#皮克斯圖片網站爬蟲
#css選擇器
import requests
import re
import lxml
from bs4 import BeautifulSoup
urls=['https://www.pexels.com/?page={}'.format(str(i)) for i in range(1,2)]
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
}
photos=[]
 
for url in urls:
req=requests.get(url=url,headers=headers)
text=req.text
    soup=BeautifulSoup(text,'lxml')
imgs=soup.select('body > div.l-container.home-page > div.photos > article > a.js-photo-link > img')
for img in imgs:
photo=img.get('src')
photos.append(photo)
print(photos)
path=
 
'E://photos/'
i=1
for p in photos:
data=requests.get(p,headers=headers)
fp = open(path + str(i)+'.jpg', 'wb')
fp.write(data.content)
fp.close()
i=i+1