网络爬虫简单入门--数据抓取-数据解析-数据显示-数据入库-B

代码1:

a=[3.45,4.45,5]
b=[5,4]
c=["aa",456,True]
myList=[]
myList.append(a)
myList.append(b)
myList.append(c)
print(myList)

代码2:

#coding=utf-8
list=[]
for i in range(1,101):
    list.append(i)

# print(list)

tempList=[]
newList=[]

while True:
    num=0
    for temp in list:
        tempList.append(temp)
        num+=1
        if num==3:
            newList.append(tempList)
            tempList=[]
            num=0
            continue
    if temp==100:
        newList.append(tempList)
        break

print(newList)

代码3：

import requests
from bs4 import BeautifulSoup
allUniv = []
def getHTMLText(url):
    try:
        r = requests.get(url, timeout=30)
        r.raise_for_status()
        r.encoding = 'utf-8'
        return r.text
    except:
        return ""
def fillUnivList(soup):
    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):
    print("{:^4}{:^10}{:^5}{:^8}{:^10}".format("排名","学校名称","省市","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():
    url = 'http://www.zuihaodaxue.cn/zuihaodaxuepaiming2016.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    fillUnivList(soup)
    printUnivList(10)
main()

 

课后作业:

1.复制上述代码,在Python环境下运行。

2.读懂上述代码。