selenium+chrome浏览器驱动-爬取百度图片

百度图片网页中中，当页面滚动到底部，页面会加载新的内容。

我们通过selenium和谷歌浏览器驱动，执行js，是浏览器不断加载页面，通过抓取页面的图片路径来下载图片。

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
import requests
from lxml import etree
import time
import random
import os
'''
爬取百度图片，页面向下拉到底，会加载新的网页数据。

'''

# 构建请求头
headers = {
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
"Accept-Encoding":"gzip, deflate, br",
"Accept-Language":"zh-CN,zh;q=0.9",
"Cache-Control":"max-age=0",
"Connection":"keep-alive",
"Cookie":"winWH=%5E6_1197x581; BDIMGISLOGIN=0; BDqhfp=%E5%9B%BE%E7%89%87%26%260-10-1undefined%26%260%26%261; BIDUPSID=24942ACBA645FE0108AF48B5C2509013; BAIDUID=C05587CE8C62CAB17300AA09BC6820BD:FG=1; PSTM=1528274179; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; H_PS_PSSID=1440_25810_26459_21103_18559_20928; BDUSS=VNneDRnWTQ3fnVQOWJpTG95Z1RZVnllVzlRSURpWnBMWHlwbGZha2lGZWl3VlpiQUFBQUFBJCQAAAAAAAAAAAEAAAB9W1Rr1MbFzNGnzt7Wub6zAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKI0L1uiNC9bW; PSINO=3; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; cflag=15%3A3; BDRCVFR[dG2JNJb_ajR]=mk3SLVN4HKm; BDRCVFR[X_XKQks0S63]=mk3SLVN4HKm; firstShowTip=1; indexPageSugList=%5B%22%E5%9B%BE%E7%89%87%22%5D; cleanHistoryStatus=0",

"Referer":"http://image.baidu.com/",
"Upgrade-Insecure-Requests":"1",
"User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36"
}
# 创建浏览器对象
browser = webdriver.Chrome(executable_path=r'E:PycharmProjectspachongchromedriver.exe')
# 设置加载超时时间
wait = WebDriverWait(browser,20)
# 发送请求
browser.get('https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&hs=0&xthttps=111111&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=%E5%9B%BE%E7%89%87&oq=%E5%9B%BE%E7%89%87&rsp=-1')

# 设置图片下载路径
path = './baidupic/'
if not os.path.exists(path):
    os.makedirs(path)

while True:
    # 直到网页中的图片最后一个div加载成功。(每次加载新数据都是则将一个imgpaged的div)
    wait.until(EC.presence_of_all_elements_located((By.XPATH,'//div[@id="imgid"]/div[last()]')))
    # 获取网页源
    html = browser.page_source
    html = etree.HTML(html)
    # 获取图片的url
    # img_urls = html.xpath('//div[@id="imgid"]/div[last()]//li/@data-objurl') #大图
    img_urls = html.xpath('//div[@id="imgid"]/div[last()]//img/@data-imgurl') #小图
    # print(img_url)
    for img_url in img_urls:
        #获取图片名字.(直接按原名字存储，防止重名)
        fname = img_url.split('/')[-1]
        try:
            response = requests.get(img_url,headers=headers)
            data = response.content
            with open('./baidupic/'+fname,mode='wb') as f:
                f.write(data)
        except:
            print(img_url,'下载失败')

        # 防止请求过快,这里是单线程下载图片本身需要一定时间，先注释掉
        # time.sleep(2+ random.random()*1)

    # 将页面滚动底，加载新数据(执行js)
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    # 页面加载需要时间
    time.sleep(5+ random.random()*1)

    # break

请求头headers中的内容源于浏览器的审查。删除了Host内容，百度的有些大图来源于其他网站，如果设置Host,一些大图可能不能下载。

在网页源码中发现，图片有大图，有小图，路径不同。