from lxml Import html DEF the parse (): "" " " the contents of the html file, using small path extraction "" " # reading file content F = Open ( ' ./venv/static_/index.html ' , ' R & lt ' , encoding = ' UTF-. 8 ' ) S = reached, f.read () Selector = html.fromstring (S) # J parsing title H3 = selector.xpath ( ' / HTML / body / H3 / text () ' ) Print (h3 [0]) # here to get a list, I use the list get f.close() # Parse the contents inside ul ul = selector.xpath ( ' / HTML / body / ul / Li ' ) # ul = selector.xpath ( '// ul / Li') may also be used Print (len (ul)) for Li in UL: Print (li.xpath ( ' text () ' ) [0]) # parse the contents inside tr # tr = selector.xpath ( '/ HTML / body / form / Table / tr / TD / text ()' ) # Print (TR) # analytical element ul specified value UL2 = selector.xpath ( ' / HTML / body / ul / Li [@ class = "Important"] / text () ' ) Print (UL2) # parsing specified ul elements attributes selector.xpath = A ( ' // div [@ ID = "Container"] / A / text () ' ) Print (A [0]) # the href attribute the alink = selector.xpath ( ' // div [@ ID = "Container"] / A / @ the href ' ) Print (the alink [0]) # parse tag p p = selector.xpath ( ' / HTML / body / p / text () ' ) # p = selector.xpath (' / html / body / p [last ( )] / text () ') # Get the last Print (len (P)) Print (P [0]) # use browsing xpath builder Test selector.xpath = ( ' / HTML / body / form / Table / TR [. 1] / TH / text () ')# Can only learn / HTML / body / form / Table / tbody / TR [. 1] / TH Print (Test [0]) IF the __name__ == ' __main__ ' : the parse ()