python---Scrapy实现使用Splash进行网页信息爬取

python---Scrapy实现使用Splash进行网页信息爬取 

一：回顾Scrapy的使用

 

二：爬取网址

（一）需求

最近想看漫画，奈何需要注册并支付...，想着爬取图片到本地进行浏览

（二）页面源码

我们可以知道图片网址存在一部分规则，我们可以按照这部分规则进行网站爬取。

但是我们可以知道在Img标签前面有<script>脚本信息，是用来对图片信息进行js渲染显示的，所以我们直接对该网页进行源码匹配是无法获取图片信息的。

这里我们就需要用到Splash技术

（三）Splash技术

https://www.jianshu.com/p/41e0a7e40824

三：代码实现

（一）主业务实现zymk.py

复制代码
import scrapy
from scrapy_splash import SplashRequest

from zymkPro.items import ZymkproItem


class ZymkSpider(scrapy.Spider):
    name = 'zymk'
    start_chapter = 700
    allowed_domains = []
    start_urls = ['http://www.zymk.cn/2/']

    def start_requests(self):
        for url in self.start_urls:
            yield scrapy.Request(url=url, callback=self.parse,
                                dont_filter=True)

    def parse(self,response):
        # 获取首页中所有的章节
        Cp_a = response.xpath('//ul[@id="chapterList"]/li') #解析实体
        for cp in Cp_a:
            cp_url = cp.xpath("./a/@href").extract_first()  #获取链接
            cp_title = cp.xpath("./a/text()").extract_first()   #获取文本
            try:
                if int(cp_title.split("话")[0]) < self.start_chapter:
                    continue
            except ValueError:
                print("异常番号")
                continue
            if not cp_url.startswith("http"):
                cp_url = "https://www.zymk.cn/2/%s" % cp_url

            yield SplashRequest(url=cp_url,callback=self.parseNextClsPage,　　#对于这里URL，我们是要去获取图片网址，而这里是js动态渲染的，所以需要是要Splash技术
                                args={'timeout': 3600,'wait':1})


    def parseNextClsPage(self,response):
        # 下面是所有章节去查找所有的图片
        xh_img = response.xpath('//img[@class="comicimg"]')
        xh_img_samp = xh_img.xpath("./@src").extract_first()

        ch_name = response.xpath('//div[@id="readEnd"]/div/p/strong/text()').extract_first()
        href_list = xh_img_samp.split(".jpg")
        xh_img_href_list = []

        xh_pages = response.xpath("//select[@class='selectpage']")
        xh_pagesC = xh_pages.xpath("./option[1]/text()").extract_first()

        xh_pagesCount = int(xh_pagesC.split("/")[1][:-1])
        xh_href_form = (href_list[0][:-1]).split("//")[1]

        #新操作
        xh_href_form_l = xh_href_form.split("/")
        xh_href_form_l[0] = "mhpic.xiaomingtaiji.net"
        xh_href_form = "/".join(xh_href_form_l)

        xh_href_latt = href_list[1]

        for i in range(1,xh_pagesCount+1):
            new_img_href= "http://"+xh_href_form+("%d.jpg"%i)+xh_href_latt    #获取所有图片信息
            item_obj = ZymkproItem(title=ch_name, img_url=new_img_href,img_number=i)
            yield item_obj
复制代码

（二）item.py设置字段

复制代码
# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class ZymkproItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    img_url = scrapy.Field()
    img_number = scrapy.Field()
复制代码

（三）中间件middlewares.py实现动态UA

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

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
from fake_useragent import UserAgent



class ZymkproSpiderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the spider 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_spider_input(self, response, spider):
        # Called for each response that goes through the spider
        # middleware and into the spider.

        # Should return None or raise an exception.
        return None

    def process_spider_output(self, response, result, spider):
        # Called with the results returned from the Spider, after
        # it has processed the response.

        # Must return an iterable of Request, or item objects.
        for i in result:
            yield i

    def process_spider_exception(self, response, exception, spider):
        # Called when a spider or process_spider_input() method
        # (from other spider middleware) raises an exception.

        # Should return either None or an iterable of Request or item objects.
        pass

    def process_start_requests(self, start_requests, spider):
        # Called with the start requests of the spider, and works
        # similarly to the process_spider_output() method, except
        # that it doesn’t have a response associated.

        # Must return only requests (not items).
        for r in start_requests:
            yield r

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)


class ZymkproDownloaderMiddleware:
    # 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):
        # 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

    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)


class MyUseragent(object):
    def __init__(self):
        self.ua = UserAgent()

    def process_request(self,request,spider):
        referer=request.url
        if referer:
            request.headers["referer"] = referer
        request.headers.setdefault("User-Agent", self.ua.random)
复制代码

（四）持久化操作pipelines.py

复制代码
# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import requests,os
from fake_useragent import UserAgent

class ZymkproPipeline:
    def process_item(self, item, spider):
        file_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'upload', item['title'])
        ua = UserAgent().random

        if not os.path.isdir(file_path):
            os.makedirs(file_path)

        header = {
            'User-Agent': ua,
            'Referer': item['img_url']
        }

        response = requests.get(item['img_url'], stream=False,headers=header)
        with open(os.path.join(file_path,"%d.jpg"%item['img_number']), "wb") as fp:
            fp.write(response.content)

        return item
复制代码

（五）配置文件setting.py

View Code

四：结果显示

 

posted @ 2022-01-10 10:47  小学弟-  阅读(235)  评论(0)  编辑  收藏  举报