通过selenium框架爬取图片

通过selenium框架爬取图片

环境搭建

搭建python环境就不在此展开了， 首先安装selenium框架:

pip install selenium

下载浏览器驱动， 此处仅仅以Chrome浏览器为例子， 驱动版本必须与当前系统安装的Chrome对应。

chromedriver下载，如果找不到对应版本， 是因为版本太新， 需要到此链接找到对应版本。

版本对应关系在链接中存在说明:

基本过程

首先将下载的chromedriver放置到环境变量：

current_script_path = os.path.abspath(os.path.dirname(__file__))
original_path = os.environ.get("PATH")
os.environ["PATH"] = original_path +";" + os.path.join(current_script_path,"chromedriver-win64","chromedriver.exe")

接下来启动浏览器驱动:

from selenium import webdriver

driver = webdriver.Chrome() 

# ....

driver.get(search_link)

查找指定元素

如果要找到指定元素, 可通过xpath:

from selenium.webdriver.common.by import By
first_link = driver.find_element(By.XPATH, '//ul[@class="dgControl_list "][1]//li[1]//a[1]')

点击指定元素

如果要点击指定元素:

first_link = driver.find_element(By.XPATH, '//ul[@class="dgControl_list "][1]//li[1]//a[1]')
first_link.click()

等待元素出现

如果要等待某元素出现:

from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

wait = WebDriverWait(driver, 10)

image = wait.until(EC.presence_of_element_located((By.XPATH, '//div[@id="mainImageWindow"]//img')))

获取元素属性

image = driver.find_element(By.XPATH, '//div[@id="mainImageWindow"]//img')
src = image.get_attribute("src")

关闭驱动

driver.close()

完整示例

该示例展示了如何从bing爬取指定关键字的图片:

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

def get_image_url_from_keyword(keyword, num_of_image):
    search_link = f"https://cn.bing.com/images/search?q={keyword}"
    driver = webdriver.Chrome() 
    wait = WebDriverWait(driver, 10)
    current_image_amount = 0
    urls = []
    try:
        driver.get(search_link)
        first_link = driver.find_element(By.XPATH, '//ul[@class="dgControl_list "][1]//li[1]//a[1]')
        # root = etree.HTML(driver.page_source)
        # first_link = root.xpath('//ul[@class="dgControl_list "][1]//li[1]//a[1]')
        first_link.click()
        while True:
            driver.refresh()
            image = wait.until(EC.presence_of_element_located((By.XPATH, '//div[@id="mainImageWindow"]//img')))
            src = image.get_attribute("src")
            urls.append(src)
            current_image_amount+=1
            if current_image_amount >= num_of_image:
                break
            next = wait.until(EC.presence_of_element_located((By.XPATH, '//div[@id="mainImageContainer"]/div[@id="navr"]')))
            next.click()
            driver.implicitly_wait(0.5)
            sys.stdout.write('\rprogress: {}/{}'.format(current_image_amount, num_of_image))
            sys.stdout.flush()
    except Exception as e:
        print(e)
   
    driver.close()
    return set(urls)


if __name__ == "__main__":
    
    key_words = ["美女", "帅哥"]
    for key in key_words:
        # 最多爬取500张截止
        urls = list(get_image_url_from_keyword(key, 500))
     

原文链接