python爬虫--获取网页图片

源码:

    
import urllib.request
import urllib.parse
import os

def url_open(url):
    req = urllib.request.urlopen(url)
    response = urllib.request.urlopen(url)

    html = response.read()

    return html

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,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]
        if os.path.exists(filename):
            break
        else:
            with open(filename,'wb') as f:
                img = url_open('http:'+each)
                f.write(img)


def download_mm(folder='ooxx',pages=10):
    #os.mkdir(folder)

    os.chdir(folder)

    url = 'https://jandan.net/ooxx/'

    page_num = int(get_page(url))

    for i in range(page_num):
        page_num -= 1
        if page_num!=0:
            page_url = url + 'page-' + str(page_num) + '#comments'
            img_addrs = find_imgs(page_url)
            save_imgs(folder,img_addrs)

if __name__ == '__main__':
    download_mm()

本人今天试了一下,还不错!

注意: 必须得有Python的运行环境!
在运行的时候,必须 在程序的下面 建一个 ooxx 的文件夹!