mirror of
https://github.com/redoules/redoules.github.io.git
synced 2025-12-12 15:59:34 +00:00
267 lines
19 KiB
HTML
267 lines
19 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="fr">
|
|
|
|
<head>
|
|
<meta charset="utf-8">
|
|
<meta http-equiv="X-UA-Compatible" content="IE=edge">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<!-- The above 3 meta tags *must* come first in the head; any other head content must come *after* these tags -->
|
|
<meta name="description" content="Data Science for Political and Social Phenomena">
|
|
<meta name="author" content="Guillaume Redoulès">
|
|
<link rel="icon" href="../favicon.ico">
|
|
|
|
<title>Downloading a static webpage with python - Python</title>
|
|
|
|
<!-- JQuery -->
|
|
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.11.3/jquery.min.js"></script>
|
|
<script>
|
|
window.jQuery || document.write('<script src="../theme/js/jquery.min.js"><\/script>')
|
|
</script>
|
|
|
|
<!-- Bootstrap core CSS -->
|
|
<link rel="stylesheet" href="../theme/css/bootstrap.css" />
|
|
<!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
|
|
<link rel="stylesheet" type="text/css" href="../theme/css/ie10-viewport-bug-workaround.css" />
|
|
<!-- Custom styles for this template -->
|
|
<link rel="stylesheet" type="text/css" href="../theme/css/style.css" />
|
|
<link rel="stylesheet" type="text/css" href="../theme/css/notebooks.css" />
|
|
<link href='https://fonts.googleapis.com/css?family=PT+Serif:400,700|Roboto:400,500,700' rel='stylesheet' type='text/css'>
|
|
|
|
<!-- HTML5 shim and Respond.js for IE8 support of HTML5 elements and media queries -->
|
|
<!--[if lt IE 9]>
|
|
<script src="https://oss.maxcdn.com/html5shiv/3.7.2/html5shiv.min.js"></script>
|
|
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
|
|
<![endif]-->
|
|
|
|
|
|
<meta name="tags" content="Web Scraping" />
|
|
|
|
|
|
</head>
|
|
|
|
<body>
|
|
|
|
<div class="navbar navbar-fixed-top">
|
|
<div class="container">
|
|
<div class="navbar-header">
|
|
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-collapse">
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
<span class="icon-bar"></span>
|
|
</button>
|
|
<a class="navbar-brand" href="..">Guillaume Redoulès</a>
|
|
</div>
|
|
<div class="navbar-collapse collapse" id="searchbar">
|
|
|
|
<ul class="nav navbar-nav navbar-right">
|
|
<li class="dropdown">
|
|
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">About<span class="caret"></span></a>
|
|
<ul class="dropdown-menu">
|
|
<li><a href="../pages/about.html">About Guillaume</a></li>
|
|
<li><a href="https://github.com/redoules">GitHub</a></li>
|
|
<li><a href="https://www.linkedin.com/in/guillaume-redoul%C3%A8s-33923860/">LinkedIn</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="dropdown">
|
|
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Data Science<span class="caret"></span></a>
|
|
<ul class="dropdown-menu">
|
|
<li><a href="..#Blog">Blog</a></li>
|
|
<li><a href="..#Python">Python</a></li>
|
|
<li><a href="..#Bash">Bash</a></li>
|
|
<li><a href="..#SQL">SQL</a></li>
|
|
<li><a href="..#Mathematics">Mathematics</a></li>
|
|
<li><a href="..#Machine_Learning">Machine Learning</a></li>
|
|
<li><a href="..#Projects">Projects</a></li>
|
|
</ul>
|
|
</li>
|
|
<li class="dropdown">
|
|
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="false">Projects<span class="caret"></span></a>
|
|
<ul class="dropdown-menu">
|
|
<li><a href="https://github.com/redoules/redoules.github.io">Notes (Github)</a></li>
|
|
</ul>
|
|
</li>
|
|
|
|
<!--<li class="dropdown">
|
|
<a href="../feeds/blog.rss.xml">Blog RSS</a>
|
|
</li>-->
|
|
|
|
|
|
</ul>
|
|
|
|
<form class="navbar-form" action="../search.html" onsubmit="return validateForm(this.elements['q'].value);">
|
|
<div class="form-group" style="display:inline;">
|
|
<div class="input-group" style="display:table;">
|
|
<span class="input-group-addon" style="width:1%;"><span class="glyphicon glyphicon-search"></span></span>
|
|
<input class="form-control search-query" name="q" id="tipue_search_input" placeholder="e.g. scikit KNN, pandas merge" required autocomplete="off" type="text">
|
|
</div>
|
|
</div>
|
|
</form>
|
|
|
|
</div>
|
|
<!--/.nav-collapse -->
|
|
</div>
|
|
</div>
|
|
|
|
|
|
|
|
<!-- end of header section -->
|
|
<div class="container">
|
|
<!-- <div class="alert alert-warning" role="alert">
|
|
Did you find this page useful? Please do me a quick favor and <a href="#" class="alert-link">endorse me for data science on LinkedIn</a>.
|
|
</div> -->
|
|
<section id="content" class="body">
|
|
<header>
|
|
<h1>
|
|
Downloading a static webpage with python
|
|
</h1>
|
|
<ol class="breadcrumb">
|
|
<li>
|
|
<time class="published" datetime="2018-08-05T10:47:00+02:00">
|
|
05 août 2018
|
|
</time>
|
|
</li>
|
|
<li>Python</li>
|
|
<li>Web Scraping</li>
|
|
</ol>
|
|
</header>
|
|
<div class='article_content'>
|
|
<p>If you are using python legacy (aka python 2) first of all, stop ! Furthermore, this method won't work in python legacy</p>
|
|
<div class="highlight"><pre><span></span><span class="c1"># Import modules</span>
|
|
<span class="kn">from</span> <span class="nn">urllib.request</span> <span class="kn">import</span> <span class="n">urlopen</span>
|
|
</pre></div>
|
|
|
|
|
|
<p>The webpage source code can be downloaded with the command urlopen</p>
|
|
<div class="highlight"><pre><span></span><span class="n">url</span> <span class="o">=</span> <span class="s2">"http://example.com/"</span>
|
|
<span class="c1">#create a HTTP request in order to read the page</span>
|
|
<span class="n">page</span> <span class="o">=</span> <span class="n">urlopen</span><span class="p">(</span><span class="n">url</span><span class="p">)</span><span class="o">.</span><span class="n">read</span><span class="p">()</span>
|
|
</pre></div>
|
|
|
|
|
|
<p>The source code will be stored in the variable page as a string </p>
|
|
<div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="n">page</span><span class="p">)</span>
|
|
</pre></div>
|
|
|
|
|
|
<div class="highlight"><pre><span></span>b'<span class="cp"><!doctype html></span>\n<span class="nt"><html></span>\n<span class="nt"><head></span>\n <span class="nt"><title></span>Example Domain<span class="nt"></title></span>\n\n <span class="nt"><meta</span> <span class="na">charset=</span><span class="s">"utf-8"</span> <span class="nt">/></span>\n <span class="nt"><meta</span> <span class="na">http-equiv=</span><span class="s">"Content-type"</span> <span class="na">content=</span><span class="s">"text/html; charset=utf-8"</span> <span class="nt">/></span>\n <span class="nt"><meta</span> <span class="na">name=</span><span class="s">"viewport"</span> <span class="na">content=</span><span class="s">"width=device-width, initial-scale=1"</span> <span class="nt">/></span>\n <span class="nt"><style</span> <span class="na">type=</span><span class="s">"text/css"</span><span class="nt">></span>\n body {\n background-color: #f0f0f2;\n margin: 0;\n padding: 0;\n font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif;\n \n }\n div {\n width: 600px;\n margin: 5em auto;\n padding: 50px;\n background-color: #fff;\n border-radius: 1em;\n }\n a:link, a:visited {\n color: #38488f;\n text-decoration: none;\n }\n @media (max-width: 700px) {\n body {\n background-color: #fff;\n }\n div {\n width: auto;\n margin: 0 auto;\n border-radius: 0;\n padding: 1em;\n }\n }\n <span class="nt"></style></span> \n<span class="nt"></head></span>\n\n<span class="nt"><body></span>\n<span class="nt"><div></span>\n <span class="nt"><h1></span>Example Domain<span class="nt"></h1></span>\n <span class="nt"><p></span>This domain is established to be used for illustrative examples in documents. You may use this\n domain in examples without prior coordination or asking for permission.<span class="nt"></p></span>\n <span class="nt"><p><a</span> <span class="na">href=</span><span class="s">"http://www.iana.org/domains/example"</span><span class="nt">></span>More information...<span class="nt"></a></p></span>\n<span class="nt"></div></span>\n<span class="nt"></body></span>\n<span class="nt"></html></span>\n'
|
|
</pre></div>
|
|
|
|
|
|
<p>Additionally, you can beautifulsoup in order to make it easier to work with html</p>
|
|
<div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">bs4</span> <span class="kn">import</span> <span class="n">BeautifulSoup</span>
|
|
<span class="n">soup</span> <span class="o">=</span> <span class="n">BeautifulSoup</span><span class="p">(</span><span class="n">page</span><span class="p">,</span> <span class="s1">'lxml'</span><span class="p">)</span>
|
|
<span class="n">soup</span><span class="o">.</span><span class="n">prettify</span><span class="p">()</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="n">soup</span><span class="p">)</span>
|
|
</pre></div>
|
|
|
|
|
|
<div class="highlight"><pre><span></span><span class="cp"><!DOCTYPE html></span>
|
|
<span class="p"><</span><span class="nt">html</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">head</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">title</span><span class="p">></span>Example Domain<span class="p"></</span><span class="nt">title</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">meta</span> <span class="na">charset</span><span class="o">=</span><span class="s">"utf-8"</span><span class="p">/></span>
|
|
<span class="p"><</span><span class="nt">meta</span> <span class="na">content</span><span class="o">=</span><span class="s">"text/html; charset=utf-8"</span> <span class="na">http-equiv</span><span class="o">=</span><span class="s">"Content-type"</span><span class="p">/></span>
|
|
<span class="p"><</span><span class="nt">meta</span> <span class="na">content</span><span class="o">=</span><span class="s">"width=device-width, initial-scale=1"</span> <span class="na">name</span><span class="o">=</span><span class="s">"viewport"</span><span class="p">/></span>
|
|
<span class="p"><</span><span class="nt">style</span> <span class="na">type</span><span class="o">=</span><span class="s">"text/css"</span><span class="p">></span>
|
|
<span class="nt">body</span> <span class="p">{</span>
|
|
<span class="k">background-color</span><span class="p">:</span> <span class="mh">#f0f0f2</span><span class="p">;</span>
|
|
<span class="k">margin</span><span class="p">:</span> <span class="mi">0</span><span class="p">;</span>
|
|
<span class="k">padding</span><span class="p">:</span> <span class="mi">0</span><span class="p">;</span>
|
|
<span class="k">font-family</span><span class="p">:</span> <span class="s2">"Open Sans"</span><span class="p">,</span> <span class="s2">"Helvetica Neue"</span><span class="p">,</span> <span class="n">Helvetica</span><span class="p">,</span> <span class="n">Arial</span><span class="p">,</span> <span class="kc">sans-serif</span><span class="p">;</span>
|
|
|
|
<span class="p">}</span>
|
|
<span class="nt">div</span> <span class="p">{</span>
|
|
<span class="k">width</span><span class="p">:</span> <span class="mi">600</span><span class="kt">px</span><span class="p">;</span>
|
|
<span class="k">margin</span><span class="p">:</span> <span class="mi">5</span><span class="kt">em</span> <span class="kc">auto</span><span class="p">;</span>
|
|
<span class="k">padding</span><span class="p">:</span> <span class="mi">50</span><span class="kt">px</span><span class="p">;</span>
|
|
<span class="k">background-color</span><span class="p">:</span> <span class="mh">#fff</span><span class="p">;</span>
|
|
<span class="k">border-radius</span><span class="p">:</span> <span class="mi">1</span><span class="kt">em</span><span class="p">;</span>
|
|
<span class="p">}</span>
|
|
<span class="nt">a</span><span class="p">:</span><span class="nd">link</span><span class="o">,</span> <span class="nt">a</span><span class="p">:</span><span class="nd">visited</span> <span class="p">{</span>
|
|
<span class="k">color</span><span class="p">:</span> <span class="mh">#38488f</span><span class="p">;</span>
|
|
<span class="k">text-decoration</span><span class="p">:</span> <span class="kc">none</span><span class="p">;</span>
|
|
<span class="p">}</span>
|
|
<span class="p">@</span><span class="k">media</span> <span class="o">(</span><span class="nt">max-width</span><span class="o">:</span> <span class="nt">700px</span><span class="o">)</span> <span class="p">{</span>
|
|
<span class="nt">body</span> <span class="p">{</span>
|
|
<span class="k">background-color</span><span class="p">:</span> <span class="mh">#fff</span><span class="p">;</span>
|
|
<span class="p">}</span>
|
|
<span class="nt">div</span> <span class="p">{</span>
|
|
<span class="k">width</span><span class="p">:</span> <span class="kc">auto</span><span class="p">;</span>
|
|
<span class="k">margin</span><span class="p">:</span> <span class="mi">0</span> <span class="kc">auto</span><span class="p">;</span>
|
|
<span class="k">border-radius</span><span class="p">:</span> <span class="mi">0</span><span class="p">;</span>
|
|
<span class="k">padding</span><span class="p">:</span> <span class="mi">1</span><span class="kt">em</span><span class="p">;</span>
|
|
<span class="p">}</span>
|
|
<span class="p">}</span>
|
|
<span class="p"></</span><span class="nt">style</span><span class="p">></span>
|
|
<span class="p"></</span><span class="nt">head</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">body</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">div</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">h1</span><span class="p">></span>Example Domain<span class="p"></</span><span class="nt">h1</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">p</span><span class="p">></span>This domain is established to be used for illustrative examples in documents. You may use this
|
|
domain in examples without prior coordination or asking for permission.<span class="p"></</span><span class="nt">p</span><span class="p">></span>
|
|
<span class="p"><</span><span class="nt">p</span><span class="p">><</span><span class="nt">a</span> <span class="na">href</span><span class="o">=</span><span class="s">"http://www.iana.org/domains/example"</span><span class="p">></span>More information...<span class="p"></</span><span class="nt">a</span><span class="p">></</span><span class="nt">p</span><span class="p">></span>
|
|
<span class="p"></</span><span class="nt">div</span><span class="p">></span>
|
|
<span class="p"></</span><span class="nt">body</span><span class="p">></span>
|
|
<span class="p"></</span><span class="nt">html</span><span class="p">></span>
|
|
</pre></div>
|
|
</div>
|
|
<aside>
|
|
<div class="bug-reporting__panel">
|
|
<h3>Find an error or bug? Have a suggestion?</h3>
|
|
<p>Everything on this site is avaliable on GitHub. Head on over and <a href='https://github.com/redoules/redoules.github.io/issues/new'>submit an issue.</a> You can also message me directly by <a href='mailto:guillaume.redoules@gadz.org'>email</a>.</p>
|
|
</div>
|
|
</aside>
|
|
</section>
|
|
|
|
</div>
|
|
<!-- start of footer section -->
|
|
<footer class="footer">
|
|
<div class="container">
|
|
<p class="text-muted">
|
|
<center>This project contains 119 pages and is available on <a href="https://github.com/redoules/redoules.github.io">GitHub</a>.
|
|
<br/>
|
|
Copyright © Guillaume Redoulès,
|
|
<time datetime="2018">2018</time>.
|
|
</center>
|
|
</p>
|
|
</div>
|
|
</footer>
|
|
|
|
<!-- This jQuery line finds any span that contains code highlighting classes and then selects the parent <pre> tag and adds a border. This is done as a workaround to visually distinguish the code inputs and outputs -->
|
|
<script>
|
|
$( ".hll, .n, .c, .err, .k, .o, .cm, .cp, .c1, .cs, .gd, .ge, .gr, .gh, .gi, .go, .gp, .gs, .gu, .gt, .kc, .kd, .kn, .kp, .kr, .kt, .m, .s, .na, .nb, .nc, .no, .nd, .ni, .ne, .nf, .nl, .nn, .nt, .nv, .ow, .w, .mf, .mh, .mi, .mo, .sb, .sc, .sd, .s2, .se, .sh, .si, .sx, .sr, .s1, .ss, .bp, .vc, .vg, .vi, .il" ).parent( "pre" ).css( "border", "1px solid #DEDEDE" );
|
|
</script>
|
|
|
|
|
|
<!-- Load Google Analytics -->
|
|
<script>
|
|
/*
|
|
(function(i, s, o, g, r, a, m) {
|
|
i['GoogleAnalyticsObject'] = r;
|
|
i[r] = i[r] || function() {
|
|
(i[r].q = i[r].q || []).push(arguments)
|
|
}, i[r].l = 1 * new Date();
|
|
a = s.createElement(o),
|
|
m = s.getElementsByTagName(o)[0];
|
|
a.async = 1;
|
|
a.src = g;
|
|
m.parentNode.insertBefore(a, m)
|
|
})(window, document, 'script', '//www.google-analytics.com/analytics.js', 'ga');
|
|
|
|
ga('create', 'UA-66582-32', 'auto');
|
|
ga('send', 'pageview');
|
|
*/
|
|
</script>
|
|
<!-- End of Google Analytics -->
|
|
|
|
<!-- Bootstrap core JavaScript
|
|
================================================== -->
|
|
<!-- Placed at the end of the document so the pages load faster -->
|
|
<script src="../theme/js/bootstrap.min.js"></script>
|
|
<!-- IE10 viewport hack for Surface/desktop Windows 8 bug -->
|
|
<script src="../theme/js/ie10-viewport-bug-workaround.js"></script>
|
|
|
|
|
|
</body>
|
|
|
|
</html> |