python爬虫：批量爬取网页图片

引言

自学python爬虫，完成了批量爬取网页图片，记录一下。

代码

中间包含一些用于测试的输出代码。

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; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.1071 SLBChan/1')
    header = {
    
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36 SLBrowser/7.0.0.1071 SLBChan/1'}
    req = urllib.request.Request(url = url,headers = header)
    response = urllib.request.urlopen(req)

    #response = urllib.request.urlopen(url)
    html = response.read()

    print(url)
    return html


def get_page(url):
    html =  url_open(url).decode('utf-8')


    a = html.find('current-comment-page') + 23
    b = html.find(']',a)

    print(html[a:b])
    return html[a:b]


   #获取页面内部的图片地址
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)

    for each in img_addrs:
        print(each)

    return img_addrs

    #保存图片模块
def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            #  + http:
            img = url_open('http:'+ each)
            f.write(img)



def download_10(folder = 'niu',pages = 2):
    os.mkdir(folder)
    os.chdir(folder)

    #http://jandan.net/ooxx/MjAyMTAyMjAtMTA5#comments
    #获取当前页面的URL
    url = "http://jandan.net/ooxx/"
    #获取当前页面数
    page_num = int(get_page(url))
    #根据偏移量依次寻找页面
    for i in range(pages):
        page_num -= i
        #页数问题
        page_url = url+ 'MjAyMTAyMjEtMTE'+str(page_num) +'#comments'
        img_addrs = find_imgs(page_url)

        save_imgs(folder,img_addrs)


if __name__== '__main__':
    download_10()

总结

继续努力！！！