<scrapy爬虫>爬取quotes.toscrape.com

1.创建scrapy项目

dos窗口输入:

scrapy startproject quote

cd quote

2.编写item.py文件(相当于编写模板,需要爬取的数据在这里定义)

import scrapy

class QuoteItem(scrapy.Item):
    # define the fields for your item here like:
    text = scrapy.Field()
    author = scrapy.Field()
    tags = scrapy.Field()

　　

3.创建爬虫文件

dos窗口输入:

scrapy genspider myspider quotes.toscrape.com

4.编写myspider.py文件(接收响应,处理数据)

# -*- coding: utf-8 -*-
import scrapy
from quote.items import QuoteItem

class MyspiderSpider(scrapy.Spider):
    name = 'myspider'
    allowed_domains = ['quotes.toscrape.com']
    start_urls = ['http://quotes.toscrape.com/']

    def parse(self, response):
        for each in response.xpath('//div[@class="quote"]'):
            item = QuoteItem()
            item['text'] = each.xpath('./span/text()').extract()[0]
            item['author'] = each.xpath('.//small/text()').extract()[0]
            list = each.xpath('.//a[@class="tag"]/text()').extract()
            #列表形式的文件不能存入mysql,需要弄成str形式
            item['tags']= '/'.join(list)
            yield item

        next = response.xpath('//li[@class="next"]/a/@href').extract()[0]
        url = response.urljoin(next)
        yield scrapy.Request(url=url,callback=self.parse)

　　

5.编写pipelines.py(存储数据)

存储到mysql

import pymysql.cursors

class QuotePipeline(object):
    def __init__(self):
        self.connect = pymysql.connect(
            host='localhost',
            user='root',
            password='',
            database='quotes',
            charset='utf8',
        )
        self.cursor = self.connect.cursor()

    def process_item(self, item, spider):
        item = dict(item)
        sql = 'insert into quote(text,author,tags) values(%s,%s,%s)'
        self.cursor.execute(sql,(item['text'],item['author'],item['tags']))
        self.connect.commit()
        return item

    def close_spider(self,spider):
        self.cursor.close()
        self.connect.close()　　

改进版:

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html
import pymysql.cursors

class QuotePipeline(object):
	def __init__(self):
		self.connect = pymysql.connect(
			host='localhost',
			user='root',
			password='',
			database='quotes',
			charset='utf8',
		)
		self.cursor = self.connect.cursor()

	def process_item(self, item, spider):
		item = dict(item)
		table = 'quote'
		keys = ','.join(item.keys())
		values = ','.join(['%s']*len(item))
		sql = 'insert into {table}({keys}) values({values})'.format(table=table,keys=keys,values=values)
		try:
			if self.cursor.execute(sql, tuple(item.values())):
				self.connect.commit()
				print("Successful!")
		except:
			print("Failed!")
			self.connect.rollback()
		return item

	def close_spider(self, spider):
		self.cursor.close()
		self.connect.close()

存储到mongoDB

　　1.在setting文件设置2个属性

MONGO_URI = 'localhost'
MONGO_DB = 'study'

#一个管道文件

ITEM_PIPELINES = {
   # 'quote.pipelines.QuotePipeline': 300,
   'quote.pipelines.MongoPipeline': 300,

}

　　2.pipeline.py

import pymongo

class MongoPipeline(object):
	# 表名字
	collection = 'student'

	def __init__(self, mongo_uri, mongo_db):
		self.mongo_uri = mongo_uri
		self.mongo_db = mongo_db

	@classmethod
	def from_crawler(cls, crawler):
		return cls(
			mongo_uri=crawler.settings.get('MONGO_URI'),
			mongo_db=crawler.settings.get('MONGO_DB'),
		)

	def open_spider(self, spider):
		self.client = pymongo.MongoClient(self.mongo_uri)
		self.db = self.client[self.mongo_db]

	def close_spider(self, spider):
		self.client.close()

	def process_item(self, item, spider):
		# 插入到mongo数据库
		self.db[self.collection].insert(dict(item))
		return item

　　

　　　　

6.编写settings.py(设置headers,pipelines等)

robox协议

# Obey robots.txt rules
ROBOTSTXT_OBEY = False　　

headers

DEFAULT_REQUEST_HEADERS = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
  # 'Accept-Language': 'en',
}

pipelines

ITEM_PIPELINES = {
   'quote.pipelines.QuotePipeline': 300,
}

　　

7.运行爬虫

dos窗口输入:

scrapy crawl myspider　

运行结果