python 爬虫实例--2016中国最好大学排名（非原创）

在慕课上看到了一个简单易懂的爬虫实例，添加一下注释算是自己保存着，顺便分享一下~

url为 http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html

#CrawUnivRankingB.py
import requests
from bs4 import BeautifulSoup
import bs4

def getHTMLText(url): #1 get url
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

def fillUnivList(ulist, html): #2 解析网址生成列表
    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): #3 显示列表
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num): #后来做了优化，是输出的学校名称居中对齐，chr（12288）是汉字里面的空格
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))

def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()

小白的同学也可以看一下原来教程

http://www.icourse163.org/learn/BIT-1001870001?tid=1002236011#/learn/content?type=detail&id=1002993610&cid=1003503396&replay=true