爬虫框架：scrapy

#1、执行全局命令：请确保不在某个项目的目录下，排除受该项目配置的影响
scrapy startproject MyProject

cd MyProject
scrapy genspider baidu www.baidu.com

scrapy settings --get XXX #如果切换到项目目录下，看到的则是该项目的配置

scrapy runspider baidu.py

scrapy shell https://www.baidu.com
    response
    response.status
    response.body
    view(response)
    
scrapy view https://www.taobao.com #如果页面显示内容不全，不全的内容则是ajax请求实现的，以此快速定位问题

scrapy fetch --nolog --headers https://www.taobao.com

scrapy version #scrapy的版本

scrapy version -v #依赖库的版本


#2、执行项目命令：切到项目目录下
scrapy crawl baidu
scrapy check
scrapy list
scrapy parse http://quotes.toscrape.com/ --callback parse
scrapy bench
    

import scrapy
 
class XiaoHuarSpider(scrapy.spiders.Spider):
    name = "xiaohuar"                            # 爬虫名称 *****
    allowed_domains = ["xiaohuar.com"]  # 允许的域名
    start_urls = [
        "http://www.xiaohuar.com/hua/",   # 其实URL
    ]
 
    def parse(self, response):
        # 访问起始URL并获取结果后的回调函数

import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding=‘gb18030‘)

#在项目目录下新建：entrypoint.py
from scrapy.cmdline import execute
execute([‘scrapy‘, ‘crawl‘, ‘xiaohua‘])

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class BaiduSpider(CrawlSpider):
    name = ‘xiaohua‘
    allowed_domains = [‘www.xiaohuar.com‘]
    start_urls = [‘http://www.xiaohuar.com/v/‘]
    # download_delay = 1

    rules = (
        Rule(LinkExtractor(allow=r‘p\-\d\-\d+\.html$‘), callback=‘parse_item‘,follow=True,),
    )


    def parse_item(self, response):

        if url:
            print(‘======下载视频==============================‘, url)
            yield scrapy.Request(url,callback=self.save)



    def save(self,response):
        print(‘======保存视频==============================‘,response.url,len(response.body))

        import time
        import hashlib
        m=hashlib.md5()
        m.update(str(time.time()).encode(‘utf-8‘))
        m.update(response.url.encode(‘utf-8‘))

        filename=r‘E:\\mv\\%s.mp4‘ %m.hexdigest()
        with open(filename,‘wb‘) as f:
            f.write(response.body)

response.selector.css()
response.selector.xpath()
可简写为
response.css()
response.xpath()

#1 //与/
response.xpath(‘//body/a/‘)#
response.css(‘div a::text‘)

>>> response.xpath(‘//body/a‘) #开头的//代表从整篇文档中寻找,body之后的/代表body的儿子
[]
>>> response.xpath(‘//body//a‘) #开头的//代表从整篇文档中寻找,body之后的//代表body的子子孙孙
[<Selector xpath=‘//body//a‘ data=‘<a href="image1.html">Name: My image 1 <‘>, <Selector xpath=‘//body//a‘ data=‘<a href="image2.html">Name: My image 2 <‘>, <Selector xpath=‘//body//a‘ data=‘<a href="
image3.html">Name: My image 3 <‘>, <Selector xpath=‘//body//a‘ data=‘<a href="image4.html">Name: My image 4 <‘>, <Selector xpath=‘//body//a‘ data=‘<a href="image5.html">Name: My image 5 <‘>]

#2 text
>>> response.xpath(‘//body//a/text()‘)
>>> response.css(‘body a::text‘)

#3、extract与extract_first:从selector对象中解出内容
>>> response.xpath(‘//div/a/text()‘).extract()
[‘Name: My image 1 ‘, ‘Name: My image 2 ‘, ‘Name: My image 3 ‘, ‘Name: My image 4 ‘, ‘Name: My image 5 ‘]
>>> response.css(‘div a::text‘).extract()
[‘Name: My image 1 ‘, ‘Name: My image 2 ‘, ‘Name: My image 3 ‘, ‘Name: My image 4 ‘, ‘Name: My image 5 ‘]

>>> response.xpath(‘//div/a/text()‘).extract_first()
‘Name: My image 1 ‘
>>> response.css(‘div a::text‘).extract_first()
‘Name: My image 1 ‘

#4、属性：xpath的属性加前缀@
>>> response.xpath(‘//div/a/@href‘).extract_first()
‘image1.html‘
>>> response.css(‘div a::attr(href)‘).extract_first()
‘image1.html‘

#4、嵌套查找
>>> response.xpath(‘//div‘).css(‘a‘).xpath(‘@href‘).extract_first()
‘image1.html‘

#5、设置默认值
>>> response.xpath(‘//div[@id="xxx"]‘).extract_first(default="not found")
‘not found‘

#4、按照属性查找
response.xpath(‘//div[@id="images"]/a[@href="image3.html"]/text()‘).extract()
response.css(‘#images a[@href="image3.html"]/text()‘).extract()

#5、按照属性模糊查找
response.xpath(‘//a[contains(@href,"image")]/@href‘).extract()
response.css(‘a[href*="image"]::attr(href)‘).extract()

response.xpath(‘//a[contains(@href,"image")]/img/@src‘).extract()
response.css(‘a[href*="imag"] img::attr(src)‘).extract()

response.xpath(‘//*[@href="image1.html"]‘)
response.css(‘*[href="image1.html"]‘)

#6、正则表达式
response.xpath(‘//a/text()‘).re(r‘Name: (.*)‘)
response.xpath(‘//a/text()‘).re_first(r‘Name: (.*)‘)

#7、xpath相对路径
>>> res=response.xpath(‘//a[contains(@href,"3")]‘)[0]
>>> res.xpath(‘img‘)
[<Selector xpath=‘img‘ data=‘<img src="image3_thumb.jpg">‘>]
>>> res.xpath(‘./img‘)
[<Selector xpath=‘./img‘ data=‘<img src="image3_thumb.jpg">‘>]
>>> res.xpath(‘.//img‘)
[<Selector xpath=‘.//img‘ data=‘<img src="image3_thumb.jpg">‘>]
>>> res.xpath(‘//img‘) #这就是从头开始扫描
[<Selector xpath=‘//img‘ data=‘<img src="image1_thumb.jpg">‘>, <Selector xpath=‘//img‘ data=‘<img src="image2_thumb.jpg">‘>, <Selector xpath=‘//img‘ data=‘<img src="image3_thumb.jpg">‘>, <Selector xpa
th=‘//img‘ data=‘<img src="image4_thumb.jpg">‘>, <Selector xpath=‘//img‘ data=‘<img src="image5_thumb.jpg">‘>]

#8、带变量的xpath
>>> response.xpath(‘//div[@id=$xxx]/a/text()‘,xxx=‘images‘).extract_first()
‘Name: My image 1 ‘
>>> response.xpath(‘//div[count(a)=$yyy]/@id‘,yyy=5).extract_first() #求有5个a标签的div的id
‘images‘

1、
scrapy startproject Amazon
cd Amazon
scrapy genspider spider_goods www.amazon.cn

2、settings.py
ROBOTSTXT_OBEY = False
#请求头
DEFAULT_REQUEST_HEADERS = {
    ‘Referer‘:‘https://www.amazon.cn/‘,
    ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36‘
}
#打开注释
HTTPCACHE_ENABLED = True
HTTPCACHE_EXPIRATION_SECS = 0
HTTPCACHE_DIR = ‘httpcache‘
HTTPCACHE_IGNORE_HTTP_CODES = []
HTTPCACHE_STORAGE = ‘scrapy.extensions.httpcache.FilesystemCacheStorage‘

3、items.py
class GoodsItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    #商品名字
    goods_name = scrapy.Field()
    #价钱
    goods_price = scrapy.Field()
    #配送方式
    delivery_method=scrapy.Field()

4、spider_goods.py
# -*- coding: utf-8 -*-
import scrapy

from Amazon.items import  GoodsItem
from scrapy.http import Request
from urllib.parse import urlencode

class SpiderGoodsSpider(scrapy.Spider):
    name = ‘spider_goods‘
    allowed_domains = [‘www.amazon.cn‘]
    # start_urls = [‘http://www.amazon.cn/‘]


    def __int__(self,keyword=None,*args,**kwargs):
        super(SpiderGoodsSpider).__init__(*args,**kwargs)
        self.keyword=keyword

    def start_requests(self):
        url=‘https://www.amazon.cn/s/ref=nb_sb_noss_1?‘
        paramas={
            ‘__mk_zh_CN‘: ‘亚马逊网站‘,
            ‘url‘: ‘search - alias = aps‘,
            ‘field-keywords‘: self.keyword
        }
        url=url+urlencode(paramas,encoding=‘utf-8‘)
        yield Request(url,callback=self.parse_index)


    def parse_index(self, response):
        print(‘解析索引页:%s‘ %response.url)

        urls=response.xpath(‘//*[contains(@id,"result_")]/div/div[3]/div[1]/a/@href‘).extract()
        for url in urls:
            yield Request(url,callback=self.parse_detail)

        next_url=response.urljoin(response.xpath(‘//*[@id="pagnNextLink"]/@href‘).extract_first())
        print(‘下一页的url‘,next_url)
        yield Request(next_url,callback=self.parse_index)

    def parse_detail(self,response):
        print(‘解析详情页:%s‘ %(response.url))

        item=GoodsItem()
        # 商品名字
        item[‘goods_name‘] = response.xpath(‘//*[@id="productTitle"]/text()‘).extract_first().strip()
        # 价钱
        item[‘goods_price‘] = response.xpath(‘//*[@id="priceblock_ourprice"]/text()‘).extract_first().strip()
        # 配送方式
        item[‘delivery_method‘] = ‘‘.join(response.xpath(‘//*[@id="ddmMerchantMessage"]//text()‘).extract())
        return item

5、自定义pipelines
#sql.py
import pymysql
import settings


MYSQL_HOST=settings.MYSQL_HOST
MYSQL_PORT=settings.MYSQL_PORT
MYSQL_USER=settings.MYSQL_USER
MYSQL_PWD=settings.MYSQL_PWD
MYSQL_DB=settings.MYSQL_DB

conn=pymysql.connect(
    host=MYSQL_HOST,
    port=int(MYSQL_PORT),
    user=MYSQL_USER,
    password=MYSQL_PWD,
    db=MYSQL_DB,
    charset=‘utf8‘
)
cursor=conn.cursor()

class Mysql(object):
    @staticmethod
    def insert_tables_goods(goods_name,goods_price,deliver_mode):
        sql=‘insert into goods(goods_name,goods_price,delivery_method) values(%s,%s,%s)‘
        cursor.execute(sql,args=(goods_name,goods_price,deliver_mode))
        conn.commit()

    @staticmethod
    def is_repeat(goods_name):
        sql=‘select count(1) from goods where goods_name=%s‘
        cursor.execute(sql,args=(goods_name,))
        if cursor.fetchone()[0] >= 1:
            return True

if __name__ == ‘__main__‘:
    cursor.execute(‘select * from goods;‘)
    print(cursor.fetchall())


#pipelines.py
from Amazon.mysqlpipelines.sql import Mysql


class AmazonPipeline(object):
    def process_item(self, item, spider):
        goods_name=item[‘goods_name‘]
        goods_price=item[‘goods_price‘]
        delivery_mode=item[‘delivery_method‘]
        if not Mysql.is_repeat(goods_name):
            Mysql.insert_table_goods(goods_name,goods_price,delivery_mode)



6、创建数据库表
create database amazon charset utf8;
create table goods(
    id int primary key auto_increment,
    goods_name char(30),
    goods_price char(20),
    delivery_method varchar(50)
);

7、settings.py
MYSQL_HOST=‘localhost‘
MYSQL_PORT=‘3306‘
MYSQL_USER=‘root‘
MYSQL_PWD=‘123‘
MYSQL_DB=‘amazon‘


#数字代表优先级程度（1-1000随意设置，数值越低，组件的优先级越高）
ITEM_PIPELINES = {
   ‘Amazon.mysqlpipelines.pipelines.mazonPipeline‘: 1,
}


#8、在项目目录下新建：entrypoint.py
from scrapy.cmdline import execute
execute([‘scrapy‘, ‘crawl‘, ‘spider_goods‘,‘-a‘,‘keyword=iphone8‘])