import requests
from lxml import etree
import re
import os
#原网址:https://www.pexels.com/zh-tw/
#F12之后选择XHR,然后不断往下滑,可以看到出现了更多的URL,如下
# url='https://www.pexels.com/zh-tw/?format=js&seed=2019-04-02%2B11%3A58%3A30%2B%2B0000&dark=true&page=3&type='
#可以进行简化,提取有用的部分,结果为
url=['https://www.pexels.com/zh-tw/?page={}'.format(i) for i in range(3,6)]
for i in range(len(url)):
response=requests.get(url[i])
html=etree.HTML(response.text)
url_image=html.xpath('//div[@class="photos__column"]/div/article/a[1]/img/@data-pin-media')
url_name=html.xpath('//div[@class="photos__column"]/div/article/a[1]/@href') #获得特有的id值
url_num=" ".join(url_name) #列表转为字符串
url_num=(re.compile('\d+').findall(url_num)) #使用正则表达式后返回列表
#建立文件夹
dir_path='D:/picture/ajax/{}page'.format(i)
if os.path.exists(dir_path)==0:
os.mkdir(dir_path)
for j,k in zip(url_image,url_num):
# 获得图片内容
res = requests.get(j)
with open(dir_path+'/{}.jpg'.format(k),'wb')as f:
f.write(res.content)
print(i)