【MOOC】Python网络爬虫与信息提取
import requests
from bs4 import BeautifulSoup
import bs4
# 获取网页内容
def getHTMLText(url):
try:
r = requests.get(url, timeout=30)
r.raise_for_status
r.encoding = r.apparent_encoding
return r.text
except:
return ""
# 解析网页内容
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[2].string, tds[3].string])
def printUnivList(ulist, num):
tplt = "{0:^10}\t{1:^10}\t{2:^10}\t{3:^10}"
print(tplt.format("排名", "学校", "省份" ,"总分", chr(12288)))
for i in range(num):
u = ulist[i]
print(tplt.format(u[0], u[1], u[2],u[3], chr(12288)))
def main():
uinfo = []
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
html = getHTMLText(url)
fillUnivList(uinfo, html)
printUnivList(uinfo, 20) # 打印出前20名
if __name__ == '__main__':
main()
输出结果如图所示:
缺陷:不对称,format函数还需研究