第一个爬虫和测试

1 import requests
2 for i in range(20):
3     r=requests.get("http://www.baidu.com")
4     s=r.text
5     f=r.content
6     d1=len(r.text)
7     d2=len(r.content)
8     print(s,f,d1,d2)

 1 import requests
 2 import bs4
 3 from bs4 import BeautifulSoup
 4 def getHTMLText(url):
 5     try:
 6         r=requests.get(url,timeout=30)
 7         r.raise_for_status()
 8         r.encoding=r.apparent_encoding
 9         return r.text
10     except:
11         return ‘‘
12  
13 def fillUnivList(ulist,html):
14     soup=BeautifulSoup(html,‘html.parser‘)
15     for tr in soup.find(‘tbody‘).children:
16         if isinstance(tr,bs4.element.Tag):
17             tds=tr(‘td‘)
18             ulist.append([tds[0].string,tds[1].string,tds[3].string])
19 def printUnivList(ulist,num):
20     tplt="{0:^10}\t{1:{3}^10}\t{2:^10}"
21     print(tplt.format(‘排名‘,‘学校名称‘,‘总分‘,chr(12288))) 
22     for i in range(num):
23         u=ulist[i]
24         print(tplt.format(u[0],u[1],u[2],chr(12288)))
25 def main():
26     uinfo=[]
27     url=‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html‘
28     html=getHTMLText(url)
29     fillUnivList(uinfo,html)
30     printUnivList(uinfo,10)  
31 main()