Python网络爬虫

 一、访问网站20次

import requests
from bs4 import BeautifulSoup#调用函数
r = requests.get("http://www.baidu.com")#输入网站名字
r.encoding = "utf-8"
soup = BeautifulSoup(r.text)

for i in range(20):#控制循环，访问网站20次即可。
    print(soup.head)
    print("\n")
    print(i+1)
    print("\n")

通过用for循环，来控制访问次数，效果如下：

 

 二、爬虫

 

 

import requests
from bs4 import BeautifulSoup
alluniv = []
def getHTMLText(url):#访问网站并获取内容
    try:
        r = requests.get(url,timeout = 30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return "error"
def fillunivlist(soup):#获取我们需要的内容
    data=soup.find_all('tr')
    for tr in data:
        ltd =tr.find_all('td')
        if len(ltd)==0:
            continue
        singleuniv=[]
        for td in ltd:
            singleuniv.append(td.string)
        alluniv.append(singleuniv)
def printunivlist(num):#建立这个排名表格
    print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名字","省份","总分","培养规模"))
    for i in range(num):
        u=alluniv[i]
        print("{:^4}{:^10}{:^5}{:^8}{:^10}".format(u[0],u[1],u[2],u[3],u[6]))
def main(num):#输出num个数的大学排名
    url = "http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html"
    html=getHTMLText(url)
    soup=BeautifulSoup(html,"html.parser")
    fillunivlist(soup)
    printunivlist(num)
main(100)

 效果如下：