python生成html页面 文件夹图片_使用Python提取html文件中的图片链接

#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 + '\n')

f.close()

print('\n-------------------------------------------')

print("\n链接已保存至{}".format(outputfile))

def main():

inputfile = '/Users/denglinzhe/Documents/html.txt'

outputfile = '/Users/denglinzhe/Documents/pic.txt'

filetxt = DuQuWenJian(inputfile)

TiQuDaoDeLianJei = TiQuImgLianJei(filetxt)

XianShiLianJei(TiQuDaoDeLianJei)

ShuChuDaoWenJian(outputfile,TiQuDaoDeLianJei)

main()