selenium+chrome瀏覽器驅動-爬取百度圖片

百度圖片網頁中中，當頁面滾動到底部，頁面會加載新的內容。

我們通過selenium和谷歌瀏覽器驅動，執行js，是瀏覽器不斷加載頁面，通過抓取頁面的圖片路徑來下載圖片。

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
'''
爬取百度圖片，頁面向下拉到底，會加載新的網頁數據。

'''

# 構建請求頭
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"
}
# 創建瀏覽器對象
browser = webdriver.Chrome(executable_path=r'E:\PycharmProjects\pachong\chromedriver.exe')
# 設置加載超時時間
wait = WebDriverWait(browser,20)
# 發送請求
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')

# 設置圖片下載路徑
path = './baidupic/'
if not os.path.exists(path):
    os.makedirs(path)

while True:
    # 直到網頁中的圖片最后一個div加載成功。(每次加載新數據都是則將一個imgpaged的div)
    wait.until(EC.presence_of_all_elements_located((By.XPATH,'//div[@id="imgid"]/div[last()]')))
    # 獲取網頁源
    html = browser.page_source
    html = etree.HTML(html)
    # 獲取圖片的url
    # img_urls = html.xpath('//div[@id="imgid"]/div[last()]//li/@data-objurl') #大圖
    img_urls = html.xpath('//div[@id="imgid"]/div[last()]//img/@data-imgurl') #小圖
    # print(img_url)
    for img_url in img_urls:
        #獲取圖片名字.(直接按原名字存儲，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,'下載失敗')

        # 防止請求過快,這里是單線程下載圖片本身需要一定時間，先注釋掉
        # time.sleep(2+ random.random()*1)

    # 將頁面滾動底，加載新數據(執行js)
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    # 頁面加載需要時間
    time.sleep(5+ random.random()*1)

    # break

請求頭headers中的內容源於瀏覽器的審查。刪除了Host內容，百度的有些大圖來源於其他網站，如果設置Host,一些大圖可能不能下載。

在網頁源碼中發現，圖片有大圖，有小圖，路徑不同。