个人 圈外同学 Python下载文章里面的ppt图片

import requests



#原文：https://www.cnblogs.com/denglinzhe/p/12673766.html
#1.读取保存在本地的html文件
#2.提取页面中的链接文件
#3.在屏幕上显示提取到的链接文件
#4.将提取到的链接保存到文件




def DuQuWenJian(inputfile):
    f = open(inputfile,'r',encoding='utf-8')
    fo = f.readlines()
    f.close()
    return fo

def TiQuImgLianJei(filetxt):
    urls = []
    for line in filetxt:
        if 'img' in line:
            url = line.split('src=')[-1].split('"')[1]
            if 'http' in url:
                urls.append(url)
    return urls

def XianShiLianJei(TiQuDaoDeLianJei):
    count = 0
    for url in TiQuDaoDeLianJei:
        count += 1
        print('第{}张图片URL:{}'.format(count,url))

def ShuChuDaoWenJian(outputfile,TiQuDaoDeLianJei):
    f = open(outputfile,'w',encoding = 'utf-8')
    for line in TiQuDaoDeLianJei:
        f.write(line + '
')
    f.close()
    print('
-------------------------------------------')
    print("
链接已保存至{}".format(outputfile))


def main():

    inputfile = 'html.txt'
    outputfile = 'pic.txt'
    filetxt = DuQuWenJian(inputfile)
    TiQuDaoDeLianJei = TiQuImgLianJei(filetxt)
    XianShiLianJei(TiQuDaoDeLianJei)
    ShuChuDaoWenJian(outputfile,TiQuDaoDeLianJei)


#得到图片链接
#main()








def download_img(img_url, img_name):
    header = {"user-agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36"} 
    r = requests.get(img_url, headers=header, stream=True)
    if r.status_code == 200:        
        with open(img_name, "wb") as f:
            f.write(r.content)
    del r


def download():
    f = open("pic.txt", "r") 
    lines = f.readlines()
    arr=[]
    for line in lines:  
        line=line.strip('
')
        arr.append(line)

    for inx, val in enumerate(arr):
        print(inx)        
        img_name=str(inx)+".png"        
        download_img(val, img_name)   
    
#下载图片    
download()