爬虫系列----scrapy爬取网页初始

一 基本流程

  1. 创建工程,工程名称为(cmd):firstblood: scrapy startproject firstblood
  2. 进入工程目录中(cmd):cd :./firstblood
  3. 创建爬虫文件(cmd):scrapy genspider first www.xxx.con (first为爬虫文件名称 www.xxx.com :起始url)
  4. pycharm打开爬虫项目,进入到spider文件下,找到first爬虫文件,书写爬虫代码.注释allowed_domains
  5. 启动爬虫文件(cmd):scrapy crawl first

***在pycharm中启动设置方法

#在项目根目录下新建:entrypoint.py
from scrapy.cmdline import execute
execute(['scrapy', 'crawl', '爬虫名称'])

二 spider反反爬配置

  • robot.txt
settings 中修改为:ROBOTSTXT_OBEY = False
  • UA伪装
setting文件中
USER_AGENT = 'firstblood (+http://www.yourdomain.com)'
修改为:
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36' 自定义请求头信息,重写start_requests方法:
def start_requests(self):
headers={
'Host': 'www.amazon.cn',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36', }
url='https://www.amazon.cn/s/ref=nb_sb_noss?__mk_zh_CN=%E4%BA%9A%E9%A9%AC%E9%80%8A%E7%BD%91%E7%AB%99&url=search-alias%3Daps&field-keywords=iphone-x'
resquest=scrapy.Request(url=url,headers=headers)
yield resquest

三 基本命令汇总

  1. scrapy startproject firstblood #新建工程
  2. scrapy genspider first www.xxx.con #新建爬虫文件
  3. scrapy crawl first #执行爬虫文件,并打印日记
  4. scrapy crawl first --nolog #执行爬虫文件,不打印日记
  5. scrapy crawl qiubai -o qiushibaike.csv 把parse函数的返回结果存入csv文件中
  6. scrapy genspider -t crawl chouti www.xxx.com 创建crawspider爬虫项目

四 存储

  • 基于终端指令的持久化存储(只会将parse函数返回值进行本地持久化存储)

    命令: scrapy crawl qiubai -o qiushibaike.csv

      局限性:只能存储这些后缀的文件('json', 'jsonlines', 'jl', 'csv', 'xml', 'marshal', 'pickle')  

class QiubaiSpider(scrapy.Spider):
name = 'qiubai'
# allowed_domains = ['www.xxx.com']
start_urls = ['https://www.qiushibaike.com/text/'] def parse(self, response):
div_list=response.xpath("//div[@id='content-left']/div")
res_list=[]
for div in div_list:
# author=div.xpath('./div[1]/a[2]/h2/text()')[0]
##scrapy中的xpath返回的是select对象
#<Selector xpath='./div[1]/a[2]/h2/text()' data='\n胡子灬哥\n'>
#获取select对象中data的数据 # 方式一:author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
# 方式二:author=div.xpath('./div[1]/a[2]/h2/text()').extract_first()
author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
content=div.xpath('./a[1]/div[@class="content"]/span//text()').extract()
content="".join(content) # print("author......",author)
# print("content......",content)
# break
dic={
'author':author,
'content':content
}
res_list.append(dic)
return res_list
  • 基于管道操作的持久化存储(持久化存储的操作必须写在管道文件中)

推荐使用:
pip install redis==2.10.6

如何把数据封装到item对象中

1.在items.py文件中定义存储字段的属性

        class QiubaiproItem(scrapy.Item):
# define the fields for your item here like:(定义字段如下:)
# name = scrapy.Field() (name字段=scrapy万能字段)
#示例
author=scrapy.Field()
content=scrapy.Field()

2.爬虫文件spiders/qiubai.py中引入定义的item类:

from qiubaiPro.items import QiubaiproIte

3.实例化items对象

 #实例化 item对象
item=QiubaiproItem()
item['author']=author
item['content']=content
#注意:一条数据一个item对象,pipeline接受一个item就存储一条记录

4.把实例化的对象提交给管道,scrapy自动提交,我们只需要写:

            yield item #每条数据提交一次

5.pipeline.py文件中书写管道存储的逻辑(三种存储方式)

    class QiubaiproPipeline(object):
def process_item(self, item, spider):
print(item)
return item
import pymysql
class Mysql_PipeLine(object):
#全局定义管道conn和游标cursor
#导入pymysql
conn=None
cursor=None
def open_spider(self, spider):
#端口号是数字而非字符串,
self.conn=pymysql.Connect(host='127.0.0.1',port=3306,user='root',password='',db='scrapy')
self.cursor = self.conn.cursor()
def process_item(self, item, spider):
# print(item)
try:
self.cursor.execute('insert into qiubai values ("%s","%s");'%(item['author'],item['content']))
self.conn.commit()
except Exception as e:
print(e)
self.conn.rollback()
return item def close_spider(self, spider):
# self.cursor.close()
self.conn.close() from redis import Redis
class Redis_PipeLine(object):
conn=None def open_spider(self,spider):
# 链接数据库
self.conn=Redis(host='127.0.0.1',port=6379) def process_item(self,item,spider):
dic={
'author':item['author'],
'content':item['content']
}
self.conn.lpush('qiubai',dic) 6 settings文件中开启item_pipeline功能
#允许书写多个管道,多种存储方式
ITEM_PIPELINES = {
'qiubaiPro.pipelines.QiubaiproPipeline': 300,
#'管道路径.管道名称':优先级
} ITEM_PIPELINES = {
'qiubaiPro.pipelines.QiubaiproPipeline': 300,
#新增的管道
'qiubaiPro.pipelines.Mysql_PipeLine': 301,
'qiubaiPro.pipelines.Redis_PipeLine': 302, }

五 简单实例

  • 新建的爬虫文件qiubai.py
# -*- coding: utf-8 -*-
import scrapy
from qiubaiPro.items import QiubaiproItem '''
1 基于终端指令的持久化存储(只会将parse函数返回值进行本地持久化存储)
命令: scrapy crawl qiubai -o qiushibaike.csv 局限性:只能存储这些后缀的文件('json', 'jsonlines', 'jl', 'csv', 'xml', 'marshal', 'pickle')
'''
# 基于终端指令的持久化存储(只会将parse函数返回值进行本地持久化存储)
class QiubaiSpider(scrapy.Spider):
name = 'qiubai'
# allowed_domains = ['www.xxx.com']
start_urls = ['https://www.qiushibaike.com/text/'] def parse(self, response):
div_list=response.xpath("//div[@id='content-left']/div")
res_list=[]
for div in div_list: author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
content=div.xpath('./a[1]/div[@class="content"]/span//text()').extract()
content="".join(content) dic={
'author':author,
'content':content
}
res_list.append(dic)
return res_list # 基于管道操作的持久化存储(持久化存储的操作必须写在管道文件中)
class QiubaiSpider(scrapy.Spider):
name = 'qiubai'
start_urls = ['https://www.qiushibaike.com/text/'] def parse(self, response):
div_list=response.xpath("//div[@id='content-left']/div")
for div in div_list:
try:
author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
except Exception as e:
# print(e)
author=div.xpath('./div[1]/span[2]/h2/text()')[0].extract() content=div.xpath('./a[1]/div[@class="content"]/span//text()').extract()
content="".join(content) #实例化 item对象
item=QiubaiproItem()
item['author']=author
item['content']=content
# print(item['author'])
#提交管道
yield item
  • items.py
import scrapy

class QiubaiproItem(scrapy.Item):

    author=scrapy.Field()
content=scrapy.Field()
  • pipeline.py
# -*- coding: utf-8 -*-
import pymysql
from redis import Redis #一个类对应一个存储方式
#存入文件qiubai.txt
class QiubaiproPipeline(object):
fp = None # 文件管道 # open_spider重写父类方法,爬虫过程中只会执行一次
def open_spider(self,spider):
self.fp=open('qiubai.txt','w',encoding='utf-8') # 处理item文件会执行多次,因此文件打开和关闭操作不应该放在这个函数内部,
# 否则,执行效率太低
def process_item(self, item, spider):
# print(item)
self.fp.write(item['author']+':'+item['content'])
return item # close_spider重写父类spider的方法,在爬虫执行过程只会执行一次 def close_spider(self,spider):
self.fp.close() #存入mysql数据库
#同时在settings添加该管道路径
class Mysql_PipeLine(object):
#全局定义管道conn和游标cursor
#导入pymysql
conn=None
cursor=None
def open_spider(self, spider):
#端口号是数字而非字符串,
self.conn=pymysql.Connect(host='127.0.0.1',port=3306,user='root',password='',db='scrapy')
self.cursor = self.conn.cursor()
def process_item(self, item, spider):
# print(item)
try:
self.cursor.execute('insert into qiubai values ("%s","%s");'%(item['author'],item['content']))
self.conn.commit()
except Exception as e:
print(e)
self.conn.rollback()
return item def close_spider(self, spider):
# self.cursor.close()
self.conn.close() class Redis_PipeLine(object):
conn=None def open_spider(self,spider):
# 链接数据库
self.conn=Redis(host='127.0.0.1',port=6379) def process_item(self,item,spider):
dic={
'author':item['author'],
'content':item['content']
}
self.conn.lpush('qiubai',dic)

六 scrapy中的xpath的不同点

  • scrapy中xpath表达式获取到的数据不是标签对象,而是select对象
 author=div.xpath('./div[1]/a[2]/h2/text()')[0]
#<Selector xpath='./div[1]/a[2]/h2/text()' data='\n胡子灬哥\n'>
  • 获取select对象中的data的数据
方式一:author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract()
方式二:author=div.xpath('./div[1]/a[2]/h2/text()').extract_first()
author=div.xpath('./div[1]/a[2]/h2/text()')[0].extract() #返回值为列表

七 日记处理

上一篇:《疯狂Java:突破程序员基本功的16课》读书笔记-第一章 数组与内存控制


下一篇:ldap集成jira