python爬取pexels网站图片

#coding:utf-8

from lxml import etree
import requests
import urllib.request  
import progressbar  



header={
	'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'+
	'Chrome/67.0.3396.87 Safari/537.36'
}

word=input('请输入搜索的内容:')

urls=['https://www.pexels.com/search/'+word+'/?page={}'.format(str(i))
		for i in range(11,12)]
path='E://G/'

for url in urls :
	res=requests.get(url)
	selector=etree.HTML(res.text)
	second_urls=selector.xpath('//div[@class="photos"]/article')
	print(len(second_urls))
	for second_url in second_urls:
		new_url=second_url.xpath('a[1]/@href')[0]
		new_url='https://www.pexels.com'+str(new_url)
		#print(new_url)
		new_res=requests.get(new_url)
		new_selector=etree.HTML(new_res.text)
		new_second_urls=new_selector.xpath('//a[@class="btn__primary js-download"]')
		img_src = new_second_urls[0].xpath('@href')[0]
		img_src=img_src.split('?')[0]
		data=requests.get(img_src,headers=header)
		total_length = int(data.headers.get("Content-Length"))
		with open(path+img_src.split('/')[-1], 'wb') as f:
			widgets = ['Progress: ', progressbar.Percentage(), ' ',progressbar.Bar(marker='#', left='[', right=']'),' ', progressbar.ETA(), ' ', progressbar.FileTransferSpeed()]
			pbar = progressbar.ProgressBar(widgets=widgets, maxval=total_length).start()
			count=0
			for chunk in data.iter_content(chunk_size=1):
				if chunk:
					count=count+1
					f.write(chunk)
					f.flush()
				pbar.update(count)
			pbar.finish()
	

这里首先输入搜索关键字，输出每页图片张数，打印下载进度条