獲取html頁面的編碼
阿新 • • 發佈：2019-02-07
import rea = ["<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />", '<meta http-equiv=Content-Type content="text/html;charset=gb2312">', '<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">', '<meta http-equiv="Content-Type" content="text/html; charset=gb2312" /> '<meta http-equiv="content-type" content="text/html; charset=utf-8" />', '<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />', '<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />' ]b ="<meta[ ]+http-equiv=["']?content-type["']?[ ]+content=["']?text/html;[ ]*charset=([0-9-a-zA-Z]+)["']?B = re.compile(b, re.IGNORECASE)for ax in a: r1 = B.search(ax) if r1: print r1.group() print r1.group(1), len(r1.group()) else: print'not match'