一、CrawlSpider模板
- 创建项目
scrapy startproject 项目名称
- 查看模板
scrapy genspider -l
- 创建crawl模板
scrapy genspider -t crawl 爬虫名称 地址
二、Spider爬虫
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
# 导入LinkExtractor用于提取链接
from scrapy.spiders import CrawlSpider, Rule
# Rule定义一个规则,然后让LinkExtractor取根据这些规则提取url
from CrawlSpiderDemo.items import CrawlspiderdemoItem
# 在scrapy框架中包了两个分类的爬虫分别是:Spider(基本爬虫)和CrawlSpider(增量模板爬虫)
# CrawlSpider是Spider的一个派生类,spider类设计原则只从start_urls列表中提取内容,CrawlSpider定义了一些规则,这些规则可以跟踪链接,从而可以使得一个页面中所有的符合规则的链接都被提取出来放入调度器中
# 在不断访问url的过程中,爬虫匹配到的url越来越多
class DushuSpider(CrawlSpider):
name = 'dushu'
allowed_domains = ['dushu.com']
start_urls = ['https://www.dushu.com/book/1002.html']
rules = (
Rule(LinkExtractor(allow=r'/book/1002_\d+\.html'), callback='parse_item', follow=True),
)
# rules 规则: 包含若干个Rule对象,每一个Rule对象对我们爬取网站的规则都做了一些特定的操作,根据LinkExtractor里面的规则提取出所有的链接,然后把这些链接通过引擎压入调度器的调度队列中,调度器进而去调度下载,然后回调parse_item (这里的回调方法写成了字符串形式) ,再从二次请求的这些url对应的页面中根据LinkExtractor的规则继续匹配(如果有重复,自动剔除),依次类推,直到匹配到所有的页面
# LinkExtractor的匹配规则:
# 用正则表达式来匹配:LinkExtractor(allow="某正则") # /book/1002_\d\.html
# 用xpath匹配:LinkExtractor(restrict_xpath="某xpath路径")
# 用css选择器:LinkExtractor(restrict_css="某css选择器")
def parse_item(self, response):
print(response.url)
# 解析页面
book_list = response.xpath("//div[@class='bookslist']//li")
for book in book_list:
item = CrawlspiderdemoItem()
item["book_name"] = book.xpath(".//h3/a/text()").extract_first()
# 获取到二级页面的url
next_url = "https://www.dushu.com" + book.xpath(".//h3/a/@href").extract_first()
yield scrapy.Request(url=next_url,callback=self.parse_next,meta={"item":item})
def parse_next(self, response):
item = response.meta["item"]
item["price"] = response.xpath("//span[@class='num']/text()").extract_first()
m = response.xpath("//div[@class='text txtsummary']")[2]
item["mulu"] = m.xpath(".//text()").extract()
yield item
使用xpath或其他规则匹配下来的所有节点,返回的类型是列表类型
.extract()方法是提取它的内容
.extract_first()方法是提取列表第一个内容,若列表为空返回空,而不会报错
三、Ip代理设置
- settings.py 设置
IPPOOL = [
{'ip':'113.16.160.101:8118'},
{'ip':'119.31.210.170:7777'},
{'ip':'183.129.207.83:10800'},
# {'ip':''},
# {'ip':''},
# {'ip':''},
# {'ip':''},
# {'ip':''},
]
# 下载中间件设置
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware':123,
'IpAgent.middlewares.IPPOOLS': 125,
}
定义一个字段,表示我们收集好的代理
- middlewares.py
# 从settings文件中导入IPPOOL
import random
from .settings import IPPOOL
# 导入官方文档对应的HttpProxyMiddleware
from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
# 创建一个代理中间件类集成自官方代理中间件
class IPPOOLS(HttpProxyMiddleware):
# 重写初始化方法
def __init__(self,ip=''):
self.ip = ip
# 重写请求处理方法
def process_request(self, request, spider):
# 从ip代理池中随机挑选一个ip地址
current_ip = random.choice(IPPOOL)
print('当前ip是:',current_ip['ip'])
# 设置请求对象的代理服务器是当前ip
request.meta['proxy'] = 'https://' + current_ip['ip']
# 此时就可以把代理ip植入到下载器中
四、动态页面请求之selenium
- settings.py设置
# 下载中间件设置
DOWNLOADER_MIDDLEWARES = {
'Toutiao.middlewares.ToutiaoDownloaderMiddleware': 543,
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware':None,
}
- middlewares.py设置
from scrapy import signals
from selenium import webdriver
from time import sleep
from scrapy.http import HtmlResponse
class ToutiaoDownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_request(self, request, spider):
# 创建一个webdriver对象
opt = webdriver.ChromeOptions()
opt.add_argument("--headless")
driver = webdriver.Chrome(options=opt)
driver.get(request.url)
sleep(3)
# 让页面滚动
js = "var q = document.documentElement.scrollTop=%d"
distance = 100
for i in range(100):
driver.execute_script(js%distance)
distance += 100
sleep(0.5)
body = driver.page_source
print("正在使用中间件下载...")
print("当前浏览器正在访问的网址是:",driver.current_url)
# 响应体需要重新定义
res = HtmlResponse(url=driver.current_url,body=body,encoding='utf-8',request=request)
return res
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
return response
def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception.
# Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
pass
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
五、基本分布式爬虫部署redis储存
scrapy_redis组件
pip install scrapy_redis
1、scrapy和scrapy_redis的区别
scrapy是一个通用的爬虫框架,不支持分布式
scrapy_redis就是为实现scrapy的分布式而诞生的,它里面提功了redis的组件,通过这些redis组件,就可以实现分布式
2、部署分布式
服务器端(master端):
可以用某一台主机作为redis服务器的运行方(即服务端),也称为master
客户端(slaver端):
1)把普通爬虫修改成分布式,去掉start_urls(不让slaver随意的执行),替换成redis_key(为了让master能够控制slaver的爬去)
- settings.py 设置
配置管道中间件
ITEM_PIPELINES = {
# 分布式的爬虫的数据可以不通过本地的管道(数据不需要往本地存),数据需要存在redis数据库中,在这里需要加入一个redis数据库的管道组件
"scrapy_redis.pipelines.RedisPipeline": 400
}
# 指定Redis数据库相关配置
# Redis的主机地址
REDIS_HOST = "134.175.114.102"
# 端口号
REDIS_PORT = 6379
# 密码
# REDIS_PARAMS = {"password":'xxxx'}
# 1、调度器需要切换成Scrapy_Redis的调度器(这个调度器是Scrapy_Redis组件对scrapy原生调度器的重写,加入一些分布式调度的算法)
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# 2、加入scrapy_redis的去重组件
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 3、爬取过程中是否允许暂停
SCHEDULER_PERSIST = True
- spider设置
from scrapy_redis.spiders import RedisCrawlSpider
class ReadbookSpider(RedisCrawlSpider): # 注意继承RedisCrawlSpider
name = 'Readbook'
allowed_domains = ['www.dushu.com']
# start_urls = ['http://www.dushu.com/book/1002.html']
# start_urls = ['https://www.dushu.com/book/1002.html'] # 分布式的爬虫所有的url都是从redis数据库的相关键下面提取
# redis_key这个属性指定了分布式爬虫在获取url的时候从哪些键中获取的
redis_key = "dushu:start_urls"
rules = (
Rule(LinkExtractor(allow=r'/book/1002_?\d*\.html'), callback='parse_item', follow=True),
)