简单爬虫小项目-爬取煎蛋网图片

import urllib.request
import os
import base64


def url_open(url):
    req = urllib.request.Request(url)
    req.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36')
    response = urllib.request.urlopen(req)
    html = response.read()
    return html
     


def find_imges(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('http:'+html[a+9:b+4])
        else:
            b=a+9
                

        a = html.find('img src',b)

    return img_addrs
     
    
    
    
   

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]



def save_imges(file,urls):
    for each in urls:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)
            
    



def download_mm(file = "ooxx3",pagenum = 10):
    os.mkdir(file)
    os.chdir(file)
    url = 'http://jandan.net/girl/'
# 首先访问到页面，查看页面内的页码
    page_num  = 65
    # int(get_page(url))
# 其次根据页码得到一定量的页面的网址
    for i in range(pagenum):
        page_num-=1
        datee = "20210726-"
        str_url = datee+str(page_num)
        encode_url = base64.encodebytes(str_url.encode('utf-8')).decode()
        aa = "#com"
        detail_url = url+encode_url
        detail_ur =detail_url+aa
        print(detail_ur)
        
        # 然后对网址内的jpg进行网址识别抓取
        img_addrs =find_imges(detail_url)
        #然后对jpg进行保存到文件
        save_imges(file,img_addrs)

        

download_mm()
         
# 代理使用 要得到代理表达式，获得代理支持urllib.request.proxyhander()
# 然后将获得build_oener() ，然后在安装到opener,urllib.request.intall_opener

by ：参照小甲鱼视频