007 Python网络爬虫与信息提取 中国大学排名爬虫

import requests
from bs4 import BeautifulSoup
import bs4

# 中国大学排名

# 1. 从url中获取所需html代码并返回
def getHTMLText(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ‘‘


# 2. 从获取到的html代码中解析出所需要的的数据保存在列表中并返回
def fillUnivList(html):
    ulist = []
    sublist = []
    soup = BeautifulSoup(html, ‘html.parser‘)
    text = soup.tbody
    for tr in soup.find(‘tbody‘).children:
        tds = tr(‘td‘)
        for item in tds:
            sublist.append(item.string)
        ulist.append(sublist)
        sublist = []
    return ulist


# 3. 根据输入的信息，按要求打印出相应数据
def printUnivList(ulist, start, end):
    print(‘{:^9}{:^12}{:^15}‘.format(‘排名‘, ‘学校名称‘, ‘分数‘))
    for i in range(start, end+1):
        print(‘{:^10}{:^12}{:^15}‘.format(ulist[i][0], ulist[i][1], ulist[i][2]))


# 主程序
def main():
    url = ‘http://www.gaosan.com/gaokao/299262.html‘
    html = getHTMLText(url)
    uinfor = fillUnivList(html)
    printUnivList(uinfor, 5, 30)


# 运行主程序
main()