Python爬取https://unsplash.com/的图片

Python爬虫图片爬取

跟着@Jack-Cui 学习爬虫爬取图片的时候发现之前的代码因为网站更新已经不能爬取了，就自己用Charles重新对 https://unsplash.com/ 进行了抓包。
原文地址: https://blog.youkuaiyun.com/c406495762/article/details/78123502
对抓包抓取的信息进行分析后，发现抓取的json格式的链接为：https://unsplash.com/napi/photos?page=xxx&per_page=12, xxx表示的是页数，每一页有12张图片。

下载图片的链接没有改变，还是 https://unsplash.com/photos/xxx/download?force=true, xxx表示的是图片的id。
在抓取的过程中，我没有遇到需要使用header的情况，所以就没有使用header参数。下面我贴出代码：

# -*- coding:UTF-8 -*-
import requests, json, time
from contextlib import closing

class get_photos(object):
	def __init__(self):
		self.photos_id = []
		self.download_server = 'https://unsplash.com/photos/xxx/download?force=true'
		self.target = 'https://unsplash.com/napi/photos?page=xxx&per_page=12'

	'''
	函数说明：获取图片ID
	Parameters:
		page --页数
	Returns:
		None
	'''
	def get_ids(self, page):
		target = self.target.replace('xxx', str(page))
		req = requests.get(url = target)
		html = json.loads(req.text)
		for each in html:
			self.photos_id.append(each['id'])
		time.sleep(1)
		for i in range(5):	#获取6页图片的id
			page = page + 1
			next_page = self.target.replace('xxx', str(page))
			req = requests.get(url = next_page)
			html = json.loads(req.text)
			for each in html:
				self.photos_id.append(each['id'])
			time.sleep(1)

	'''
	函数说明：图片下载
	Parameters:
		photo_id --图片id
		filename --图片存储名
	Returns:
		None
	'''
	def download(self, photo_id, filename):
		target = self.download_server.replace('xxx', photo_id)
		with closing(requests.get(url = target, stream = True)) as r:
			with open('%s.jpg' % filename, 'ab+') as f:
				for chunk in r.iter_content(chunk_size = 1024):
					if chunk:		
						f.write(chunk)
						f.flush()

if __name__ == '__main__':
	gp = get_photos()
	print('获取图片链接中：')
	gp.get_ids(1)
	print('图片下载中。。。')
	for i in range(len(gp.photos_id)):
		print('正在下载第%d张图片' % (i+1))
		gp.download(gp.photos_id[i], gp.photos_id[i])	#使用图片id作为图片的存储名