Question

我有一个包含多个javascript标签的html页面。我想从特定标记中提取数据的问题：

<head>
...
</head>
<body>
...
<script type="text/javascript">

    $j(document).ready(function() {

        if (!($j.cookie("ios"))) {
            new $c.free.widgets.FreeAdvDialog().open();
            $j.cookie("ios", "seen", { path: '/', expires: 10000});
        };

        ajax_keys = ["d24349f205e3deb7f1015f42d3a14da7205b62e4", "0ae78c4797d47745ebd44e2754367da10c6f56a4", "567b2bfb6fd1aee784115da54e5e116a280ee225", "fc5cd251be46ff101c471553d52c07bf08c9aa65"];
        var is_dm = false;

        /* async chart loader */
        var chart = new $c.free.widgets.Chart({
            target: $j('#graph'),
            width: 990,
            height: 275,
            site: "911.com",
            source_panel: 'us'
        });

        var chart_view = new $c.free.widgets.ChartView({
            chart: chart,
            csv_button: 'csv-export',
            save_button: 'graph-image',
            embed_button: 'embed-graph',
            key: ajax_keys[1]
        });
        chart_view.render();

        /* zoom info initialization */
        var zoom_info = new $c.free.widgets.ZoomInfo({
            site: "911.com",
            el: '#zoominfo',
            key: ajax_keys[3]
        });
        zoom_info.load();


        /* compete numbers initialization */
        var compete_numbers = new $c.free.widgets.CompeteNumbers({
            site: "911.com",
            key: ajax_keys[0],
            el: '#compete_numbers'
        });
        compete_numbers.load();

        /* DM Marketing widget init */
        new $c.free.widgets.DMSignupMessage({
            is_dm: is_dm,
            compete_numbers: compete_numbers
        });

        /* personalization initialization */


            var logged_in_as = null;


        var d = {
          site_name: "911.com",
          logged_in_as: logged_in_as,
          current_source_panel: {"display_abbreviation": "us", "panel_name": "us", "image_url": "http://media.compete.com/site_media/images/icons/flag_us.gif", "id": 1, "display_name": "United States"}
        };

        var auth_model = new $c.free.widgets.FreeLoginModel(d);
        var links_opts = { model: auth_model };
        var links_view = new $c.free.widgets.FreeAccountLinksView(links_opts);

        var sites_view = new $c.free.widgets.FollowSiteButtonView(links_opts);
        var manage_view = new $c.free.widgets.ManageSitesListButtonView(links_opts);

        var sites = new $c.free.widgets.SimilarSitesCollection([], {
            site: "911.com",
            source_panel: 'us',
            key: ajax_keys[2],
            auth: auth_model
        });
        var graph = new $c.free.widgets.BarGraph({
            el: $j('#similar-sites'),
            collection: sites
        });

        // tell KISSMetrics where we are
        // also identify user so KM console can refer to them by email
        if(logged_in_as != null) {
            _kmq.push(['identify', logged_in_as]);
        }
        _kmq.push(['record', 'Viewed Free Site Analytics Report (M)']);
    });

...

如何从页面的特定标签获取 ajax_keys （即“d24349f205e3deb7f1015f42d3a14da7205b62e4”）？

P.S。我试图在python脚本中使用正则表达式，但我无法从标记中检索必要的元素。

感谢您的帮助。

Answer 1

如果您使用像BeautifulSoup这样的库，您可以获取特定的脚本标记，然后对标记的内容而不是整个文档使用正则表达式。

那就是说，假设只有一个ajax_keys，它看起来像正则表达式一样：

import re

ajaxre = re.compile(r"^\s+ajax_keys = ([^;]+)", re.MULTILINE)
ajax_string = ajaxre.match(source).group(1)

# to get it as a python list
import json
ajax_keys = json.loads(ajax_string)

编辑：感谢@Karl Knechtel为json.loads

从特定的<script type =“text / javascript”> </script>获取特定数据

1 个答案: