爬虫实战案例1：中国大学排名定向爬虫(完整代码)

1.爬取结果

1.1主界面

1.2总榜

1.3医药类

1.4财经类

1.5语言类

1.6政法类

1.7民族类

1.8体育类

1.9艺术类

1.10合作办学

1.11独立学院

1.12民办高校

2.代码图片

4.完整代码(可复制)

import requests
from bs4 import BeautifulSoup
import bs4

def GetHTMLText(Univer_RANK_Url):
    '''获取某类高校页面HTML代码'''
    try:
        r = requests.get(Univer_RANK_Url, timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text                  # r.text作为html返回
    except:
        return '异常'

def fillUnivList(ulist, html, user):

    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children:
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')
            if user == '0': ## 总榜
                ulist.append([tds[0].string, tds[1].string, tds[2].string, tds[4].string])
            elif user == '7': ## 艺术
                ulist.append([tds[0].string, tds[1].string, tds[5].string, tds[6].string])
            elif user == '9' or user == '10':## 民办or独立
                ulist.append([tds[0].string, tds[1].string, tds[2].string, tds[3].string])
            else: ## 1~6 and 8
                ulist.append([tds[0].string, tds[1].string, tds[2].string, tds[3].string, tds[4].string])
def printUnivList(ulist, num, user):

    #print("{:^10}\t{:^6}\t{:^6}\t{:^10}".format("排名", "学校名称", "所在地", "总分"))

    if user == '0' or user == '9' or user == '10': #zongbang总榜
        print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}".format("排名", "学校名称", "所在地", "总分", chr(12288)))
        for i in range(num):
            try:
                u = ulist[i]
                if u[3] is None:
                    u[3] = '位次相同'
                #print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]), u[3])
                print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}".format(u[0], u[1], u[2], u[3], chr(12288)))
            except:
                pass
            continue
    elif user == '7': ## yishu艺术
        #try:
            print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}".format("学校名称", "所在地", "就业率", "深造率", chr(12288)))
            for i in range(num):
                try:
                    u = ulist[i]
                    if u[3] is None or u[2] is None:
                        u[2] = ' '
                        u[3] = ' '
                    # print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]), u[3])
                    print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}".format(u[0], u[1], u[2], u[3], chr(12288)))
                except TypeError:
                    pass
                continue
    else: #1-6 8
        print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}".format("排名", "全国排名", "学校名称", "所在地", "总分", chr(12288)))
        for i in range(num):
            #try:
                u = ulist[i]
                if u[4] is None:
                    u[4] = ' '
                # print("{:^10}\t{:^6}\t{:^10}".format(u[0], u[1], u[2]), u[3])
                print("{0:^20}\t{1:^20}\t{2:^20}\t{3:^20}\t{4:^20}".format(u[0], u[1], u[2], u[3], u[4], chr(12288)))
            #except:
             #   pass
            #continue

def get_Rank_Url():
    ''''''
    try:
        r = requests.get("http://zuihaodaxue.com/rankings.html", timeout = 30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        html = r.text
        soup = BeautifulSoup(html, 'html.parser')
        html1 = soup.find_all('div', 'smallpic')
        #print(soup.find_all('a'))
        univRankUrl = []
        univType = []
        for urltag in soup.find_all('a'):
            univRankUrl.append(urltag.attrs['href'])
        #print(univRankUrl[15:26:1])
        for nametag in soup.find_all('span'):
            univType.append(nametag)
        #print(univType[7:18:1])
        return univType,univRankUrl
    except:
        return "访问异常"
        
def welcome_screen(univType):
    ''''''
    print('欢迎使用全国大学排名查询脚本！')
    print('请输入对应数字查询：')
    print('0 .' + str(univType[17]).rstrip("").lstrip(""))
    print('1 .' + str(univType[7]).rstrip("").lstrip(""))
    print('2 .' + str(univType[8]).rstrip("").lstrip(""))
    print('3 .' + str(univType[9]).rstrip("").lstrip(""))
    print('4 .' + str(univType[10]).rstrip("").lstrip(""))
    print('5 .' + str(univType[11]).rstrip("").lstrip(""))
    print('6 .' + str(univType[12]).rstrip("").lstrip(""))
    print('7 .' + str(univType[13]).rstrip("").lstrip(""))
    print('8 .' + str(univType[14]).rstrip("").lstrip(""))
    print('9 .' + str(univType[15]).rstrip("").lstrip(""))
    print('10.' + str(univType[16]).rstrip("").lstrip(""))

def getUserDecision(univRankUrl):
    
    url = 'http://zuihaodaxue.com/'
    user = input('请输入序号(输入q退出)：')
    if user == '0':
        return url + univRankUrl[25], user
    elif user == '1':
        return url + univRankUrl[15], user
    elif user == '2':
        return url + univRankUrl[16], user
    elif user == '3':
        return url + univRankUrl[17], user
    elif user == '4':
        return url + univRankUrl[18], user
    elif user == '5':
        return url + univRankUrl[19], user
    elif user == '6':
        return url + univRankUrl[20], user
    elif user == '7':
        return url + univRankUrl[21], user
    elif user == '8':
        return url + univRankUrl[22], user
    elif user == '9':
        return url + univRankUrl[23], user
    elif user == '10':
        return url + univRankUrl[24], user
    elif user == 'q':
        pass
    else:
        print('输入有误')

def main():
    ''''''
    uinfo = []
    univType, univRankUrl = get_Rank_Url()
    welcome_screen(univType)
    Univer_RANK_Url,user = getUserDecision(univRankUrl)
    print("本次获取信息的链接："+ Univer_RANK_Url)
    html = GetHTMLText( Univer_RANK_Url)
    fillUnivList(uinfo, html, user)
    print("共计" + str(len(uinfo)) + "所高校")
    printUnivList(uinfo, len(uinfo),user)
main()