看了半天实在不知道你想爬网页上面的什么图片
只能帮你把 找页数的那个函数改好了
后面的找图片的那个程序不知道要爬什么,没改#! /usr/bin/env python
# -*- coding:utf-8 -*-
import urllib.request
import os,re
def url_open(url):
req = urllib.request.Request(url)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 UBrowser/6.2.4094.1 Safari/537.36') #加上header
response = urllib.request.urlopen(url)
html = response.read() #返回文件文本
return html
def get_page(url):
html = url_open(url).decode('utf-8')
num = re.findall(r"<dd><a href='/default.aspx\?page=2&elite=0&keyword=&type=0&tag=0&nid=-1'>(.*?)</a>",html)
return num[0]
def find_img(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])
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(each)
f.write(img)
def dowmload(folder = 'picture',pages = 10): #定义函数下载照片,文件名和page数
os.chdir(folder)#更改目录
url = "http://games.tgbus.com/default.aspx?page"#将地址传到URL里面
try:
int('')
except ValueError:
pass
page_num = int(get_page(url)) #调用get_page函数,将结果存储在page_num里面
for i in range(pages):
page_num -= i
page_url = url +'='+str(page_num)
img_addrs = find_img(page_url)
save_imgs(folder,img_addrs)
if __name__ =='__main__':
dowmload()
|