Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #!/usr/bin/python
- # -*- coding: utf-8 -*-
- #
- import sys
- from lxml import etree
- data3 = '''
- <!DOCTYPE html>
- <html xmlns="http://www.w3.org/1999/xhtml" xmlns:og="http://opengraphprotocol.org/schema/" xmlns:fb="http://www.facebook.com/2008/fbml">
- <head>
- <meta charset="UTF-8">
- <title>The 20 Most Despicable Things Gordon Ramsay Has Said and Done, Ranked -- Grub Street New York</title>
- <link rel="alternate" type="application/rss+xml" title="RSS 2.0" href="http://feedproxy.google.com/nymag/grubstreet" />
- <meta name="Headline" content="The 20 Most Despicable Things Gordon Ramsay Has Said and Done, Ranked" />
- <meta name="keywords" content="april bloomfield, el gordo, frank bruni, gordon ramsay, lawsuits, lists, marcus samuelsson, mario batali, shitlist, spotted pig, sued" />
- <meta name="description" content="Racism, fat-shaming, and vegetarian trickery." />
- <meta name="Byline" content="Sierra Tishgart" />
- <meta name="Type_of_Feature" content="" />
- <meta name="Issue_Date" content="March 8, 2013 12:50 PM" />
- <meta name="related_stories" content="The 20 Most Despicable Things Gordon Ramsay Has Said and Done, Ranked" />
- <meta name="document_type" content="Blog" />
- <meta name="category" content="Lists" />
- <link rel="image_src" href="http://pixel.nymag.com/imgs/daily/grub/2013/03/08/08-gorgon-ramsay.o.jpg/a_146x97.jpg" />
- <link rel="canonical" href="http://newyork.grubstreet.com/2013/03/20-despicable-things-gordon-ramsay.html" id="canonical" />
- <script>
- var canonicalUrl = "http://newyork.grubstreet.com/2013/03/20-despicable-things-gordon-ramsay.html";
- </script>
- <meta name="content.tags.primary" content=";network - Grub Street,;city - New York City,;tag - lists" />
- <meta name="content.tags" content=";tag - april bloomfield,;tag - el gordo,;tag - frank bruni,;tag - gordon ramsay,;tag - lawsuits,;tag - marcus samuelsson,;tag - mario batali,;tag - shitlist,;tag - spotted pig,;tag - sued" />
- <meta name="content.hierarchy" content="New York City:Grub Street" />
- <meta name="content.type" content="Blog" />
- <meta name="content.subtype" content="Blog Entry" />
- <meta property="fb:app_id" content="206283005644" />
- <meta property="og:title" content="The 20 Most Despicable Things Gordon Ramsay Has Said and Done, Ranked" />
- <meta property="og:description" content="Racism, fat-shaming, and vegetarian trickery." />
- <meta property="og:image" content="http://pixel.nymag.com/imgs/daily/grub/2013/03/08/08-gorgon-ramsay.o.jpg/a_146x97.jpg"/>
- <meta property="og:url" content="http://newyork.grubstreet.com/2013/03/20-despicable-things-gordon-ramsay.html" />
- <meta property="og:type" content="article" />
- <meta property="og:site_name" content="Grub Street New York" />
- <meta name="viewport" content="width=1020">
- <link type="text/css" rel="stylesheet" href="http://cache.nymag.com/css/screen/grubstreet/grubstreet-core.css" media="all" />
- <link type="text/css" rel="stylesheet" href="http://cache.nymag.com/css/screen/section/daily/slideshow.css" media="all" />
- <link type="text/css" rel="stylesheet" href="http://cache.nymag.com/css/screen/echo.css" media="all" />
- <link type="text/css" rel="stylesheet" href="http://cache.nymag.com/css/screen/loginRegister.css" media="all" />
- <link rel="stylesheet" href="http://cache.nymag.com/css/screen/advertising.css" media="all" />
- <link rel="shortcut icon" href="http://images.nymag.com/gfx/grubst/favicon.ico" />
- <style type="text/css">
- #adsplashtop,#pushdown {padding:5px 5px;}
- #pushdown {border-top:1px solid #737373}
- </style>
- <!--[if IE 6]>
- <link rel="stylesheet" href="http://cache.nymag.com/css/screen/grubstreet/win-ie6.css" type="text/css" media="screen, projection" />
- <![endif]-->
- <!--[if IE 7]>
- <link rel="stylesheet" href="http://cache.nymag.com/css/screen/grubstreet/win-ie7.css" type="text/css" media="screen, projection" />
- <![endif]-->
- <script type="text/javascript">
- var NYM = {};
- NYM.config = {};
- NYM.config.membership = {
- "service":"nym"
- };
- NYM.config.advertising = {
- "sitename":"nym.grubstreet"
- };
- </script>
- <script type="text/javascript">
- var date = 'March 12, 2013 12:42:38';
- var currDate=new Date(date);
- var GRUBST = {};
- if (!NYM) {
- var NYM = {};
- NYM.config = {};
- NYM.config.membership = {
- "service":"nym"
- };
- NYM.config.advertising = {
- "sitename":"nym.grubstreet"
- };
- }
- </script>
- <script type="text/javascript" src="http://cache.nymag.com/scripts/modernizr-1.7.min.js"></script>
- <script type="text/javascript" src="http://ajax.googleapis.com/ajax/libs/jquery/1.4.2/jquery.min.js"></script>
- <script type="text/javascript" src="http://cache.nymag.com/scripts/jquery-ui-1.8.2.custom.min.js"></script>
- <script type="text/javascript" src="http://cache.nymag.com/scripts/ad_manager.js"></script>
- <script type="text/javascript" src="http://cache.nymag.com/js/2/global.js"></script>
- <script type="text/javascript" src="http://cache.nymag.com/scripts/skinTakeover.js"></script>
- <script type="text/javascript" src="http://cache.nymag.com/scripts/grubstreet-controls.js"></scr
- '''
- n = 0
- while True:
- n += 1
- tree = etree.HTML( data3 )
- m = tree.xpath("//meta[@property]")
- print '-', n
- for i in m:
- print n
- #print (i.attrib['property'], i.attrib['content'])
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement