scrapy 遞歸發送請求， 請求附帶參數，手動發送請求， 設置ua與代理池

scrapy遞歸爬取網頁

爬取網易新聞的五個分類下的標題和正文,結合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/']
    #瀏覽器實例化的操作只會被執行一次
    bro = webdriver.Chrome(executable_path='chromedriver.exe')

    urls = []#最終存放的就是五個板塊對應的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)
            #是五大板塊對應的url進行請求發送
            yield scrapy.Request(url=new_url,callback=self.parse_news)

    #是用來解析每一個板塊對應的新聞數據（新聞的標題）
    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()

            #實例化item對象將解析到的標題和內容存儲到item對象中
            item = WangyiproItem()
            item['title'] = title

            #對詳情頁的url進行手動請求發送以便回去新聞的內容
            yield scrapy.Request(url=news_detail_url,callback=self.parse_detail,meta={'item':item})
    def parse_detail(self,response):
        item = response.meta['item']
        #通過response解析出新聞的內容
        content = response.xpath('//div[@id="endText"]//text()').extract()
        content = ''.join(content)

        item['content'] = content

        yield item


    def closed(self,spider):
        print('爬蟲整體結束！！！')
        self.bro.quit()

結合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

    #攔截整個工程中所有的響應對象
    def process_response(self, request, response, spider):
        if request.url in spider.urls:
            #就要將其對應的響應對象進行處理

            #獲取了在爬蟲類中定義好的瀏覽器對象
            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)
            #獲取攜帶了新聞數據的頁面源碼數據
            page_text = bro.page_source
            #實例化一個新的響應對象
            new_response = HtmlResponse(url=request.url,body=page_text,encoding='utf-8',request=request)
            return new_response
        else:
            return response

scrapy請求傳參

1.爬取www.id97.com電影網，將一級頁面中的電影名稱，類型，評分一級二級頁面中的上映時間，導演，片長進行爬取。

爬蟲文件:

# -*- 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模板只適用於非第一頁
    url = 'https://www.4567tv.tv/frim/index1-%d.html'
    page = 2

    #電影名稱（首頁），簡介（詳情頁）
    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

            #對詳情頁的url發起get請求
            #請求傳參：meta參數對應的字典就可以傳遞給請求對象中指定好的回調函數
            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)
    #解析詳情頁的頁面數據
    def detail_parse(self,response):
        #回調函數內部通過response.meta就可以接收到請求傳參傳遞過來的字典
        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手動請求發送

# -*- 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']
    #父類方法，就是將start_urls中的列表元素進行get請求的發送
    # 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請求的手動發送使用的是FormRequest
            yield scrapy.FormRequest(url=url,callback=self.parse,formdata=data)

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

scrapy中間件設置UA及代理池

注意要在settings文件中將中間件打開

# -*- 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

#批量攔截所有的請求和響應
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',
    ]

    #攔截正常請求：request就是該方法攔截到的請求，spider就是爬蟲類實例化的一個對象
    def process_request(self, request, spider):
        print('this is process_request!!!')
        #UA偽裝
        request.headers['User-Agent'] = random.choice(self.user_agent_list)
        return None

    #攔截所有的響應
    def process_response(self, request, response, spider):

        return response

    #攔截發生異常的請求對象
    def process_exception(self, request, exception, spider):
        print('this is process_exception!!!!')
        #代理ip的設定
        if request.url.split(':')[0] == 'http':
            request.meta['proxy'] = random.choice(self.PROXY_http)
        else:
            request.meta['proxy'] = random.choice(self.PROXY_https)

        #將修正后的請求對象重新進行請求發送
        return request