爬虫_小试牛刀_爬取中国大学排名数据

```python
import requests
from bs4 import BeautifulSoup as bs
import csv
url = ‘http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html’
kv = {‘user-agent’:‘Mozilla/5.0’}
r = requests.get(url, headers = kv)
print(r.status_code)
print(r.encoding)
print(r.apparent_encoding)
print(r.request.url)
r.encoding = r.apparent_encoding
soup = bs(r.text,features=“html.parser”)
print(soup.prettify())

csvFile = open(“a_instance.csv”, “w”)
writers = csv.writer(csvFile)
l = list()
for infor in soup.find_all(‘td’):
if len(l)!=13:
l.append(str(infor.string))
else:
writers.writerow(l)
l = list()
l.append(str(infor.string))
print(‘Yep’)
csvFile.close()