煎蛋的扒图小例子

import urllib.request
import os
def url_open(url):
	req = urllib.request.Request(url)
	req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36')
	response = urllib.request.urlopen(req)
	html = response.read()
	return html
def get_page(url):
	html = url_open(url).decode('utf-8')
	a = html.find('current-comment-page') + 23 #正好是页码的位置
	b = html.find(']',a)#从索引a出开始查找
	#print(html[a:b])
	return html[a:b]

def find_imgs(url):
	html = url_open(url).decode('utf-8')
	img_addrs = []

	a = html.find('img src=')
	while a != -1:
		b = html.find('.jpg',a,a+255)
		if b != -1:
			img_addrs.append(html[a+9:b+4])#图片链接
		else:
			b = a+9
		a = html.find('img src=',b)

	return img_addrs                    
def save_imgs(folder,img_addrs):

    for each in img_addrs:
	    filename = each.split('/')[-1]
	    with open(filename,'wb') as f:
		    img = url_open('http:' + each)#这里需要加上http:，不知道为什么视频里不加就可以
		    f.write(img)

def download_mm(folder='ooxx',page=10):
	os.mkdir(folder)#创建文件夹
	os.chdir(folder)#改变工作目录

	url = 'http://jandan.net/ooxx/'
	page_num = int(get_page(url)) #页码

	for i in range(page):
		page_num -= i
		page_url = url + 'page-' + str(page_num) + '#comments'
		img_addrs = find_imgs(page_url)
		save_imgs(folder,img_addrs)

if __name__ == '__main__':
	download_mm()