自己写的小代码,对齐上还需要改进
import requests
import os
from bs4 import BeautifulSoup
import bs4
def getHTMLText(url):
try:
kv = {'user-agent':'Mozilla/5.0'}
r = requests.get(url,headers = kv)
r.raise_for_status()
r.encoding = r.apparent_encoding
return r.text
except:
return ""
def fillUnivList(ulist,html):
soup = BeautifulSoup(html,'html.parser')
for tr in soup.find('tbody').children:
if isinstance(tr,bs4.element.Tag):
tds = tr('td')
ulist.append([tds[0].string,tds[1].string,tds[3].string])
def printUnivList(ulist,num):
path = '路径,你懂得'
try:
if os.path.exists(path):
with open(path,'wb') as f:
temp = '{:^10}\t{:^6}\t{:^10}'.format('排名','学校名称','总分',chr(12288))+"\r\n"
f.write(temp.encode('utf-8'))
for i in range(num):
u = ulist[i]
temp = '{:^10}\t{:^6}\t{:^10}'.format(u[0],u[1],u[2],chr(12288))+"\r\n"
f.write(temp.encode('utf-8'))
f.close()
print('done')
else:
print('exited')
except:
print('failed')
uinfo = []
url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html"
html = getHTMLText(url)
fillUnivList(uinfo,html)
printUnivList(uinfo,20)
值得注意的有两点,写入文件时decode,以及换行时”\r\n”
In python 3, bytes strings and unicode strings are now two different types.
python3中对bytes strings和unicode strings区别对待,因此注意解码
另外换行不能用\n,而是\r\n