python-中国大学排名爬虫

#CrawUnivRankingB.py
import requests
from bs4 import BeautifulSoup
import bs4
 
def getHTMLText(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):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:#children迭代找到tbldy标签的孩子
        if isinstance(tr, bs4.element.Tag): #排除不是tag类型的内容，比如字符串
            tds = tr('td')#在每个tr中查找td，tr('td')等价tr.find_all('td')查找全部td标签内容，返回列表
            ulist.append([tds[0].string, tds[1].string, tds[3].string])#前三项就是排名，名称，总分,二位列表中添加一项列表，内含三个元素
 
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"#3是槽中的槽，是中文空格字符
    print(tplt.format("排名","学校名称","总分",chr(12288)))#12288中文空格编码，被chr转换成字符串
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],chr(12288)))
     
def main():
    uinfo = []
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 20) # 20 univs
main()

总结：采用requests-bs4技术路线，实现定向爬虫，对中英文混排输出问题进行了优化。