百度图片下载（进程池）

百度图片获取，进程池

# coding=utf-8
import multiprocessing
from selenium import webdriver
import requests
import os
import time

def geturls(key,scrollnum):
    url = 'http://image.baidu.com/'
    browser = webdriver.Chrome()
    browser.get(url)
    browser.maximize_window()
    inputtext = browser.find_element_by_id('kw')
    inputtext.send_keys(key)
    for i in range(scrollnum):
        time.sleep(1)
        browser.execute_script("window.scrollTo(0,document.body.scrollHeight);")
    browser.implicitly_wait(10)
    elements = browser.find_elements_by_class_name('imgitem')     #关键之处1
    urls = ''
    for element in elements:
        url = element.get_attribute('data-objurl')
        urls = urls + url + ','
    browser.close()
    urls[:-1] #删除最后一个逗号
    urls = urls.split(',') #返回序列
    print(len(urls))
    #返回二维序列
    n = int(0.1 * len(urls))
    urls_lists = []
    [urls_lists.append(urls[i:i+n]) for i in range(0,len(urls),n)]
    return urls_lists

def save_img(urls):
    root = 'I:/pics/佟丽娅/'
    for url in urls:
        path = root + url.split('/')[-1] + '.jpg'
        try:
            if not os.path.exists(root):
                os.mkdir(root)
            if not os.path.exists(path):
                r = requests.get(url)
                with open(path,'wb') as f:
                    f.write(r.content)
                    f.close()
            else:
                print('图片已存在！')
        except:
            print('爬取失败')


if __name__ == '__main__':
    starttime = time.time()
    urls_lists = geturls('佟丽娅\n',2)	#输入两个参数，一个是搜索内容，一个是数量，以ajax下拉次数为单位。
    time.sleep(1)    
    pool = multiprocessing.Pool()
    pool.map(save_img,urls_lists)
    pool.close()
    pool.join()
    finishtime = time.time()
    print(finishtime - starttime)