selenium+chrome浏览器驱动-爬取百度图片

Posted 2020-11-20 doitjust

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。

 1 from selenium import webdriver
 2 from selenium.webdriver.common.by import By
 3 from selenium.webdriver.support import expected_conditions as EC
 4 from selenium.webdriver.support.ui import WebDriverWait
 5 import requests
 6 from lxml import etree
 7 import time
 8 import random
 9 import os
10 ‘‘‘
11 爬取百度图片，页面向下拉到底，会加载新的网页数据。
12 
13 ‘‘‘
14 
15 # 构建请求头
16 headers = {
17 "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
18 "Accept-Encoding":"gzip, deflate, br",
19 "Accept-Language":"zh-CN,zh;q=0.9",
20 "Cache-Control":"max-age=0",
21 "Connection":"keep-alive",
22 "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",
23 
24 "Referer":"http://image.baidu.com/",
25 "Upgrade-Insecure-Requests":"1",
26 "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"
27 }
28 # 创建浏览器对象
29 browser = webdriver.Chrome(executable_path=r‘E:PycharmProjectspachongchromedriver.exe‘)
30 # 设置加载超时时间
31 wait = WebDriverWait(browser,20)
32 # 发送请求
33 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‘)
34 
35 # 设置图片下载路径
36 path = ‘./baidupic/‘
37 if not os.path.exists(path):
38     os.makedirs(path)
39 
40 while True:
41     # 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)
42     wait.until(EC.presence_of_all_elements_located((By.XPATH,‘//div[@id="imgid"]/div[last()]‘)))
43     # 获取网页源
44     html = browser.page_source
45     html = etree.HTML(html)
46     # 获取图片的url
47     # img_urls = html.xpath(‘//div[@id="imgid"]/div[last()]//li/@data-objurl‘) #大图
48     img_urls = html.xpath(‘//div[@id="imgid"]/div[last()]//img/@data-imgurl‘) #小图
49     # print(img_url)
50     for img_url in img_urls:
51         #获取图片名字.(直接按原名字存储，防止重名)
52         fname = img_url.split(‘/‘)[-1]
53         try:
54             response = requests.get(img_url,headers=headers)
55             data = response.content
56             with open(‘./baidupic/‘+fname,mode=‘wb‘) as f:
57                 f.write(data)
58         except:
59             print(img_url,‘下载失败‘)
60 
61         # 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
62         # time.sleep(2+ random.random()*1)
63 
64     # 将页面滚动底，加载新数据(执行js)
65     browser.execute_script(‘window.scrollTo(0,document.body.scrollHeight)‘)
66     # 页面加载需要时间
67     time.sleep(5+ random.random()*1)
68 
69     # 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。