Python爬虫下载图片

import requests
import os
from bs4 import BeautifulSoup
class Picture():
def __init__(self):
# 给请求指定一个请求头来模拟chrome浏览器
self.headers &＃61; {
&＃39;User-Agent&＃39;: &＃39;Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36&＃39;}
self.web_url &＃61; &＃39;https://unsplash.com/&＃39;
self.base_path &＃61; os.path.dirname(__file__)
def makedir(self, name):
path &＃61; os.path.join(self.base_path, name)
isExist &＃61; os.path.exists(path)
if not isExist:
os.makedirs(path)
print(&＃39;File has been created.&＃39;)
else:
print(&＃39;The file is existed.&＃39;)
#切换到该目录下
os.chdir(path)
def request(self, url):
r &＃61; requests.get(url, headers&＃61;self.headers)
return r
def get_img(self):
r &＃61; self.request(self.web_url)
# r.text是返回的网页HTML;这里的find_all(&＃39;a&＃39;, class_&＃61;&＃39;cV68d&＃39;) 是找到所有class为cV68d的a标签&＃xff0c;返回的是一个list&＃xff0c;所以可以用for循环获取每个a标签
all_a &＃61; BeautifulSoup(r.text, &＃39;lxml&＃39;).find_all(&＃39;a&＃39;, class_&＃61;&＃39;cV68d&＃39;)
self.makedir(&＃39;pictures&＃39;)
for a in all_a:
# a标签中完整的style字符串
img_str &＃61; a[&＃39;style&＃39;]
# 使用python的切片功能街区双引号之间的内容
img_url &＃61; img_str[img_str.index(&＃39;"&＃39;) &＃43; 1: img_str.index(&＃39;"&＃39;, img_str.index(&＃39;"&＃39;) &＃43; 1)]
start_pos &＃61; img_url.index(&＃39;photo&＃39;)
end_pos &＃61; img_url.index(&＃39;?&＃39;)
file_name &＃61; img_url[start_pos: end_pos] &＃43; &＃39;.jpg&＃39;
with open(file_name, &＃39;ab&＃39;) as f:
r &＃61; requests.get(img_url)
f.write(r.content)
if __name__ &＃61;&＃61; &＃39;__main__&＃39;:
picture &＃61; Picture()
picture.get_img()