Scrapy中selenium的使用

场景1：项目中有多个爬虫时，将driver对象的初始化放在各个spider中

#!/usr/bin/env python
# -*- coding: UTF-8 -*-
'''
@author: carry
@time: 2019/6/19 15:56
@desc:
'''
import scrapy
from selenium import webdriver
from scrapy import signals
from scrapy.xlib.pydispatch import dispatcher
from scrapy.http import HtmlResponse
from selenium.webdriver.chrome.options import Options


class ZhihuSpider(scrapy.Spider):
    '''
    项目中有多个爬虫时，将driver对象的初始化放在各个spider中
    '''
    name = 'zhihu'
    allowed_domains = ['oschina.net/blog']
    start_urls = ['https://www.oschina.net/blog']

    def __init__(self):
        # 初始化chrome对象
        chrome_options = Options()
        chrome_options.add_argument('--headless')
        self.browser = webdriver.Chrome('D:\chromedriver_win32\chromedriver.exe', chrome_options=chrome_options)
        super(ZhihuSpider, self).__init__()

        # 当爬虫关闭时scrapy会发出一个spider_closed的信息,当这个信号发出时就调用closeSpider函数关闭这个浏览器.
        dispatcher.connect(receiver=self.closeSpider, signal=signals.spider_closed)

    def closeSpider(self, spider):
        print("spider closed")
        self.browser.quit()

    def parse(self, response):
        pass


class SeleniumMiddleware(object):
    '''
    Middleware中的类设置
    '''
    def process_request(self, request, spider):
        if spider.name == "zhihu":
            spider.browser.get(request.url)
            return HtmlResponse(url=spider.browser.current_url, body=spider.browser.page_source, encoding="utf-8",
                                request=request)

 

场景2：当需要用selenium进行 键入搜索，而此时得到的是list，需循环点击获取详情页

def use_selenium_step01(self, request, spider):
    '''
    键入搜索逻辑，返回搜索结果页面到
    '''
    driver = spider.browser
    driver.get(request.url)
    try:
        input = spider.browser.find_element_by_xpath('//textarea')
        input.send_keys(request.meta['keyword'])
        btn_submit = spider.browser.find_element_by_xpath(
            '//span[contains(text(),"Find")]/..')
        btn_submit.click()
        WebDriverWait(spider.browser, 5, 0.5).until(
            EC.presence_of_element_located(
                (By.XPATH, '//div[@class="ui-datatable-tablewrapper"]/table/tbody')))
    except Exception as e:
        print(e)
        return

def use_selenium_setp02(self, request, spider):
    '''
    此为点击list页面每个详情链接的处理逻辑
    在parser_01中得到1获取每个链接的唯一Xpath定位标识
    '''
    driver = spider.browser
    driver.get(request.url)
    try:
        # 重复键入搜索逻辑
        input = spider.browser.find_element_by_xpath('//textarea')
        input.send_keys(request.meta['keyword'])
        btn_submit = spider.browser.find_element_by_xpath(
            '//span[contains(text(),"Find")]/..')
        btn_submit.click()
        WebDriverWait(spider.browser, 5, 0.5).until(
            EC.presence_of_element_located(
                (By.XPATH, '//div[@class="ui-datatable-tablewrapper"]/table/tbody')))
       
        #接着点击所要获取的每个链接
        btn_submit = driver.find_element_by_xpath(
            '//div[@class="ui-datatable-tablewrapper"]/table/tbody/tr[{}]//a'.format(request.meta['i']))
        btn_submit.click()
        WebDriverWait(spider.browser, 5, 0.5).until(
            EC.presence_of_element_located(
                (By.XPATH, '//span[contains(text(),"Back")]')))
    except Exception as e:
        print(e)
        return

 

 

----------------------------------------------------我是分割线--------------------------------------------------------------------------------------------

欢迎关注博主个人公众号，一起来嗨皮呀