易知爬虫作业

访问百度20次

import requests
for i in range(20):
    r = requests.get("https://www.baidu.com")
    print("网页返回状态:{}".format(r.status_code))
print("text内容为:{}".format(r.text))
print("\n")
print("text内容长度为:{}".format(len(r.text)))
print("content内容长度为:{}".format(len(r.content)))

结果

网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
网页返回状态:200
text内容为:<!DOCTYPE html>

<!--STATUS OK--><html> <head><meta http-equiv=content-type content=text/html;charset=utf-8><meta http-equiv=X-UA-Compatible content=IE=Edge><meta content=always name=referrer><link rel=stylesheet type=text/css href=https://ss1.bdstatic.com/5eN1bjq8AAUYm2zgoY3K/r/www/cache/bdorz/baidu.min.css><title>百度一下，你就知道</title></head> <body link=#0000cc> <div id=wrapper> <div id=head> <div class=head_wrapper> <div class=s_form> <div class=s_form_wrapper> <div id=lg> <img hidefocus=true src=//www.baidu.com/img/bd_logo1.png width=270 height=129> </div> <form id=form name=f action=//www.baidu.com/s class=fm> <input type=hidden name=bdorz_come value=1> <input type=hidden name=ie value=utf-8> <input type=hidden name=f value=8> <input type=hidden name=rsv_bp value=1> <input type=hidden name=rsv_idx value=1> <input type=hidden name=tn value=baidu><span class="bg s_ipt_wr"><input id=kw name=wd class=s_ipt value maxlength=255 autocomplete=off autofocus=autofocus></span><span class="bg s_btn_wr"><input type=submit id=su value=百度一下 class="bg s_btn" autofocus></span> </form> </div> </div> <div id=u1> <a href=http://news.baidu.com name=tj_trnews class=mnav>新闻</a> <a href=https://www.hao123.com name=tj_trhao123 class=mnav>hao123</a> <a href=http://map.baidu.com name=tj_trmap class=mnav>地图</a> <a href=http://v.baidu.com name=tj_trvideo class=mnav>视频</a> <a href=http://tieba.baidu.com name=tj_trtieba class=mnav>贴吧</a> <noscript> <a href=http://www.baidu.com/bdorz/login.gif?login&amp;tpl=mn&amp;u=http%3A%2F%2Fwww.baidu.com%2f%3fbdorz_come%3d1 name=tj_login class=lb>登录</a> </noscript> <script>document.write('<a href="http://www.baidu.com/bdorz/login.gif?login&tpl=mn&u='+ encodeURIComponent(window.location.href+ (window.location.search === "" ? "?" : "&")+ "bdorz_come=1")+ '" name="tj_login" class="lb">登录</a>');

                </script> <a href=//www.baidu.com/more/ name=tj_briicon class=bri style="display: block;">更多产品</a> </div> </div> </div> <div id=ftCon> <div id=ftConw> <p id=lh> <a href=http://home.baidu.com>关于百度</a> <a href=http://ir.baidu.com>About Baidu</a> </p> <p id=cp>&copy;2017&nbsp;Baidu&nbsp;<a href=http://www.baidu.com/duty/>使用百度前必读</a>&nbsp; <a href=http://jianyi.baidu.com/ class=cp-feedback>意见反馈</a>&nbsp;京ICP证030173号&nbsp; <img src=//www.baidu.com/img/gs.gif> </p> </div> </div> </div> </body> </html>




text内容长度为:2443
content内容长度为:2443

访问一个简单的html

<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8">
<title>blbl(runoob.com)</title>
</head>
<body>
    <h1>我的第一个标题</h1>
    <p id="first">我的第一个段落。</p>
</body>
<table border="1">
<tr>
    <td>row 1,cell 1</td>
    <td>row 1,cell 2</td>
</tr>
<tr>
    <td>row 2,cell 1</td>
    <td>row 2,cell 1</td>
</tr>
</table>
</html>

计算代码

from bs4 import BeautifulSoup
file=open('E:/网页/123.html','rb')
html=file.read()
bs=BeautifulSoup(html,"html.parser")
print(bs.head,end=' ')
print("32")
print(bs.body)
print(bs.find(id="first"))
print(bs.h1.string)
print(bs.p.string)

 

计算结果

posted @ 2020-05-13 18:29  平平无奇的陈序员  阅读(233)  评论(0)    收藏  举报