Python高级应用程序设计任务

import re
import bs4
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import requests as req
from bs4 import BeautifulSoup
import random

agent = [‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1623.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; NetBSD) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36‘, ‘Mozilla/5.0 (X11; NetBSD) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.116 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1866.237 Safari/537.36‘, ‘Mozilla/5.0 (compatible; MSIE 10.6; Windows NT 6.1; Trident/5.0; InfoPath.2; SLCC1; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729; .NET CLR 2.0.50727) 3gpp-gba UNTRUSTED/1.0‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.60 Safari/537.17‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:40.0) Gecko/20100101 Firefox/40.1‘, ‘Mozilla/5.0 (Windows NT 6.0; WOW64; rv:24.0) Gecko/20100101 Firefox/24.0‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.2 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.16 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.517 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.14 (KHTML, like Gecko) Chrome/24.0.1292.0 Safari/537.14‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET CLR 1.1.4322; .NET4.0C; Tablet PC 2.0)‘, ‘Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.60 Safari/537.17‘, ‘Mozilla/5.0 (X11; CrOS i686 4319.74.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.57 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:25.0) Gecko/20100101 Firefox/29.0‘, ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1467.0 Safari/537.36‘, ‘Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:24.0) Gecko/20100101 Firefox/24.0‘, ‘Mozilla/5.0 (Microsoft Windows NT 6.2.9200.0); rv:22.0) Gecko/20130405 Firefox/22.0‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.62 Safari/537.36‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; chromeframe/11.0.696.57)‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.517 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36‘, ‘Opera/9.80 (Windows NT 5.1; U; ) Presto/2.7.62 Version/11.01‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.17 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1667.0 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.137 Safari/4E423F‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0‘, ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/5.0)‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; chromeframe/11.0.696.57)‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1309.0 Safari/537.17‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1664.3 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36‘, ‘Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1944.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.3319.102 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/33.0.1750.517 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1464.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.2117.157 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.2117.157 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.2; Win64; x64; rv:16.0.1) Gecko/20121011 Firefox/21.0.1‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.137 Safari/4E423F‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:29.0) Gecko/20120101 Firefox/29.0‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10; rv:33.0) Gecko/20100101 Firefox/33.0‘, ‘Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1944.0 Safari/537.36‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/32.0.1664.3 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36‘, ‘Mozilla/5.0 (X11; OpenBSD i386) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.36‘, ‘Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0; FunWebProducts)‘, ‘Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.17 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.60 Safari/537.17‘, ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; Trident/6.0)‘, ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36‘, ‘Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36‘, ‘Mozilla/5.0 (Windows; U; Windows NT 6.1; fr-FR) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27‘]

# 返回网页源码的函数
def getHTMLText(url):
    try:
        # 使用requests库爬取网页源码2
        r = req.get(
            url, headers={‘user-agent‘: ‘Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36‘, "Referer": "https://www.xiami.com/billboard/332"})
        # 判断是否爬取过程中出现错误
        r.raise_for_status()
        #  设置源码的编码格式
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "爬取失败"

# 解析页面源码并组成集合返回爬取数据
def XiamiMusicList(html):
    musicList = []

    # 使用bs4库中的BeautifulSoup类解析html文本
    soup = BeautifulSoup(html, "html.parser")
    
    trs = soup.select("tbody>tr")

    # print(trs)
    for i in trs :
        top = i.select("div.index-container")[0].text
        song_id = i.select("div.song-name>a")[0].attrs["href"].split("/")[-1]
        song_name = i.find("div", "song-name").text
        song_mv_id = i.select("div.songName-container a")[-1].attrs["href"].split("/")[-1]
        singers = i.select("div.singers>a")[0].text
        album = i.select("div.album-container a")[0].text
        timesize = i.select("div.duration-container>span")[0].text
        href = i.select("div.song-name>a")[0].attrs["href"]
        temp = [top,song_id, song_name, song_mv_id, singers, album, timesize, href]
        musicList.append(temp)
    return musicList

# 数据持久化函数
def saveExcel(musicList,MusicListPath):
    # 将数据转化为DataFrame格式
    df = pd.DataFrame(musicList, columns=["top","song_id", "song_name", "song_mv_id", "singers", "album", "timesize","href"])

    # 输出excel的对象
    writer = pd.ExcelWriter(MusicListPath)
    # 将数据写入到excel表格中
    df.to_excel(writer,sheet_name="MusicList")
    # 关闭输出流
    writer.save()


def XiamiMusicListDetail(html):
    soup = BeautifulSoup(html, "html.parser")
    div0 = soup.find("div",attr = {"class":"song-name"})
    print(div0)


if __name__ == "__main__":
    # # 网站域名
    Path = "https://www.xiami.com/"
    # 榜单链接
    url = "https://www.xiami.com/billboard/103"
    html = getHTMLText(url)
    # print(html[:100000])
    musicList = XiamiMusicList(html)
    saveExcel(musicList, "MusicList.xlsx")


    df = pd.read_excel("MusicList.xlsx", sheet_name="MusicList")
    # for href in df["href"]:
    #     url = Path + href
    #     html = getHTMLText(url)
    # html = getHTMLText("https://www.xiami.com/artist/nnArZF4f128")

    # XiamiMusicListDetail(html)