selenium中webdriver打开新页面无法获取页面元素

谁践踏了优雅 2022-06-11 06:43 490阅读 0赞

# 当我们使用selenium 抓取数据时候 #

--------------------

### 首先我们要明白问题出在哪里？ ###

在新打开页面，我们无法获取元素，是因为 **句柄** 不在当前打开页面，我们需要做的是将 **句柄** 移动到当前页面就ok 了

--------------------

![这里写图片描述][SouthEast]

![这里写图片描述][SouthEast 1]

## 我们以智联招聘为例：直接上代码 ##

# -*- coding: utf-8 -*-
    import scrapy
    import time
    from selenium import webdriver
    
    from tutorial.items import TutorialItem
    
    
    class jobboleSpider(scrapy.Spider):
        #先进行登录
        global driver
    
        name = 'tutorial'
        allowed_domains = ["tutorial.org"]
        start_urls = ['https://passport.zhaopin.com/org/login?DYWE=1500951340319.109686.1500951340.1500951340.1&y7bRbP=dponrhKTzMKTzMKTuTndxC6SfMXcLLK6ijFVr6jEz.V']
        driver = webdriver.Firefox()
        driver.get(start_urls[0])
        time.sleep(10)
        uname = ''
        password = ''
        driver.find_element_by_xpath(".//*[@id='LoginName']").send_keys(uname)  # 你的用户名
        driver.find_element_by_xpath(".//*[@id='Password']").send_keys(password)
        time.sleep(5)
        driver.find_element_by_xpath(".//*[@id='loginbutton']").click()
        time.sleep(5)
        driver.get("https://rdsearch.zhaopin.com/Home/SearchByCustom?source=rd")
        driver.find_element_by_xpath(".//*[@id='SF_1_1_1']").send_keys("java")  # 搜索职位
        driver.find_element_by_xpath(".//*[@id='searchSubmit']/button").click()
        time.sleep(10)
    
        # 当前信息有多少页
        global start_page  # 起始页
        global page_count  # 总页数
    
    
        page_index = str(driver.find_element_by_xpath(".//*[@id='rd-resumelist-pageNum']").text)
        nowPag,pageCount = page_index.split("/")
        page_count = int(pageCount)
        print("总页数是=====================")
        print(page_count)
        #tex = 1
    
        x=1
        def parse(self, response,num=x,start_page=x):
            #start_page = 1
            j = 1
            for i in range(1, 31):
    
                title="html/body/div[6]/div[5]/form/table/tbody/tr["+str(j)+"]/td[2]/a"
                driver.find_element_by_xpath(title).click()
                time.sleep(3)
                # 移动句柄为当前页面
                all=driver.window_handles #显示当前页面一共有多少个句柄，结果是一个列['' ,'']
                z=driver.current_window_handle #当前页面的句柄
    
                driver.switch_to_window(driver.window_handles[1])#移动句柄
                time.sleep(2)
                ##具体爬取数据的方法
                self.auto_info(response,num)
    
                #关闭当前句柄
                driver.close()
                #移动句柄
                driver.switch_to_window(driver.window_handles[0])
                j = j + 2
                num +=1
                print("-----------------------")
                print(num)
    
                #driver.current_window_handle
                #return item
            #翻页
            if (start_page <= page_count):
               time.sleep(1)
               driver.find_element_by_xpath("html/body/div[6]/div[5]/div/div[3]/a[3]").click()
               time.sleep(2)
               start_page +=1
               print("翻页============================================")
    
               # num1 =num
               print(start_page)
               print(num)
    
               self.parse(response,num=num,start_page=start_page)
            else:
                print("-------数据爬取结束---------")
    
    
        def auto_info(self,response,num):
                print("简历内容---------------------------------")
                path = "D:/test2/java/"
                path += str(num)
                path +=".txt"
                print(path)
                f = open(path, 'a')
                for tag in driver.find_elements_by_xpath(".//*[@id='resumeContentBody']/div"):
                    try:
                     f.write(tag.text)
                     f.write("\n")
                    except:
                        continue
                f.close()

## 如需源码：可以留下邮箱–看到后会发送你邮箱里 ##

[SouthEast]: /images/20220611/2d0a22ae3c7045c0b39123baa03341f9.png
[SouthEast 1]: /images/20220611/cbd903766d664f0fbafddb3d407f7b92.png