【作品展示】闲来无事做了个半自动获取妹子图的爬虫

Catgu

新手来学习

laolao程序猿

喜欢喜欢

fforwardd

good

七彩兔

sansansa

太强了

1058704332

1

罗罗罗罗

666

cosyeria

1

bilibiliyo

看看

xspython

小魔芋

开车了，滴滴滴~~~

吴半仙

nj2010

BC菜鸡

111111

SeanNate

感谢分享

xjk39809337

？？？？/

WxxThu

很符合龟仙人的头像

东北第一好汉

2020.6.14随笔做了一个

import os
import urllib.request
import urllib.parse
import bs4
def open_url(url):
    req = urllib.request.Request(url)
    req.add_header("User-Agent","Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36")
    response = urllib.request.urlopen(req)
    html = response.read()
    return html
#找出当前网页的下一页
def begin(url):
    html = open_url(url)
    html = html.decode("utf-8")
    soup=bs4.BeautifulSoup(html,"html.parser")
    temp=soup.find_all(class_="previous-comment-page")#class_="current-comment-page"
    print("begin")
    #print(temp)
    #print(temp[0].attrs["href"])
    return (temp[0].attrs["href"])

#找出当前网页的所有图片下载地址网址
def find_imgs(url_page):
    html = open_url(url_page).decode("utf-8")
    soup=bs4.BeautifulSoup(html,"html.parser")
    temp=soup.find_all("img",referrerpolicy="no-referrer")
    addrs=[]   
    for i in temp:
        print(i.attrs["src"])
        addrs.append(i.attrs["src"])
    print("find")
    return addrs
#保存图片
def save_imgs(img_addrs):  
    for i in img_addrs:
        url = "http:"+i
        html = open_url(url)
        name = url.split("/")[-1]
        with open(name,"wb") as f:
            f.write(html)
    print("save")

#初始网页   
url = "http://jandan.net/ooxx"   
def download(url,page=30):   
    path=os.getcwd()+"/aaa"
    os.mkdir(path)
    os.chdir(path)
    save_imgs(find_imgs(url))#url第一个网页下载图片
    #后续网页循环下载
    for i in range(page-1):
         url_page = "http:" + begin(url)
         save_imgs(find_imgs(url_page))
         url = url_page


if __name__ == "__main__":
    download(url)

zhanghaofeng1

6

xiaoywy

ddsds