python爬虫 将在线html网页中的图片链接替换成本地链接并将html文件下载到本地

import os,re

def check_flag(flag):

regex = re.compile(r'images\/')

result = True if regex.match(flag) else False

return result

#soup = BeautifulSoup(open('index.html'))

from bs4 import BeautifulSoup

html_content = '''

<a href="https://xxx.com">测试01</a>

<a href="https://yyy.com/123">测试02</a>

<a href="https://xxx.com">测试01</a>

<a href="https://xxx.com">测试01</a>

'''

file = open(r'favour-en.html','r',encoding="UTF-8")

soup = BeautifulSoup(file, 'html.parser')

for element in soup.find_all('img'):

if 'src' in element.attrs:

print(element.attrs['src'])

if check_flag(element.attrs['src']):

#if element.attrs['src'].find("png"):

element.attrs['src'] = "michenxxxxxxxxxxxx" +'/'+ element.attrs['src']

print("##################################")

with open('index.html', 'w',encoding="UTF-8") as fp:

fp.write(soup.prettify()) # prettify()的作⽤是将sp美化⼀下，有可读性

下面是来自ci的下载辅助函数，基本原理是生成一个能下载数据的http header，然后把文件数据发送过去就行啦。应该是可以直接用的，如果还有什么问题，我再看看啊

$data = file_get_contents("/path/to/photo.jpg")// 读文件内容

$name = 'myphoto.jpg'

force_download($name, $data)

function force_download($filename = '', $data = '')

{

if ($filename == '' OR $data == '')

{

return FALSE

}

// Try to determine if the filename includes a file extension.

// We need it in order to set the MIME type

if (FALSE === strpos($filename, '.'))

{

return FALSE

}

// Grab the file extension

$x = explode('.', $filename)

$extension = end($x)

$mimes = array( 'bmp' =>array('image/bmp','application/octet-stream'),

'gif' =>array('image/gif','application/octet-stream'),

'jpeg' => array('image/jpeg', 'image/pjpeg', 'application/octet-stream'),

'jpg' => array('image/jpeg', 'image/pjpeg', 'application/octet-stream'),

'jpe' => array('image/jpeg', 'image/pjpeg', 'application/octet-stream'),

'png' => array('image/png', 'image/x-png', 'application/octet-stream')

)

// Set a default mime if we can't find it

if ( ! isset($mimes[$extension]))

{

$mime = 'application/octet-stream'

}

else

{

$mime = (is_array($mimes[$extension])) ? $mimes[$extension][0] : $mimes[$extension]

}

// Generate the server headers

if (strstr($_SERVER['HTTP_USER_AGENT'], "MSIE"))

{

header('Content-Type: "'.$mime.'"')

header('Content-Disposition: attachmentfilename="'.$filename.'"')

header('Expires: 0')

header('Cache-Control: must-revalidate, post-check=0, pre-check=0')

header("Content-Transfer-Encoding: binary")

header('Pragma: public')

header("Content-Length: ".strlen($data))

}

else

{

header('Content-Type: "'.$mime.'"')

header('Content-Disposition: attachmentfilename="'.$filename.'"')

header("Content-Transfer-Encoding: binary")

header('Expires: 0')

header('Pragma: no-cache')

header("Content-Length: ".strlen($data))

}

exit($data)

}

<a href="picName.jpg" id=pic1 onclick="savepic()return false" style="cursor:hand">点击下载</a>

<script type="text/javascript">

function savepic() {

if (document.all.a1 == null) {

objIframe = document.createElement("IFRAME")

document.body.insertBefore(objIframe)

objIframe.outerHTML = "<iframe name=a1 style='width:400pxhieght:300px' src=" + imageName.href + "></iframe>"

re = setTimeout("savepic()", 1)

}

else {

clearTimeout(re)

pic = window.open(imageName.href, "a1")

pic.document.execCommand("SaveAs")

document.all.a1.removeNode(true)

}

}

</script>

---