Python crawler replaces the links in the online html page with local links and saves the html file.

Import operating system, re

Def check_flag (flag):

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

If regex.match(flag) is False otherwise, result = True.

return result

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

Import BeautifulSoup from bs4.

html_content = ' ' '

& lta href = ""> Test 0 1

& lta href="/ 123 " >。 Test 02

& lta href = ""> Test 0 1

'''

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

Soup = BeautifulSoup (file, "html.parser")

For elements in soup.find_all('img'):

If there is "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 ("# # # # # # # # # # # # # # # # # # # #")

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

FP . write(soup . pretify())# pretify()？ Is to beautify sp? , readable.