思路：
1、圖片放在<image>XXX</image>標簽中
2、利用fiddler抓包獲取存放圖片信息的js文件url
3、利用requests庫獲取html內容，然后獲取其中圖片id
4、利用fiddler抓取下載圖片地址，結合圖片id來下載圖片（大文件）
# -*- 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=trues'#下載圖片地址，通過fiddler抓包獲取
self.target = 'https://unsplash.com/napi/photos?page=1&per_page=24'#存有圖片信息的js文件地址
self.headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36'}
"""
函數說明:獲取圖片ID
"""
def get_ids(self):
req = requests.get(url=self.target, headers=self.headers, verify=False)
html = json.loads(req.text)
print(type(html), len(html))
for i in range(len(html)):
self.photos_id.append(html[i]['id'])#將列表html中獲取id放到列表photos_id中
print(self.photos_id)
time.sleep(1)
"""
函數說明:圖片下載
"""
def download(self, photo_id, filename):
self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36'}
self.target = self.download_server.replace('xxx', photo_id)#將xxx換成圖片id
#closing可以將任意對象轉成上下文對象
with closing(requests.get(url=self.target, stream=True, verify = False, headers = self.headers)) as r:
with open('%d.jpg' % filename, 'ab+') as f:
#下載大文件，r.iter_content表示獲取響應原始內容
for chunk in r.iter_content(chunk_size = 1024):#邊下載邊存硬盤，chunk_size表示以1024比例存數據
if chunk:
f.write(chunk)
f.flush()#強行把緩沖區中的內容放到磁盤中
if __name__ == '__main__':
gp = get_photos()#類實例化
print('獲取圖片連接中:')
gp.get_ids()#獲取圖片id
print('圖片下載中:')
for i in range(len(gp.photos_id)):
print('正在下載第%d張圖片' % (i+1))
gp.download(gp.photos_id[i], (i+1))