zoukankan      html  css  js  c++  java
  • Python-爬取b站的热门视频并导入Excel中

    #encoding:utf-8
    import requests
    from lxml import etree
    import xlwt
    import os
    
    # 爬取b站热门视频信息
    def spider():
        video_list = []
        url = "https://www.bilibili.com/ranking?spm_id_from=333.851.b_7072696d61727950616765546162.3"
        html = requests.get(url, headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36"}).text
        html = etree.HTML(html)
        infolist = html.xpath("//li[@class='rank-item']")
        for item in infolist:
            rank = "".join(item.xpath("./div[@class='num']/text()"))
            video_link = "".join(item.xpath(".//div[@class='info']/a/@href"))
            title = "".join(item.xpath(".//div[@class='info']/a/text()"))
            payinfo = "".join(item.xpath(".//div[@class='detail']/span/text()")).split("万")
            play = payinfo[0] + "万"
            comment = payinfo[1]
            if comment.isdigit() == False:
                comment += "万"
            upname = "".join(item.xpath(".//div[@class='detail']/a/span/text()"))
            uplink = "http://" + "".join(item.xpath(".//div[@class='detail']/a/@href"))
            hot = "".join(item.xpath(".//div[@class='pts']/div/text()"))
            video_list.append({
                'rank': rank,
                'videolink': video_link,
                'title': title,
                'play': play,
                'comment': comment,
                'upname': upname,
                'uplink': uplink,
                'hot': hot
            })
        return video_list
    
    
    def write_Excel():
        # 将爬取的信息添加到Excel
        video_list = spider()
        workbook = xlwt.Workbook()  # 定义表格
        sheet = workbook.add_sheet("b站热门视频")   # 添加sheet的name
        xstyle = xlwt.XFStyle()   # 实例化表格样式对象
        xstyle.alignment.horz = 0x02  # 字体居中
        xstyle.alignment.vert = 0x01
        head = ['视频名', 'up主','排名', '热度','播放量','评论数']
        for h in range(len(head)):
            sheet.write(0, h, head[h], xstyle)
        i = 1
        for item in video_list:
            # 向单元格(视频名)添加该视频的超链接
            if '"' in item["title"]:
                item["title"] = item["title"].split('"')[1]
            title_data = 'HYPERLINK("'+item["videolink"]+'";"'+item["title"]+'")'    # 设置超链接
            sheet.col(0).width = int(256 * len(title_data) * 3/5)    # 设置列宽
            sheet.write(i, 0, xlwt.Formula(title_data), xstyle)
            name_data = 'HYPERLINK("'+item["uplink"]+'";"'+item["upname"]+'")'
            sheet.col(1).width = int(256 * len(name_data) * 3/5)
            sheet.write(i, 1, xlwt.Formula(name_data), xstyle)
            sheet.write(i, 2, item["rank"], xstyle)
            sheet.write(i, 3, item["hot"], xstyle)
            sheet.write(i, 4, item["play"], xstyle)
            sheet.write(i, 5, item["comment"], xstyle)
            i += 1
        # 如果文件存在,则将其删除
        file = "b站热门视频信息.xls"
        if os.path.exists(file):
            os.remove(file)
        workbook.save(file)
    
    if __name__ == '__main__':
        write_Excel()
    

     结果展示:

  • 相关阅读:
    正则表达式入门
    Tyvj 1518 CPU监控——极恶线段树
    数据结构-元组
    洛谷P3195 玩具装箱TOY
    数据结构-列表基本语法
    P2569 股票交易
    列表循环
    P3507 GRA-The Minima Game
    数据结构-集合
    洛谷P1595 信封问题
  • 原文地址:https://www.cnblogs.com/zhouzetian/p/12613930.html
Copyright © 2011-2022 走看看