Python爬虫爬取必应图片的一个环节,使用xpath获取下载图片的URL时,获取内容为空,检查过xpath语法正确,坐等解决方法
import requests
from lxml import etree
url = 'https://cn.bing.com/images/search?view=detailV2&ccid=lH2TkHTF&id=65167C9E54BD6A516682173F7A4747E63FA4D77E&thid' \
'=OIP.lH2TkHTFHjovR0wqZFDVoAHaEK&mediaurl=https%3a%2f%2fts1.cn.mm.bing.net%2fth%2fid%2fR-C' \
'.947d939074c51e3a2f474c2a6450d5a0%3frik%3dftekP%252bZHR3o%252fFw%26riu%3dhttp%253a%252f%252fimg3.donews.com' \
'%252fuploads%252fimg3%252fimg_pic_1530694840_0%26ehk%3dTqmFU1WejMz%252frQawSVbV7db9KDdl%252fUw5L2HWmPQHqPQ' \
'%253d%26risl%3d%26pid%3dImgRaw%26r%3d0&exph=1080&expw=1920&q=%e6%95%85%e5%ae%ab&simid=608051165034519383&FORM' \
'=IRPRST&ck=06B53B135EB364C0A5765DF5E81F6BF7&selectedIndex=33&qft=+filterui%3aimagesize-custom_1920_1080&vt=0' \
'&sim=11 '
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.188 '
}
res = requests.get(url=url, headers=headers)
page = res.text
ele = etree.HTML(page)
new_url = ele.xpath('//div[@class="imgContainer"]/img/@src')
print(new_url)