Scrapy+Splash爬取动态加载js的网页数据

HTML渲染分为两类。动态加载和静态加载。静态加载就是整个HTML文档都是有服务器渲染之后，发送给客户端进行展示。但是随着技术拓展，越来越多的网页上的有效数据是通过js动态加载出来的，如果我们还是用传统的方式爬取，那么结果可想而知。今天介绍Scrapy+Splash模拟浏览器行为，动态加载js之后，获取有效数据。

1、安装Scrapy

C:\Users\Administrator>pip install scrapy

#成功标志
Successfully installed Scrapy-1.5.1

2、创建Scrapy项目

C:\Users\Administrator>scrapy startproject ZhipinSpider

#成功标志，在Administrator文件夹下生成一个ZhipinSpider文件夹，结构如下：
ZhipinSpider
    scrapy.cfg
    ZhipinSpider
        __init__.py
        items.py
        middlewares.py
        pipelines.py
        settings.py
        spiders
            __init__.py
            job_position.py
       

 

3、编写类

3.1、job_position.py

# 导入访问MySQL的模块
import mysql.connector


class ZhipinspiderPipeline(object):
    # 定义构造器，初始化要写入的文件
    def __init__(self):
        self.conn = mysql.connector.connect(user='root',
                                            password='root',
                                            host='192.168.36.58', port='3306',
                                            database='directrecruit',
                                            use_unicode=True)
        self.cur = self.conn.cursor()

    # 重写close_spider回调方法，用于关闭数据库资源
    def close_spider(self, spider):
        print('----------关闭数据库资源-----------')
        # 关闭游标
        self.cur.close()
        # 关闭连接
        self.conn.close()

    def process_item(self, item, spider):
        self.cur.execute("INSERT INTO job_inf VALUES(null, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
                         (item['title'], item['salary'], item['company'], item['url'], item['work_addr'], item['industry'], item.get('company_size'), item['recruiter'], item['publish_date']))
        self.conn.commit()

3.2、items.py

import scrapy


class ZhipinspiderItem(scrapy.Item):
    # 工作名称
    title = scrapy.Field()
    # 工资
    salary = scrapy.Field()
    # 招聘公司
    company = scrapy.Field()
    # 工作详细链接
    url = scrapy.Field()
    # 工作地点
    work_addr = scrapy.Field()
    # 行业
    industry = scrapy.Field() 
    # 公司规模
    company_size = scrapy.Field() 
    # 招聘人
    recruiter = scrapy.Field() 
    # 发布时间
    publish_date = scrapy.Field() 

 

3.3、middlewares.py

# -*- 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


class ZhipinspiderSpiderMiddleware(object):
    # 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, dict 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 Response, dict
        # 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 ZhipinspiderDownloaderMiddleware(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):
        # 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)

3.4、pipelines.py

# 导入访问MySQL的模块
import mysql.connector


class ZhipinspiderPipeline(object):
    # 定义构造器，初始化要写入的文件
    def __init__(self):
        self.conn = mysql.connector.connect(user='root',
                                            password='root',
                                            host='192.168.36.58', port='3306',
                                            database='directrecruit',
                                            use_unicode=True)
        self.cur = self.conn.cursor()

    # 重写close_spider回调方法，用于关闭数据库资源
    def close_spider(self, spider):
        print('----------关闭数据库资源-----------')
        # 关闭游标
        self.cur.close()
        # 关闭连接
        self.conn.close()

    def process_item(self, item, spider):
        self.cur.execute("INSERT INTO job_inf VALUES(null, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
                         (item['title'], item['salary'], item['company'], item['url'], item['work_addr'], item['industry'], item.get('company_size'), item['recruiter'], item['publish_date']))
        self.conn.commit()

 

3.5、settings.py

BOT_NAME = 'ZhipinSpider'

SPIDER_MODULES = ['ZhipinSpider.spiders']
NEWSPIDER_MODULE = 'ZhipinSpider.spiders'

ROBOTSTXT_OBEY = True

# 配置默认的请求头
DEFAULT_REQUEST_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36",
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3'
}

# 配置使用Pipeline
ITEM_PIPELINES = {
    'ZhipinSpider.pipelines.ZhipinspiderPipeline': 300,
}

此处遵守采集协议，采集boss直聘上的招聘信息。只能采集静态页面。

3、安装Splash服务

先安装docker服务，如何安装docker服务，前面博客有详细步骤。

[root@Docker ~]# docker run -p 8050:8050 scrapinghub/splash
Unable to find image 'scrapinghub/splash:latest' locally
latest: Pulling from scrapinghub/splash
7b722c1070cd: Pull complete 
5fbf74db61f1: Pull complete 
ed41cb72e5c9: Pull complete 
7ea47a67709e: Pull complete 
b9ea67282e79: Pull complete 
8d0589f2b410: Pull complete 
11f417145dc7: Pull complete 
14d670a8125e: Pull complete 
81d8bf1e3bdc: Pull complete 
Digest: sha256:ec1198946284ccadf6749ad60b58b2d2fd5574376857255342a913ec7c66cfc5
Status: Downloaded newer image for scrapinghub/splash:latest
2019-07-19 03:15:03+0000 [-] Log opened.
2019-07-19 03:15:03.976877 [-] Splash version: 3.3.1
2019-07-19 03:15:03.978587 [-] Qt 5.9.1, PyQt 5.9.2, WebKit 602.1, sip 4.19.4, Twisted 18.9.0, Lua 5.2
2019-07-19 03:15:03.978696 [-] Python 3.5.2 (default, Nov 12 2018, 13:43:14) [GCC 5.4.0 20160609]
2019-07-19 03:15:03.978763 [-] Open files limit: 1048576
2019-07-19 03:15:03.978805 [-] Can't bump open files limit
2019-07-19 03:15:04.090084 [-] Xvfb is started: ['Xvfb', ':485890213', '-screen', '0', '1024x768x24', '-nolisten', 'tcp']
QStandardPaths: XDG_RUNTIME_DIR not set, defaulting to '/tmp/runtime-root'
2019-07-19 03:15:04.300570 [-] proxy profiles support is enabled, proxy profiles path: /etc/splash/proxy-profiles
2019-07-19 03:15:04.300725 [-] memory cache: enabled, private mode: enabled, js cross-domain access: disabled
2019-07-19 03:15:04.473283 [-] verbosity=1, slots=20, argument_cache_max_entries=500, max-timeout=90.0
2019-07-19 03:15:04.474206 [-] Web UI: enabled, Lua: enabled (sandbox: enabled)
2019-07-19 03:15:04.475292 [-] Site starting on 8050
2019-07-19 03:15:04.475377 [-] Starting factory 
2019-07-19 03:15:04.475596 [-] Server listening on http://0.0.0.0:8050

4、在Scrapy中使用Splash服务

4.1、安装scrapy-splash

C:\Users\Administrator>pip install scrapy-splash
Collecting scrapy-splash
  Downloading https://files.pythonhosted.org/packages/64/19/aa6e9559ca16a4daec98f6451748dd1cae9a91e7f43069cc1d294f7576bc/scrapy_splash-0.7.2-py2.py3-none-any.whl
Installing collected packages: scrapy-splash
Successfully installed scrapy-splash-0.7.2

4.2、修改代码

settings.py

# Splash服务器地址
SPLASH_URL = 'http://192.168.244.133:8050'

# 开启两个下载中间件，并调整HttpCompressionMiddlewares的次序
DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}

# 设置去重过滤器
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

# 用来支持cache_args（可选）
SPIDER_MIDDLEWARES = {
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
}

DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'