import requests import re import time import os headers = { 'User-Agent': 'assjkjsjks' } response = requests.get('www.vmgirls.com/13487.html'…) response.encoding='utf-8' print(response.request.headers) html = response.text
print(response.text)
"""解析网页""" images = re.findall('',html) """创建文件夹""" dir_name = re.findall('
(.*?)
',html)[-1] if not os.path.exists(dir_name): os.mkdir(dir_name)print(dir_name)
def urls(images): string = 'www.vmgirls.com/' n = len(images) for i in range(0,n): images[i]=string + images[i] # print(images[i]) return images urls(images) print(images) """保存图片""" for url in images: time.sleep(1) """图片名字""" file_name = url.split('/')[-1] response = requests.get(url, headers=headers) with open(dir_name + '/' + file_name,'wb') as f: f.write(response.content)
