Task 25 - first reptile test

Posted by gp177 on Tue, 19 May 2020 16:43:11 +0200

First question: use the requests library to visit Baidu homepage 20 times, and return the length of his text and content attributes.

 

 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 Attribute length",len(rest.text))
20 print("content Attribute length",len(rest.content))
Because the result is too long, only part of the crawler content is intercepted:
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>Baidu once, you will know</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=use Baidu Search class="bg s_btn" autofocus></span> </form> </div> </div> <div id=u1> <a href=http://news.baidu.com name=tj_trnews class=mnav>Journalism</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>Map</a> <a href=http://v.baidu.com name=tj_trvideo class=mnav>video</a> <a href=http://tieba.baidu.com name=tj_trtieba class=mnav>Post Bar</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>Sign in</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">Sign in</a>');
3                 </script> <a href=//www.baidu.com/more/ name=tj_briicon class=bri style="display: block;">More products</a> </div> </div> </div> <div id=ftCon> <div id=ftConw> <p id=lh> <a href=http://home.baidu.com>About Baidu</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/>Read Before Using Baidu</a>&nbsp; <a href=http://jianyi.baidu.com/ class=cp-feedback>Feedback</a>&nbsp;Beijing ICP Zheng 030173&nbsp; <img src=//www.baidu.com/img/gs.gif> </p> </div> </div> </div> </body> </html>

The length output is as follows:

Textproperty length 2443
content attribute length 2443

Second question:

This is a simple html page. Please keep it as a string to complete the following calculation requirements.

a. Print the content of the head label and the last two digits of your student number

b get the body label content

c get the label object with id first

d get and print Chinese characters in html page

html is:

1 <!DOCTYPE html>
 2 
 3 <html>
 4 
 5 <head>
 6 
 7 <meta charset="utf-8">
 8 
 9 <title>Rookie tutorial( runoob.com)</title>
10 
11 </head>
12 
13 <body>
14 
15          <hl>My first title student number 25</hl>
16 
17          <p id="first">My first paragraph.</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>

My results are as follows:

Print the head label and my student number:
None my student number: 02
Get body tag content < body > < html1 >
<meta charset="utf-8"/>
< title > rookie tutorial( runoob.com )</title>
< HL > my first title < / HL >
< p id = "first" > my first paragraph. </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>
Get the tag object with ID first [< p id = "first" > my first paragraph. </p>]
Get and print Chinese characters in html page
['dish', 'bird', 'teaching', 'Cheng', 'I', 'my', 'no', 'one', 'Mark', 'title', 'I', 'no', 'one', 'one', 'piece', 'paragraph', 'fall'. ]

Question 3: ranking Chinese Universities

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

The code is as follows:

 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=["ranking","School name","Provinces and cities","Total score","Source quality","Culture results","Scale of scientific research",
39        "Quality of scientific research","Top results","Top Talent ","Science and technology services","Industry university research cooperation","Transformation of achievements","Internationalization of students"]
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()

The csv file is as follows:

Topics: Python REST Attribute IE Excel