Scrapy应用之抓取《宦海沉浮》小说

目标站点

 

http://www.shushu8.com/huanhaichenfu/

第一步：新建项目

KeysdeMacBook:Desktop keys$ scrapy startproject MyCrawl
New Scrapy project 'MyCrawl', using template directory '/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/scrapy/templates/project', created in:
    /Users/keys/Desktop/MyCrawl
You can start your first spider with:
    cd MyCrawl
    scrapy genspider example example.com

第二步：创建爬虫

KeysdeMacBook:Desktop keys$ cd MyCrawl/
KeysdeMacBook:MyCrawl keys$ scrapy genspider FirstSpider www.shushu8.com/huanhaichenfu

第三步：配置item.py

import scrapy


class MycrawlItem(scrapy.Item):
    url = scrapy.Field()
    title = scrapy.Field()
    text = scrapy.Field()

 

第四步：编写爬虫

# -*- coding: utf-8 -*-
import scrapy
from MyCrawl.items import MycrawlItem


class FirstspiderSpider(scrapy.Spider):
    name = 'FirstSpider'
    allowed_domains = ['www.shushu8.com/huanhaichenfu']
    start_urls = ['http://www.shushu8.com/huanhaichenfu/'+str(i+1) for i in range(502)]

    def parse(self, response):
        url = response.url
        title = response.xpath('//*[@id="main"]/div[2]/div/div[1]/h1/text()').extract_first('')
        text = response.css('#content::text').extract()

        myitem = MycrawlItem()
        myitem['url'] = url
        myitem['title'] = title
        myitem['text'] = ','.join(text)

        yield myitem

第五步：配置pipeline.py

# -*- coding: utf-8 -*-
import pymysql

class MysqlPipeline(object):
    # 采用同步的机制写入mysql
    def __init__(self):
        self.conn = pymysql.connect(
            '127.0.0.1',
            'root',
            'rootkeys',
            'Article',
            charset="utf8",
            use_unicode=True)
        self.cursor = self.conn.cursor()

    def process_item(self, item, spider):
        insert_sql = """
            insert into huanhaichenfu(url, title, text)
            VALUES (%s, %s, %s)
        """
        # 使用VALUES实现传值
        self.cursor.execute(
            insert_sql,
            (item["url"],
             item["title"],
             item["text"]))
        self.conn.commit()

第六步：配置setting.py

# -*- coding: utf-8 -*-

BOT_NAME = 'MyCrawl'
SPIDER_MODULES = ['MyCrawl.spiders']
NEWSPIDER_MODULE = 'MyCrawl.spiders'

USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36'
ROBOTSTXT_OBEY = False
ITEM_PIPELINES = {
   'MyCrawl.pipelines.MysqlPipeline': 1,
}

第七步：运行爬虫

import os
import sys
from scrapy.cmdline import execute


sys.path.append(os.path.dirname(os.path.abspath(__file__)))

run_spider = 'FirstSpider'

if __name__ == '__main__':
    print('Running Spider of ' + run_spider)
    execute(['scrapy', 'crawl', run_spider])