python爬虫--09 大学排名

import requests
from bs4 import BeautifulSoup
import bs4

## 步骤1：从网络上获取大学排名网页内容
def getHTMLText(url):
    try:
        r =  requests.get(url,timeout = 10)
        r.raise_for_status()
        r.encoding =r.apparent_encoding
        return r.text
    except:
        return '爬取失败'
## 步骤2：提取网页内容中信息到合适的数据结构
def fillUnivList(ulist,html):
    soup = BeautifulSoup(html,'html.parser')
    for tr in soup.find('tbody').children:
        if isinstance(tr,bs4.element.Tag):    ## 过滤掉非标签类型（字符串）
            tds = tr('td')        ## 查询td标签并存为列表tds
            ## #tds = tr.find_all('td')
            ulist.append([tds[0].string,tds[1].string,tds[3].string])
## 步骤3：利用数据结构展示并输出结果
def printUnivList(ulist,num):
    tplt = "{0:^10}\t{1:{3}^10}\t{2:^10}"   ## 定义模板，\t:横向制表符
    #print('{:^10}\t{:^6}\t{:^10}'.format('排名','学校名称','总分'))
    ## 当中文字符宽度不够时，采用西文字符填充；中西文字符占用宽度不同。采用中文字符的空格填充chr(12288).
    print(tplt.format("排名","学校名称","总分",chr(12288)))
    for i in range(num):
        u = ulist[i]
        #print('{:^10}\t{:^6}\t{:^10}'.format(u[0],u[1],u[2]))
        print(tplt.format(u[0], u[1], u[2], chr(12288)))

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

import requests
import bs4
from bs4 import BeautifulSoup
url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
r = requests.get(url)
r.encoding = r.apparent_encoding
soup = BeautifulSoup(r.text,'html.parser')
m = soup.find('tbody')
l = []
for tr in m.children:
    if isinstance(tr,bs4.element.Tag):
        tds = tr.find_all('td')
        l.append([tds[0].string,tds[1].string,tds[3].string])

t = '{0:^10}\t{1:{3}^10}\t{2:^10}'
print('{0:^10}\t{1:{3}^6}\t{2:^16}'.format('序号','名称','成绩',chr(12288)))
for i in range(20):
    u = l[i]
    print(t.format(u[0],u[1],u[2],chr(12288)))

代码解析

# find_all():返回一个数据列表---[****]
# find():返回一组数据