第十三周学习博客——实训总结

爬虫

import requests
from lxml import etree
import sqlite3
import datetime



conn = sqlite3.connect('movie.db')
cursor = conn.cursor()
sql = 'insert into movie(m_id,m_name,m_img) values (:m_id,:m_name,:m_img)'

url_news = 'https://www.dy2018.com/html/tv/oumeitv/index.html'
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
           'Referer':'https://www.dy2018.com/html/tv/oumeitv/index.html'}

response = requests.get(url_news,headers=headers)
#返回网络通信状态
print(response.status_code)
#中文编码
response.encoding = 'gb2312'

scode = response.status_code

if scode == 200:
    print("start now")
    #网页的节点对象
    domroot = etree.HTML(response.text)

    # xpath 进行爬虫规格设置
    movielist = domroot.xpath('//td[@height=26]/b/a')

    # 电影的个数
    print('电影个数为：', len(movielist))

    # 循环进行遍历
    for x in movielist:
        title = x.xpath('text()')
        if title:
            title = title[0]
        else:
            continue
        print('电影名字:',title)

        # 电影标题
        url =x.xpath('@href')
        if url:
            url = url[0]
        else:
            continue
        print('电影地址: ', url)  # 电影地址

        url = "https://www.dy2018.com/" + url

        response = requests.get(url, headers=headers)
        response.encoding = 'gb2312'

        page_2 = etree.HTML(response.text)
        page_2_img_url = page_2.xpath("//div[@id='Zoom']/p[1]/img[1]/@src")

        if page_2_img_url:
            page_2_img_url = page_2_img_url[0]
        else:
            continue
        print('电影图片: ', page_2_img_url)
        time_now = datetime.datetime.now().strftime('%H:%M:%S.%f')
        cursor.execute(sql, {'m_id':time_now, 'm_name':title, 'm_img':page_2_img_url})
        conn.commit()
    conn.close()

数据结果截图

js初学

// 第一步: 82~84行
var xhr = new XMLHttpRequest(); // JS语法严格区分大小写
	xhr.open('GET', 'movie.db', true); // 标准的ajax的代码
	xhr.responseType = 'arraybuffer';

	// 定义查询数据库代码
	function queryBy(sql, t) {
		var uInt8Array = new Uint8Array(t.response);
		var db = new SQL.Database(uInt8Array);
		var content = db.exec(sql);
		return content;
	}

	// 第二步: 读取数据,进行数据渲染
	function templateHTML(content, name) {
		moviedata = content[0].values; // 数据库里面的数据
		console.log(moviedata); // 数据测试
		html = '<div class="news">';
		for (i = 0; i < moviedata.length; i++) {
			html += '<div>';
			html += '<img src="'+ moviedata[i][2] +'">';
			html += '<span>'+ moviedata[i][1] +'</span>';
			html += '</div>';
		}
		html += '</div>';
		$("body").append(html);
	}

	// 第三步: 发送SQL语句
	xhr.onload = function(e) {
		content = queryBy('select * from movie limit 5 offset 0', this);
		templateHTML(content, 'main_recommand');

		content = queryBy('select * from movie limit 5 offset 4', this);
		templateHTML(content, 'main_recommand');
	}

	// 第四步: 执行
	xhr.send();

数据库创建

成果总结