scrapy 递归发送请求， 请求附带参数，手动发送请求， 设置ua与代理池

scrapy递归爬取网页

爬取网易新闻的五个分类下的标题和正文,结合selenium

# -*- coding: utf-8 -*-
import scrapy
from wangyiPro.items import WangyiproItem
from selenium import webdriver
class WangyiSpider(scrapy.Spider):
    name = 'wangyi'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']
    #浏览器实例化的操作只会被执行一次
    bro = webdriver.Chrome(executable_path='chromedriver.exe')

    urls = []#最终存放的就是五个板块对应的url
    def parse(self, response):
        li_list = response.xpath('//*[@id="index2016_wrap"]/div[1]/div[2]/div[2]/div[2]/div[2]/div/ul/li')
        for index in [3,4,6,7,8]:
            li = li_list[index]
            new_url = li.xpath('./a/@href').extract_first()

            self.urls.append(new_url)
            #是五大板块对应的url进行请求发送
            yield scrapy.Request(url=new_url,callback=self.parse_news)

    #是用来解析每一个板块对应的新闻数据（新闻的标题）
    def parse_news(self,response):
        div_list = response.xpath('//div[@class="ndi_main"]/div')
        for div in div_list:
            title = div.xpath('./div/div[1]/h3/a/text()').extract_first()
            news_detail_url = div.xpath('./div/div[1]/h3/a/@href').extract_first()

            #实例化item对象将解析到的标题和内容存储到item对象中
            item = WangyiproItem()
            item['title'] = title

            #对详情页的url进行手动请求发送以便回去新闻的内容
            yield scrapy.Request(url=news_detail_url,callback=self.parse_detail,meta={'item':item})
    def parse_detail(self,response):
        item = response.meta['item']
        #通过response解析出新闻的内容
        content = response.xpath('//div[@id="endText"]//text()').extract()
        content = ''.join(content)

        item['content'] = content

        yield item


    def closed(self,spider):
        print('爬虫整体结束！！！')
        self.bro.quit()

结合selenium,在middlewares.py文件中

from scrapy import signals
from scrapy.http import HtmlResponse
from time import sleep

class WangyiproDownloaderMiddleware(object):


    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    #拦截整个工程中所有的响应对象
    def process_response(self, request, response, spider):
        if request.url in spider.urls:
            #就要将其对应的响应对象进行处理

            #获取了在爬虫类中定义好的浏览器对象
            bro = spider.bro
            bro.get(request.url)

            bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
            sleep(1)
            bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
            sleep(1)
            bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
            sleep(1)
            bro.execute_script('window.scrollTo(0,document.body.scrollHeight)')
            sleep(1)
            #获取携带了新闻数据的页面源码数据
            page_text = bro.page_source
            #实例化一个新的响应对象
            new_response = HtmlResponse(url=request.url,body=page_text,encoding='utf-8',request=request)
            return new_response
        else:
            return response

scrapy请求传参

1.爬取www.id97.com电影网，将一级页面中的电影名称，类型，评分一级二级页面中的上映时间，导演，片长进行爬取。

爬虫文件:

# -*- coding: utf-8 -*-
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']

    #通用的url模板只适用于非第一页
    url = 'https://www.4567tv.tv/frim/index1-%d.html'
    page = 2

    #电影名称（首页），简介（详情页）
    def parse(self, response):
        li_list = response.xpath('/html/body/div[1]/div/div/div/div[2]/ul/li')
        for li in li_list:
            name = li.xpath('./div/a/@title').extract_first()
            detail_url = 'https://www.4567tv.tv'+li.xpath('./div/a/@href').extract_first()
            item = MovieproItem()
            item['name'] = name

            #对详情页的url发起get请求
            #请求传参：meta参数对应的字典就可以传递给请求对象中指定好的回调函数
            yield scrapy.Request(url=detail_url,callback=self.detail_parse,meta={'item':item})
        if self.page <= 5:
            new_url = format(self.url%self.page)
            self.page += 1
            yield scrapy.Request(url=new_url,callback=self.parse)
    #解析详情页的页面数据
    def detail_parse(self,response):
        #回调函数内部通过response.meta就可以接收到请求传参传递过来的字典
        item = response.meta['item']
        desc = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[5]/span[2]/text()').extract_first()
        item['desc'] = desc

        yield item

items文件:

import scrapy

class MovieproItem(scrapy.Item):
    name = scrapy.Field()
    desc = scrapy.Field()

scrapy手动请求发送

# -*- coding: utf-8 -*-
import scrapy


class PostdemoSpider(scrapy.Spider):
    name = 'postDemo'
    # allowed_domains = ['www.xxx.com']
    #https://fanyi.baidu.com/sug
    start_urls = ['https://fanyi.baidu.com/sug']
    #父类方法，就是将start_urls中的列表元素进行get请求的发送
    # def start_requests(self):
    #     for url in self.start_urls:
    #         yield scrapy.Request(url=url,callback=self.parse)

    def start_requests(self):
        for url in self.start_urls:
            data = {
                'kw':'cat'
            }
            #post请求的手动发送使用的是FormRequest
            yield scrapy.FormRequest(url=url,callback=self.parse,formdata=data)

    def parse(self, response):
        print(response.text)

scrapy中间件设置UA及代理池

注意要在settings文件中将中间件打开

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

# Define here the models for your spider middleware
#
# See documentation in:
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html

from scrapy import signals
import random

#批量拦截所有的请求和响应
class MiddlewearproDownloaderMiddleware(object):
    #UA池
    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"
    ]
    #代理池
    PROXY_http = [
        '153.180.102.104:80',
        '195.208.131.189:56055',
    ]
    PROXY_https = [
        '120.83.49.90:9000',
        '95.189.112.214:35508',
    ]

    #拦截正常请求：request就是该方法拦截到的请求，spider就是爬虫类实例化的一个对象
    def process_request(self, request, spider):
        print('this is process_request!!!')
        #UA伪装
        request.headers['User-Agent'] = random.choice(self.user_agent_list)
        return None

    #拦截所有的响应
    def process_response(self, request, response, spider):

        return response

    #拦截发生异常的请求对象
    def process_exception(self, request, exception, spider):
        print('this is process_exception!!!!')
        #代理ip的设定
        if request.url.split(':')[0] == 'http':
            request.meta['proxy'] = random.choice(self.PROXY_http)
        else:
            request.meta['proxy'] = random.choice(self.PROXY_https)

        #将修正后的请求对象重新进行请求发送
        return request