scarpy_流程

scrapy 中间键

review

1.
    pip install wheel
    pip install twisted
    pip install pywin32
    pip install scrapy

2.
    scrapy startproject ProName
    cd ProName
    scrapy genspider projectName www.xxx.com


3.
   目录结构:
   spider: 放置一个爬虫文件
   item:
        xxx = Filed()

   pipeline:
        - process_item():
        - open_spider():
        - close_spider():

    setting: 配置文件

4.爬虫文件
    - name:
    - start_urls:
    - parse(self,response):
    - xpath():列表元素Selector对象.extract()
    - 持久化存储:
        -终端指令: 只可将parse方法的返回值进行本地文件的持久化存储
            - scrapy crawl xxx -o ./xxx.csv

        - 管道:
            1. 数据解析
            2. 将解析到的数据封装到item类型的对象
            3. 通过yield向管道提交item对象
            4. 在管道的process_item 方法中执行io操作,进行持久化配置
            5. 在配置文件中开启管道
            注意: process_item 方法中返回值的作业:
        - 手动请求的发送:
            - yield scrapy.Request(url,callback)

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

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


class MiddleproSpiderMiddleware(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 MiddleproDownloaderMiddleware(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.

    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"
    ]

    # 可选备用的代理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',
    ]

    @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

    # 拦截所有未发生异常的请求
    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

        # 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('User_Agent', request.headers['User_Agent'])

        # #使用代理池进行请求代理ip的设置
        # if request.url.split(':')[0] == 'http':
        #     request.meta['proxy'] = random.choice(self.PROXY_http)
        # else:
        #     request.meta['proxy'] = random.choice(self.PROXY_https)
        return None

    # 拦截所有的响应
    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

    #   拦截到产生异常的请求
    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

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

        else:
            request.meta['proxy'] = random.choice(self.PROXY_https)



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

爬取电影网

https://www.4567tv.tv/frim/index1.html

movie_pro.py

# -*- coding: utf-8 -*-
import scrapy
from movie.items import MovieItem


class MoveProSpider(scrapy.Spider):
    name = 'movie_pro'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.4567tv.tv/frim/index1.html']

    # 解析详情页面的数据
    def parse_detail(self, response):
        # response,meta 返回接受到的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 = MovieItem()
            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})

网易

# -*- 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
from scrapy.http import HtmlResponse
from time import sleep

class WangyiproSpiderMiddleware(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 WangyiproDownloaderMiddleware(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
        # 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)
    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)

wangyi.py

# -*- coding: utf-8 -*-
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.在下载中间键得process_response方法中,通过spider参数获取浏览器对象
    4.在中间键得process_response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.example.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()