python 爬虫第二节 爬取图片

今天进行网页的图片爬取 用的最低级的urllib

import urllib.request
import os
def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('url-Agent','Mozz\illa/5.0()windows NT 6.3;WOW64')
    response = urllib.request.urlopen(url)
    html = response.read()
def get_page(url):
    html = url_open(url).decode('utf-8')
    
    a = html.find('current-comment-page')+23
    b = html.find(']',a)
    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+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 download(folder = 'paper',pages = 10):
    os.mkdir(folder)
    os.chdir(folder)

    url = "http://pic.netbian.com/"
    page_num = int(get_page(url))

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

if __name =='main':
            download()