scrapy中selenium模拟点击下一页代码

class ZufangDownloaderMiddleware(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):
        click_page_url = "http://www.XXX.com"
        print(request.url)
        initcnt = 0
        trycnt = 0

        while (initcnt < 3):
            try:
                initcnt += 1
                if click_page_url in request.url:
                    options = webdriver.FirefoxOptions()
                    options.add_argument('--headless')
                    options.add_argument('--disable-gpu')
                    driver = webdriver.Firefox(firefox_options=options)

                    while (trycnt < 3) :
                        try:
                            trycnt += 1
                            driver.get(request.url)
                            driver.implicitly_wait(5)
                            time.sleep(5)
                            print(driver.title)

                            look_more = "//a[@id='goNextPeriod']"
                            driver.find_element_by_xpath(look_more).click()
                            time.sleep(5)
                            print(driver.current_url)

                            urlchangecnt = 0
                            while (urlchangecnt < 3) :
                                urlchangecnt += 1
                                if request.url in driver.current_url:
                                    driver.find_element_by_xpath(look_more).click()
                                    time.sleep(5+urlchangecnt*2)
                                    print(driver.current_url)
                                else:
                                    break

                            true_page = driver.page_source
                            # print(true_page)

                            new_url = {'new_url': driver.current_url}
                            driver.close()

                            return HtmlResponse(request.url, body=true_page, headers=new_url, encoding='utf-8', request=request)

                        except:
                            print("get news data failed ")
                else:
                    return None
            except:
                print("webdriver init failed ")
        return None
这里是一个使用ScrapySelenium结合爬取淘宝的简单示例代码: ```python import scrapy from scrapy.selector import Selector from selenium import webdriver from scrapy.http import HtmlResponse from time import sleep class TaobaoSpider(scrapy.Spider): name = 'taobao' allowed_domains = ['taobao.com'] start_urls = ['https://www.taobao.com/'] def __init__(self, *args, **kwargs): super(TaobaoSpider, self).__init__(*args, **kwargs) self.driver = webdriver.Chrome() def parse(self, response): self.driver.get(response.url) sleep(3) selector = Selector(text=self.driver.page_source) search_input = selector.css("#q") search_input.clear() search_input.send_keys("手机") btn = self.driver.find_element_by_css_selector('#J_TSearchForm > div.search-button > button') btn.click() sleep(3) while True: selector = Selector(text=self.driver.page_source) goods = selector.css('.J_MouserOnverReq') for good in goods: title = good.css('.title a::text').extract_first() price = good.css('.price strong::text').extract_first() yield { 'title': title, 'price': price } next_page = self.driver.find_element_by_css_selector('.J_Ajax.next') if 'disabled' in next_page.get_attribute('class'): break else: next_page.click() sleep(3) self.driver.quit() ``` 首先,我们需要在`__init__`方法中初始化Selenium的驱动程序。在`parse`方法中,我们使用Selenium模拟用户在淘宝搜索框中输入"手机",然后点击搜索按钮。接下来,我们使用Scrapy的选择器从页面源代码中提取商品的标题和价格,并将其作为字典返回。最后,我们使用Selenium查找下一页按钮,如果按钮没有被禁用,则点击它并等待页面加载。重复此过程,直到找到所有的商品。 需要注意的是,使用Selenium爬取数据的效率比纯粹使用Scrapy要慢得多。因此,如果可以,最好尝试避免使用Selenium来爬取数据。
评论 4
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

灰暗角落里的琴

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值