爬虫scrapy组件 请求传参,post请求,中间件

post请求

在scrapy组件使用post请求需要调用

def start_requests(self): 
进行传参再回到

yield scrapy.FormRequest(url=url,formdata=data,callback=self.parse)
进行post请求   其中FormRequest()为post 请求方式

import scrapy

class PostSpider(scrapy.Spider):
    name = 'post'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://fanyi.baidu.com/sug']

    def start_requests(self):
        data = {
            'kw':'dog'
        }
        for url in self.start_urls:
            yield scrapy.FormRequest(url=url,formdata=data,callback=self.parse)
#scrapy.FormRequest() 进行post请求
    def parse(self, response):
        print(response.text)

请求传参

scrapy请求传参 主核心的就是

meta={'item':item}

是一个字典结构,用来存储item 等

通过回调函数的返回url进行访问

import scrapy
from moviePro.items import MovieproItem

class MovieSpider(scrapy.Spider):
    name = 'movie'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.4567tv.tv/frim/index1.html']
    #解析详情页中的数据
    def parse_detail(self,response):
        #response.meta返回接收到的meta字典
        item = response.meta['item']
        actor = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[3]/a/text()').extract_first()
        item['actor'] = actor

        yield item

    def parse(self, response):
        li_list = response.xpath('//li[@class="col-md-6 col-sm-4 col-xs-3"]')
        for li in li_list:
            item = MovieproItem()
            name = li.xpath('./div/a/@title').extract_first()
            detail_url = 'https://www.4567tv.tv'+li.xpath('./div/a/@href').extract_first()
            item['name'] = name
            #meta参数:请求传参.meta字典就会传递给回调函数的response参数
            yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={'item':item})

 　　　　　　　　#这里url 值定的start_urls 调用直接访问

注意:这里存储的字段一定要与items.py 创建的一致,就是以items.py的字段为主

items.py

import scrapy

class MovieproItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
     name = scrapy.Field()
     actor = scrapy.Field()

pipelines.py

import pymysql

class MovieproPipeline(object):
    conn = None
    cursor = None

    def open_spider(self,spider):
        print("开始爬虫")
        self.conn = pymysql.Connect(host='127.0.0.1',port=3306, user='root', password="",db='movie',charset='utf8')

    def process_item(self, item, spider):
        self.cursor = self.conn.cursor()
        try:
            self.cursor.execute('insert into av values("%s","%s")'%(item['name'],item['actor']))
            self.conn.commit()
        except Exception as e:
            self.conn.rollback()

    def close_spider(self,spider):
        print('结束爬虫')
        self.cursor.close()
        self.conn.close()

在执行时可以 省去--nolog,在setting中配置LOG_LEVEL="ERROR"

也可以定义写入文件 ,在setting中配置LOG_FILE = "./log.txt"

五大核心组件

其中dowmloader 最为重要,它分为三大重要的方法

(1)
def process_request(self, request, spider):

return None
需要有返回NONE 同django的中间建,表示在访问来之前进行操作
用来范文时 ,进行user_agent 的替换, request.headers['User-Agent'] = random.choice([ ...])

(2)

def process_response(self, request, response, spider):

需要有返回respons给 spider 进行数据 处理
用作selenium 模拟访问时,倘若放在spider访问,一条数据就需要生成一个bro,所以添加到这里,一次就好
它将获取的数据

return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request)

返回给spider 进行数据解析

return response

(3)

def process_exception(self, request, exception, spider):

pass

指进行报错使用的情况
用作代理吃进行请求代理ip 的设置

request.meta['proxy'] = random.choice([])

使用

 import random

 class MiddleproDownloaderMiddleware(object):
     user_agent_list = [
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 "
         "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1",
         "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 "
         "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11",
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 "
         "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6",
         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 "
         "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6",
         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 "
         "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1",
         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 "
         "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5",
         "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 "
         "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5",
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
         "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
         "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3",
         "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 "
         "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3",
         "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 "
         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24",
         "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 "
         "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24"
     ]
     # 可被选用的代理IP
     PROXY_http = [
         '153.180.102.104:80',
         '195.208.131.189:56055',
     ]
     PROXY_https = [
         '120.83.49.90:9000',
         '95.189.112.214:35508',
     ]
    #拦截所有未发生异常的请求
     def process_request(self, request, spider):

         #使用UA池进行请求的UA伪装
         print('this is process_request')
         request.headers['User-Agent'] = random.choice(self.user_agent_list)
         print(request.headers['User-Agent'])

         return None
     #拦截所有的响应
     def process_response(self, request, response, spider):

         return response
     #拦截到产生异常的请求
     def process_exception(self, request, exception, spider):

         print('this is process_exception!')
         if request.url.split(':')[0] == 'http':
             request.meta['proxy'] = random.choice(self.PROXY_http)
         else:
             request.meta['proxy'] = random.choice(self.PROXY_https)

selenium的中间件使用

注意:使用中间件需要打开中间件的封印 (p56-58)

DOWNLOADER_MIDDLEWARES = {
   'wangyiPro.middlewares.WangyiproDownloaderMiddleware': 543,
}

通过实例化bro对象,在请求结束后访问download中间件的 def response(self):

通过获取的数据

return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request)

返回给spider

import scrapy
from selenium import webdriver

'''
在scrapy中使用selenium的编码流程:
    1.在spider的构造方法中创建一个浏览器对象(作为当前spider的一个属性)
    2.重写spider的一个方法closed(self,spider),在该方法中执行浏览器关闭的操作
    3.在下载中间件的process_response方法中,通过spider参数获取浏览器对象
    4.在中间件的process_response中定制基于浏览器自动化的操作代码(获取动态加载出来的页面源码数据)
    5.实例化一个响应对象,且将page_source返回的页面源码封装到该对象中
    6.返回该新的响应对象
'''

class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['http://war.163.com/']
    def __init__(self):
        self.bro = webdriver.Chrome(executable_path=r'C:\Users\Administrator\Desktop\爬虫+数据\day_03_爬虫\chromedriver.exe')
    def parse(self, response):
        div_list = response.xpath('//div[@class="data_row news_article clearfix "]')
        for div in div_list:
            title = div.xpath('.//div[@class="news_title"]/h3/a/text()').extract_first()
            print(title)
    def closed(self,spider):
        print('关闭浏览器对象!')
        self.bro.quit()

def process_response(self, request, response, spider):

    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
        print('即将返回一个新的响应对象!!!')
        #如何获取动态加载出来的数据
        bro = spider.bro
        bro.get(url=request.url)
        sleep(3)
        #包含了动态加载出来的新闻数据
        page_text = bro.page_source
        sleep(3)
        return HtmlResponse(url=spider.bro.current_url,body=page_text,encoding='utf-8',request=request)