论坛 › Python交流 › 手机上编写python

kuangshigubei 发表于 2020-11-13 08:51:35

{:5_109:}

大耳朵 发表于 2020-11-13 18:32:35

手机上编写python

青松100 发表于 2020-11-13 21:44:41

来学习学习

小帅小帅 发表于 2020-11-13 23:34:41

学习一下

小帅小帅 发表于 2020-11-13 23:35:17

不知道行不行

zk18336238932 发表于 2020-11-14 06:24:19

。。。

临时号 发表于 2020-11-14 11:19:25

看看

大昊 发表于 2020-11-14 15:51:02

收到

筱陌 发表于 2020-11-14 16:55:24

看看

6xl 发表于 2020-11-30 14:25:55

学习学习！

shaol2008 发表于 2020-11-30 22:16:26

谢谢分享

景行维贤 发表于 2020-11-30 23:38:24

1

伊格利斯 发表于 2020-12-1 00:04:02

看看再说

zhangshilin98 发表于 2020-12-1 09:32:29

学习！致敬！

今天又起雾了 发表于 2020-12-1 09:53:49

1

1240413749 发表于 2020-12-1 10:01:42

666

thon怪 发表于 2020-12-1 15:00:47

打卡

QuengC 发表于 2020-12-1 17:13:06

6666

yangminer 发表于 2020-12-1 21:31:19

看看

日暮途远Ez 发表于 2020-12-3 01:30:55

import requests
import os
import re
from bs4 import BeautifulSoup
import time


def url_open(url):
    headers = {
    'Referer': 'https://www.mzitu.com/',
    'User-Agent': 'Mozilla /5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
    }
    response = requests.get(url, headers=headers)
    #print(response)
    #return response
    html=response.text
    #soup=BeautifulSoup(html,'html.parser')
    soup=BeautifulSoup(html,'lxml')
    #div=soup.find('div',attrs={'id':'pins'})
    soup=soup.find(class_='postlist')
    soup1=str(soup)
    ss = r'<a href="([^"]+\d)"'
    urls=re.findall(ss,soup1)
    return urls

def url_open2(url):
    headers = {
    'Referer': 'https://www.mzitu.com/',
    'User-Agent': 'Mozilla /5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
    }
    response = requests.get(url, headers=headers)
    #print(response)
    #return response
    html=response.text

    return response



def save_jpg(jpg,x):
    jpg_dir='jpgs'
    filename =str(x) + '_' + jpg.split('/')[-1]
    #filename=jpg
    #x += 1
    print('正在保存文件'+filename)
    print('='*50)
    with open(filename, 'wb') as f:
      img = url_open2(jpg).content
      f.write(img)

def find_imgs(url):
    os.system("cls")
    x=0
    while True:
      headers = {
            'Referer': 'https://www.mzitu.com/',
            'User-Agent': 'Mozilla /5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0'
      }
      response = requests.get(url, headers=headers)
      html = response.text
      soup = BeautifulSoup(html, 'lxml')
      # print(html)
      soup = soup.find(class_='main-image')
      soup1 = str(soup)
      p = r'src="([^"]+\.jpg)"'
      pp = re.findall(p, soup1)
      # print(soup1)
      s = r'href="([^"]+\d)"'
      ss = re.findall(s,soup1)
      ppp=pp
      sss=ss
      print()
      print('处理图片：%s \n下一网址：%s' %(ppp,sss),)
      url=sss
      save_jpg(ppp,x)
      x+=1


def url_open1(htmls):
    print(htmls)
    for url in htmls:
      find_imgs(url)
      print('Ctrl+C退出吧。')
      time.sleep(555)



def download_new(folder='OOXX'):
    os.system('cls')
    os.system('del /qOOXX\*.*')
    os.system('rmdir OOXX')
    os.mkdir(folder)
    os.chdir(folder)
    print(url)
    htmls = url_open(url)
    htmls1 = url_open1(htmls)

if __name__ == '__main__':
    url = 'http://www.mzitu.com/'
    #download_mm()
    download_new()

查看完整版本: 手机上编写python