python爬虫定向爬取中国大学排名

来源：互联网发布：女装淘宝店铺名字特别编辑：程序博客网时间：2024/06/10 07:42

#CrawUnivRankingA.pyimport requestsfrom bs4 import BeautifulSoupimport bs4def 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:        if isinstance(tr, bs4.element.Tag):            tds = tr('td')            ulist.append([tds[0].string, tds[1].string, tds[3].string])def printUnivList(ulist, num):    print("{:^10}\t{:^6}\t{:^10}".format("排名","学校名称","总分"))    for i in range(num):        u=ulist[i]        print("{:^10}\t{:^6}\t{:^10}".format(u[0],u[1],u[2]))def main():    uinfo = []    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'    html = getHTMLText(url)    fillUnivList(uinfo, html)    printUnivList(uinfo, 20) # 20 univsmain()

利用chr12288标准对汉字排名进行对其
使得界面更加美观有效！！

#CrawUnivRankingB.pyimport requestsfrom bs4 import BeautifulSoupimport bs4def 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:        if isinstance(tr, bs4.element.Tag):            tds = tr('td')            ulist.append([tds[0].string, tds[1].string, tds[3].string])def printUnivList(ulist, num):    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):        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 univsmain()

https://xuptacm.github.io/

阅读全文

0 0