全站爬取cnblogs

全站爬取cnblogs

• 创建

"""
# 1 scrapy startproject cnblogs_crawl
# 2 scrapy genspider cnblogs www.cnblogs.com
"""

• 代码演示

"""
# -*- coding: utf-8 -*-
import scrapy
from cnblogs_crawl.items import CnblogsCrawlItem
from scrapy.http import Request


class CnblogsSpider(scrapy.Spider):
    name = 'cnblogs'
    allowed_domains = ['www.cnblogs.com']
    start_urls = ['http://www.cnblogs.com/']

    def parse(self, response):
        # print(response)
        div_list = response.css('.post_item')
        for div in div_list:
            item = CnblogsCrawlItem()
            title = div.css('h3>a::text').extract_first()
            # print(title)
            item['title'] = title
            url = div.css('h3>a::attr(href)').extract_first()
            # print(url)
            item['url'] = url
            author = div.css('.post_item_foot a::text').extract_first()
            # print(author)
            item['author'] = author
            desc = div.css('.post_item_summary::text').extract()[-1]
            # print(desc)
            item['desc'] = desc

            # yield item
            # 如果不写callback,爬完之后，就会执行parse_detail解析

            # 传参
            yield Request(url, callback=self.parse_detail, meta={'item':item})

            # 持久化

        next = response.css('div.pager a:last-child::attr(href)').extract_first()
        # print(next)

        # 继续爬取下一页内容
        yield Request('http://www.cnblogs.com/' + next)


    # 继续获取文章的真正的内容，因为解析方式可能不一样
    def parse_detail(self, response):
        # print(response)
        item = response.meta.get('item')
        content = response.css('#cnblogs_post_body').extract_first()
        if not content:
            content = response.css('content').extract_first()
        item['content'] = content
        yield item


"""

• 鼠标执行

"""
from scrapy.cmdline import execute

execute(['scrapy', 'crawl', 'cnblogs'])
"""

• 爬取数据持久化到数据库

"""
import pymysql

# 写入数据，持久化
class CnblogsCrawlPipeline(object):

    def open_spider(self, spider):
        self.conn = pymysql.Connect(host='127.0.0.1', port=3306, db='cnblogs', user='root', password='123456')

    def process_item(self, item, spider):
        curser = self.conn.cursor()
        sql = '''insert into article (title, url, `desc`, content, author) values (%s, %s, %s, %s, %s)'''
        curser.execute(sql, args=(item['title'], item['url'], item['desc'], item['content'], item['author']))
        self.conn.commit()


    def close_spider(self, spider):
        self.conn.close()
"""