第一次数据库学习

 

Python数据库的学习笔记

SQLite是一个软件库

下面简单介绍一下有关SQLite库的函数

 

1	SQLite COUNT 函数 SQLite COUNT 聚集函数是用来计算一个数据库表中的行数。
2	SQLite MAX 函数 SQLite MAX 聚合函数允许我们选择某列的最大值。
3	SQLite MIN 函数 SQLite MIN 聚合函数允许我们选择某列的最小值。
4	SQLite AVG 函数 SQLite AVG 聚合函数计算某列的平均值。
5	SQLite SUM 函数 SQLite SUM 聚合函数允许为一个数值列计算总和。
6	SQLite RANDOM 函数 SQLite RANDOM 函数返回一个介于 -9223372036854775808 和 +9223372036854775807 之间的伪随机整数。
7	SQLite ABS 函数 SQLite ABS 函数返回数值参数的绝对值。
8	SQLite UPPER 函数 SQLite UPPER 函数把字符串转换为大写字母。
9	SQLite LOWER 函数 SQLite LOWER 函数把字符串转换为小写字母。
10	SQLite LENGTH 函数 SQLite LENGTH 函数返回字符串的长度。
11	SQLite sqlite_version 函数 SQLite sqlite_version 函数返回 SQLite 库的版本。

承接上次用爬虫获取中国大学排名

代码如下

# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""
import requests
import pandas as pd
import numpy as np
from bs4 import BeautifulSoup
import sqlite3
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):
    with open(r'C:\Users\DELL\Desktop\test.txt','w') as f:
        f.write("{1:^2}{2:{0}^10}{3:{0}^4}{4:{0}^8}{5:{0}^6}\n".format((chr(12288)),"排名","学校名称","省市","总分","培训规模"))
        for i in range(num):
            u=allUniv[i]
            f.write("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}\n".format((chr(12288)),u[0],u[1],u[2],eval(u[3]),u[6]))
        f.close()
    if 1:
        print("successful")
    else:
        print("fail")

def main(num):
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)

main(600)

 

查询我们自己学校的代码为

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):
    a="广东技术师范学院"
    print("{1:^4}{2:{0}^8}{3:{0}^6}{4:{0}^6}{5:{0}^8}".format((chr(12288)),"排名","学校名称","省市","总分","培训规模"))
    for i in range(num):
        u=allUniv[i]
        if a in u:
            print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}".format((chr(12288)),u[0],u[1],u[2],eval(u[3]),u[6]))
def main(num):
    url='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2018.html'
    html = getHTMLText(url)
    soup = BeautifulSoup(html,"html.parser")
    fillUnivList(soup)
    printUnivList(num)
main(600)

 

接着再经过以下代码就可以获得以为科研质量标准的广东大学排名

def printUnivList(num):
    a="广东技术师范学院"
    print("{1:^4}{2:{0}^8}{3:{0}^6}{4:{0}^6}{5:{0}^8}".format((chr(12288)),"排名","学校名称","省市","总分","培训规模"))
    for i in range(num):
        u=allUniv[i]
        if a in u:
            print("{1:^4}{2:{0}^10}{3:{0}^5}{4:{0}^8.1f}{5:{0}^10}".format((chr(12288)),u[0],u[1],u[2],eval(u[3]),u[6]))