Python爬虫類大学ランキング

#!/usr/bin/env python
# -*- coding: utf_8 -*-

import bs4
import requests
from bs4 import BeautifulSoup

'''
    Python？     【     】      Python  ！
'''


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


# 2.                                 
def fillUnivList(ulist, html):
    #  BeautifulSoup      ’html.parser‘   
    soup = BeautifulSoup(html, "html.parser")
    #                       tbody   ，        ’tbody‘          
    for tr in soup.find('tbody').children:
        #   bs4.element.Tag     tr  
        if isinstance(tr, bs4.element.Tag):
            #   tr       tr    td  
            tds = tr('td')
            # [1, 
    
,   , 95.3...
            #             td                        ulist 
            ulist.append([tds[0].string, tds[1].string,
                          tds[2].string, tds[3].string])


# 3.                       
def printUnivList(ulist, province):
    #     
    print("        2019({}  )".center(45, '-').format(province))
    #     format      
    #   ：   {4}   utf8             ，python        
    tplt = "{0:^10}\t{1:{4}^10}\t{2:^10}\t{3:^10}"
    #      ，   chr(12288)              
    #      
    print(tplt.format("  ", "    ", "  ", "  ", chr(12288)))
    if province == '  ':
        print(tplt.format(1, '          ', '  ', 99.9, chr(12288)))
    #                 ，             (    range(len(ulist))                )
    for i in range(len(ulist)):
        #                   u
        u = ulist[i]
        # u[2]   ，         （          ，       ，        ，         ）
        if u[2] == province:
            #        ，                   
            print(tplt.format(u[0], u[1], u[2], u[3], chr(12288)))


#           
def main(province='  '):
    #        ，            
    uinfo = []
    #            
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    #                   
    html = getHTMLText(url)
    #            
    fillUnivList(uinfo, html)
    #            
    printUnivList(uinfo, province=province)


main(province='  ')

知識点をまとめる:

解析Webソース

タグの内容を検索

正確な内容を再編成