码迷,mamicode.com
首页 > Web开发 > 详细

phantomjs html to PDF

时间:2016-10-25 16:40:31      阅读:496      评论:0      收藏:0      [点我收藏+]

标签:ror   orm   方式   path   src   server   overflow   property   定义   

 

using System;
using System.Collections.Generic;
using System.Linq;
using System.Web;
using System.Configuration;
using System.IO;

/// <summary>
///PDFCommon 的摘要说明
/// </summary>
public class PDFCommon
{
	public PDFCommon()
	{
		
	}
    public static string CreatePDF(string url)
    {
        string fileNameWithOutExtention = Guid.NewGuid().ToString();
        string path = System.Web.HttpContext.Current.Server.MapPath(@"~\bin\phantomjs\");
        //string paths = System.Web.HttpContext.Current.Server.MapPath(@"~\chartPdfFile");
        string savePath = Path.Combine(@"D:/", string.Format("{0}.pdf", Guid.NewGuid()));
        string filePath = Path.Combine(path, "phantomjs.exe");
        string jsPath = Path.Combine(path, "generate_pdf.js");
        string argument = string.Format(" --ignore-ssl-errors=yes  {0} \"{1}\" {2}", jsPath, url, savePath);
        using (System.Diagnostics.Process exep = new System.Diagnostics.Process())
        {
            System.Diagnostics.ProcessStartInfo startInfo = new System.Diagnostics.ProcessStartInfo();
            startInfo.FileName = filePath;
            startInfo.Arguments = argument;
            startInfo.CreateNoWindow = true;
            startInfo.UseShellExecute = false;
            startInfo.RedirectStandardInput = true;
            startInfo.RedirectStandardOutput = true;
            startInfo.RedirectStandardError = true;
            exep.StartInfo = startInfo;
            exep.Start();
            exep.WaitForExit();
        }
        return savePath;
    }
}

  

// This file is NOT a browser-run javascript but PhantonJS script
var system = require(‘system‘);
var address = system.args[1];
var output = system.args[2];
var page = require(‘webpage‘).create();
page.paperSize = {
  format: ‘A4‘,
  orientation: ‘landscape‘,
  border: ‘1cm‘
};
page.open(address, function (status) {
    if (status !== ‘success‘) {
        console.log(‘Unable to load the address!‘);
        phantom.exit();
    } else {
        window.setTimeout(function () {
            // Remove all low-opacity paths. see PhantomJS  issue #364 
            page.evaluate(function () {
                var paths = document.getElementsByTagName("path");
                for (var i = paths.length - 1; i >= 0; i--) {
                    var path = paths[i];
                    var strokeOpacity = path.getAttribute(‘stroke-opacity‘);
                    if (strokeOpacity != null && strokeOpacity < 0.2)
                        path.parentNode.removeChild(path);
                }
            });
            page.render(output);
            phantom.exit();
        }, 5000);
    }
});

  

开篇

最近使用 Phantomjs 生成PDF,其中遇到一些问题,导致PDF生成失败,如出现空白文件或一页数据量太大,都是由于没有设置好格式导致。特别是分页问题,感觉资料很少,除了在 StackOverflow 上看到些许资料外,中文社区基本看不到,附上修改后的 rasterize.js 来做讲解:

 

var page = require(‘webpage‘).create(),
system = require(‘system‘),
address, output, size;

if (system.args.length < 3 || system.args.length > 5) {
console.log(‘Usage: rasterize.js URL filename [paperwidth*paperheight|paperformat] [zoom]‘);
console.log(‘ paper (pdf output) examples: "5in*7.5in", "10cm*20cm", "A4", "Letter"‘);
phantom.exit(1);
} else {
address = system.args[1];
output = system.args[2];
/*size of browser*/
page.viewportSize = { width: 600, height: 600 };
/*
if (system.args.length > 3 && system.args[2].substr(-4) === ".pdf") {
size = system.args[3].split(‘*‘);
page.paperSize = size.length === 2 ? { width: size[0], height: size[1], margin: ‘0px‘ }
: { format: ‘A4‘, orientation: ‘portrait‘, margin: ‘1cm‘ };
}
*/
/* ie and chrome view diffrent format of pdf */
page.settings.userAgent = ‘Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36‘;
page.paperSize = { format: ‘A4‘, orientation: ‘portrait‘, margin: ‘0.8cm‘ };
page.zoomFactor = 1;
page.settings.loadImages = true;
//some question about the page language
page.open(address, function (status) {
if (status !== ‘success‘) {
console.log(‘Unable to load the address!‘);
} else {
//page.render(output);
//phantom.exit();

window.setTimeout(function () {
page.render(output);
phantom.exit();
}, 200); //setting the time is enough to loading the page. document.ready

}
});
}

技术分享
 1 var page = require(‘webpage‘).create(),
 2     system = require(‘system‘),
 3     address, output, size;
 4 
 5 if (system.args.length < 3 || system.args.length > 5) {
 6     console.log(‘Usage: rasterize.js URL filename [paperwidth*paperheight|paperformat] [zoom]‘);
 7     console.log(‘  paper (pdf output) examples: "5in*7.5in", "10cm*20cm", "A4", "Letter"‘);
 8     phantom.exit(1);
 9 } else {
10     address = system.args[1];
11     output = system.args[2];
12     /*size of browser*/
13     page.viewportSize = { width: 600, height: 600 };
14     /*
15     if (system.args.length > 3 && system.args[2].substr(-4) === ".pdf") {
16         size = system.args[3].split(‘*‘);
17         page.paperSize = size.length === 2 ? { width: size[0], height: size[1], margin: ‘0px‘ }
18                                            : { format: ‘A4‘, orientation: ‘portrait‘, margin: ‘1cm‘ };
19     }
20     */
21     /* ie and chrome view diffrent format of pdf */
22     page.settings.userAgent = ‘Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36‘;
23     page.paperSize = { format: ‘A4‘, orientation: ‘portrait‘, margin: ‘0.8cm‘ };
24     page.zoomFactor = 1;
25     page.settings.loadImages = true;
26     //some question about the page language
27     page.open(address, function (status) {
28         if (status !== ‘success‘) {
29             console.log(‘Unable to load the address!‘);
30         } else {
31             //page.render(output);
32             //phantom.exit();
33             
34             window.setTimeout(function () {
35                 page.render(output);
36                 phantom.exit();
37             }, 200); //setting the time is enough to loading the page. document.ready
38             
39         }
40     });
41 }
技术分享

 

PDF 格式设置

关于其中 page 的设置属性,这里可以了解,更深入可以了解 WebPage Module

我们需要的设置,基本上就是页面格式、缩放、加载图片等,但有些例外,下面一一讲解。

1 page.paperSize = { format: ‘A4‘, orientation: ‘portrait‘, margin: ‘0.8cm‘ };

注释掉了官方例子的设置代码,因为传入的参数只有3个,到 .pdf 为止,如果写成通用模式,当然可以作为外部参数传入。

format :A4 纸,可以设置 "5in*7.5in", "10cm*20cm",  "Letter" 等

orientation :纸方向是竖着的,或者 landscape

margin :与纸四边间距,可自定义,也可详细设置 margin : { left: ‘0.8cm‘,  top : ‘0.8cm‘,  right : ‘0.8cm‘,  bottom : ‘0.8cm‘ }

1 page.zoomFactor = 1;
2 page.settings.loadImages = true;

zoomFactor :页面缩放比例

loadImages :页面加载图片

1 page.settings.userAgent = ‘Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.117 Safari/537.36‘;

这个设置比较不常见,一般的示例中都没有提及,因为发现用 chrome 和 IE 打开生成的 pdf 时格式有点不一样(表现在分页方面),由于偏向 Chrome 浏览格式,故设置此值,解决这个不一致问题。 

page.open 里面的 setTimeout 方法作用:等待页面执行完 js ,再生成 pdf。当然对于 js 要执行多久(要等多久),这个就不知道怎么预算了。其实我有试过 ajax 方式加载内容,但因此问题而作罢了。

更多的信息,关于页眉和页脚及页码标注问题,可以参考这里

 

PDF 分页

分页来说,更好控制,不需要代码(js)设置,页面使用样式即可:

1
style = “page-break-afteralways;”

控制每页内容的大小,使用 <div style="page-break-after: always;">content</div> 就行。

更多选择 style=“page-break-before: always;” , style="page-break-inside: avoid;" 这个可以避免内容散到两页中

 

phantomjs html to PDF

标签:ror   orm   方式   path   src   server   overflow   property   定义   

原文地址:http://www.cnblogs.com/jack-zeng/p/5997036.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!