提要：

import scrapy

class BlogSpider(scrapy.Spider):
    name = 'blogspider'
    start_urls = ['http://www.moozik.cn/']
    def parse(self, response):
        html=response.xpath('/html/body/div[2]/div/div/div')
        for res in html:
            yield {
                'title': res.xpath('div[1]/h1/a/text()').extract(),
                'content':res.xpath('div[2]/div/p/text()').extract()
            }

#http://brucedone.com/
import scrapy

class BlogSpider(scrapy.Spider):
    name = 'blogspider'
    start_urls = ['http://brucedone.com/']

    def parse(self, response):
        html=response.xpath('/html/body/div[3]/div/div/ul/li/div/a[1]/text()')
        for res in html:
            yield {
                'title': res.extract()
            }