下面程序能夠爬取百度圖片一個(gè)網(wǎng)頁里面的所以圖片，值得關(guān)注的是匹配字段，正則表達(dá)式要寫正確，雖然匹配成功的但是爬取的圖片還是較少，下篇我會(huì)采取get方法來請(qǐng)求更多圖片來爬取。

            
              import urllib.request
import re
import time

def open_url(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36 QIHU 360EE')
    page = urllib.request.urlopen(req)#打開網(wǎng)頁
    html = page.read().decode('utf-8')#網(wǎng)頁解碼
    return html

def get_img(html):
    p = r'"(https:[^"]+\.jpg)'#匹配的字段
    imglist = re.findall(p,html)
    #print(html)
    for each in imglist:
        print(each)
        filename = each.split("/")[-1]
        urllib.request.urlretrieve(each,filename,None)#保存圖片
        #time.sleep(0.01)


if __name__ == '__main__':
	#網(wǎng)址
    url = 'https://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=result&fr=&sf=1&fmq=1559194736650_R&pv=&ic=&nc=1&z=&hd=&latest=&copyright=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&sid=&word=%E5%8A%A8%E6%BC%AB%E5%B0%91%E5%A5%B3'
    get_img(open_url(url))