python网络爬虫自学笔录6_爬取大学排行实例

这里实现一个对中国大学排行的爬虫实例解析

注意：在爬取之前需要查看robot的协议，查看是否允许爬取



这个是大学排行榜的主页面，我们需要把中国大学排名的主榜爬取下来：
直接看代码：

import requests
from bs4 import BeautifulSoup
import bs4

def 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].text, tds[1].text, tds[4].text])

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 = 'https://www.shanghairanking.cn/rankings/bcur/2020'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    #print(uinfo)
    printUnivList(uinfo, 20) # 20 univs
main()

这样我们就简单的吧大学排行榜爬取下来了，那我们如果像把结果放在文件里面呢？
这里我也把结果输出出来，写入到文件里面了~

import requests
from bs4 import BeautifulSoup
import bs4
import os


def 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].text, tds[1].text, tds[4].text])

def printUnivList(ulist, num):
    tplt = "{0:}\t{1:}\t{2:}"
    root = 'C://Users//11847//plotly//spider_web//pic//'
    path = root + '2020年中国大学排行榜.txt'
    #print(tplt.format("排名","学校名称","总分",chr(12288)))
    with open(path, 'w') as f:
        f.write(tplt.format('排名', '学校', '地区',chr(12288)))
        f.close()
    for i in range(num):
        u=ulist[i]
        #print(tplt.format(u[0],u[1],u[2],chr(12288)))
        with open(path, 'a') as f:
            f.write(tplt.format(u[0],u[1],u[2],chr(12288)))
            f.close()
    print('文件保存成功')

def main():
    uinfo = []
    url = 'https://www.shanghairanking.cn/rankings/bcur/2020'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    #print(uinfo)
    printUnivList(uinfo, 50) # 20 univs
main()

你们快去试试把~