Title

任务25——第一次爬虫测试

第一题：用resquests库访问百度主页20次，并返回他的text 和content属性的长度。

 

 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Tue May 19 10:12:16 2020
 4 
 5 @author: 49594
 6 """
 7 
 8 import requests
 9 url = "https://www.baidu.com/"
10 for i in range(20):
11     try:
12         rest = requests.get (url,timeout=30)
13         rest.raise_for_status()
14         r=rest.content.decode('utf-8')
15         print(r)
16     
17     except:
18         print("error")
19 print("text属性长度",len(rest.text))
20 print("content属性长度",len(rest.content))
由于结果篇幅过长，所以只截取部分爬虫内容：
1 <!DOCTYPE html>
2 <!--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>');
3                 </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>

长度输出结果如下：

text属性长度 2443
content属性长度 2443

第二题：

这是一个简单的html页面，请保持为字符串，完成后面的计算要求。

a.打印head标签内容和你的学号后两位

b 获取body标签内容

c 获取id为first的标签对象

d 获取并打印html页面中的中文字符

html为:

1 <!DOCTYPE html>
 2 
 3 <html>
 4 
 5 <head>
 6 
 7 <meta charset="utf-8">
 8 
 9 <title>菜鸟教程（runoob.com)</title>
10 
11 </head>
12 
13 <body>
14 
15          <hl>我的第一个标题学号25</hl>
16 
17          <p id="first">我的第一个段落。</p>
18 
19 </body>
20 
21                   <table border="1">
22 
23           <tr>
24 
25                   <td>row 1, cell 1</td>
26 
27                   <td>row 1, cell 2</td>
28 
29          </tr>
30 
31          <tr>
32 
33                   <td>row 2, cell 1</td>
34 
35                   <td>row 2, cell 2</td>
36 
37          <tr>
38 
39 </table>
40 
41 </html>

 我的结果如下：

打印head标签和我的学号:
None 我的学号：02
获取body标签内容 <body><html1>
<meta charset="utf-8"/>
<title>菜鸟教程(runoob.com)</title>
<hl>我的第一标题</hl>
<p id="first">我的第一个段落。</p>
<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 2</td>
</tr><tr>
</tr></table>
</html1></body>
获取id为first的标签对象 [<p id="first">我的第一个段落。</p>]
获取并打印html页面中的中文字符
['菜', '鸟', '教', '程', '我', '的', '第', '一', '标', '题', '我', '的', '第', '一', '个', '段', '落', '。']

第三题：爬取中国大学排名

网址：http://www.zuihaodaxue.com/zuihaodaxuepaiming2015_0.html

代码如下：

 1 import csv
 2 import os
 3 import requests
 4 from bs4 import BeautifulSoup
 5 allUniv = []
 6 def getHTMLText(url):
 7     try:
 8         r = requests.get(url, timeout=30)
 9         r.raise_for_status()
10         r.encoding ='utf-8'
11         return r.text
12     except:
13         return ""
14 def fillUnivList(soup):
15     data = soup.find_all('tr')
16     for tr in data:
17         ltd = tr.find_all('td')
18         if len(ltd)==0:
19             continue
20         singleUniv = []
21         for td in ltd:
22             singleUniv.append(td.string)
23         allUniv.append(singleUniv)
24 def writercsv(save_road,num,title):
25     if os.path.isfile(save_road):
26         with open(save_road,'a',newline='')as f:
27             csv_write=csv.writer(f,dialect='excel')
28             for i in range(num):
29                 u=allUniv[i]
30                 csv_write.writerow(u)
31     else:
32         with open(save_road,'w',newline='')as f:
33             csv_write=csv.writer(f,dialect='excel')
34             csv_write.writerow(title)
35             for i in range(num):
36                 u=allUniv[i]
37                 csv_write.writerow(u)
38 title=["排名","学校名称","省市","总分","生源质量","培养结果","科研规模",
39        "科研质量","顶尖成果","顶尖人才","科技服务","产学研究合作","成果转化","学生国际化"]
40 save_road="D:\\paiming.csv"
41 def main():
42     url = 'http://www.zuihaodaxue.com/zuihaodaxuepaiming2018.html'
43     html = getHTMLText(url)
44     soup = BeautifulSoup(html, "html.parser")
45     fillUnivList(soup)
46     writercsv(save_road,20,title)
47 main()

csv文件如下：

 

posted @ 2020-05-19 11:18  赖金明的大爹  阅读(463)  评论(0)  编辑  收藏  举报