# Need to open https://www.dytt8.net/ site through the code, to get the site content from urllib.request Import urlopen # get urlopen Import Re Content = urlopen ( " https://www.dytt8.net/ " ) .read (). decode ( " GBK " ) # get links to the latest movie part # regular expression matching string LST = re.findall ( " the latest movie download </a>] <a href = '( . * ?) ' " , Content, re.S) for Item in LST: # 3. splicing a URL subpages one_page_content = urlopen ( " https://www.dytt8.net/ "Item +) .read (). Decode ( " GBK " ) one_page_lst = re.findall ( ' <div the above mentioned id = "Zoom">. *? ◎ title \ u3000 (. *?) <br />. *? < style = TD "WORD-the WRAP: BREAK-Word" bgcolor = "# fdfddf"> <a href="(.*?)"> ' , one_page_content, re.S) Print (one_page_lst) # 4. Get the name of the movie and movie links saved in txt file MOVIE_NAME is playing = one_page_lst [0] [0] DOWNLOAD_URL = one_page_lst [0] [1 ] # file operations f = Open ( " movie.txt " , the MODE = " w " ,encoding="utf-8") F.write ( " Movie name: " + MOVIE_NAME is playing + " \ the n- " ) f.write ( " Download Link: " + DOWNLOAD_URL) Print ( " a complete " ) f.close ()