ADD file via upload

播放量和评论数——蒋曙昭.ipynb

@@ -0,0 +1,164 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a5582a5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "import pandas\n",
+    "import requests\n",
+    "from bs4 import BeautifulSoup\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib import font_manager\n",
+    "\n",
+    "\n",
+    "def get_html(url):\n",
+    "    try:\n",
+    "        r = requests.get(url)  # 使用get来获取网页数据\n",
+    "        r.raise_for_status()  # 如果返回参数不为200，抛出异常\n",
+    "        r.encoding = r.apparent_encoding  # 获取网页编码方式\n",
+    "        return r.text  # 返回获取的内容\n",
+    "    except:\n",
+    "        return '错误'\n",
+    "\n",
+    "\n",
+    "def save(html):\n",
+    "    # 解析网页\n",
+    "    soup = BeautifulSoup(html, 'html.parser')  # 指定Beautiful的解析器为“html.parser”\n",
+    "\n",
+    "    with open('1.txt', 'r+', encoding='UTF-8') as f:\n",
+    "        f.write(soup.text)\n",
+    "\n",
+    "    # 定义好相关列表准备存储相关信息\n",
+    "    TScore = []  # 综合评分\n",
+    "    name = []  # 动漫名字\n",
+    "    bfl = []  # 播放量\n",
+    "    pls = []  # 评论数\n",
+    "    scs = []  # 收藏数\n",
+    "\n",
+    "    # ********************************************  动漫名字存储\n",
+    "    for tag in soup.find_all('div', class_='info'):\n",
+    "        # print(tag)\n",
+    "        bf = tag.a.string\n",
+    "        name.append(str(bf))\n",
+    "    print(name)\n",
+    "\n",
+    "    # ********************************************  播放量存储\n",
+    "    for tag in soup.find_all('div', class_='detail'):\n",
+    "        # print(tag)\n",
+    "        bf = tag.find('span', class_='data-box').get_text()\n",
+    "        # 统一单位为‘万’\n",
+    "        if '亿' in bf:\n",
+    "            num = float(re.search(r'\\d(.\\d)?', bf).group()) * 10000\n",
+    "            # print(num)\n",
+    "            bf = num\n",
+    "        else:\n",
+    "            bf = re.search(r'\\d*(\\.)?\\d', bf).group()\n",
+    "        bfl.append(float(bf))\n",
+    "    print(bfl)\n",
+    "    # ********************************************  评论数存储\n",
+    "    for tag in soup.find_all('div', class_='detail'):\n",
+    "        # pl = tag.span.next_sibling.next_sibling\n",
+    "        pl = tag.find('span', class_='data-box').next_sibling.next_sibling.get_text()\n",
+    "        # *********统一单位\n",
+    "        if '万' not in pl:\n",
+    "            pl = '%.1f' % (float(pl) / 10000)\n",
+    "            # print(123, pl)\n",
+    "        else:\n",
+    "            pl = re.search(r'\\d*(\\.)?\\d', pl).group()\n",
+    "        pls.append(float(pl))\n",
+    "    print(pls)\n",
+    "    # ********************************************  收藏数\n",
+    "    for tag in soup.find_all('div', class_='detail'):\n",
+    "        sc = tag.find('span', class_='data-box').next_sibling.next_sibling.next_sibling.next_sibling.get_text()\n",
+    "        sc = re.search(r'\\d*(\\.)?\\d', sc).group()\n",
+    "        scs.append(float(sc))\n",
+    "    print(scs)\n",
+    "    # ********************************************  综合评分\n",
+    "    for tag in soup.find_all('div', class_='pts'):\n",
+    "        zh = tag.find('div').get_text()\n",
+    "        TScore.append(int(zh))\n",
+    "    print('综合评分', TScore)\n",
+    "\n",
+    "    # 存储至excel表格中\n",
+    "    info = {'动漫名': name, '播放量(万)': bfl, '评论数(万)': pls, '收藏数(万)': scs, '综合评分': TScore}\n",
+    "    dm_file = pandas.DataFrame(info)\n",
+    "    dm_file.to_excel('Dongman.xlsx', sheet_name=\"动漫数据分析\")\n",
+    "    # 将所有列表返回\n",
+    "    return name, bfl, pls, scs, TScore\n",
+    "\n",
+    "\n",
+    "def view(info):\n",
+    "    my_font = font_manager.FontProperties(fname='./data/STHeiti Medium.ttc')  # 设置中文字体（图标中能显示中文）\n",
+    "    dm_name = info[0]  # 番剧名\n",
+    "    dm_play = info[1]  # 番剧播放量\n",
+    "    dm_review = info[2]  # 番剧评论数\n",
+    "    dm_favorite = info[3]  # 番剧收藏数\n",
+    "    dm_com_score = info[4]  # 番剧综合评分\n",
+    "    # print(dm_com_score)\n",
+    "\n",
+    "    # 为了坐标轴上能显示中文\n",
+    "    plt.rcParams['font.sans-serif'] = ['SimHei']\n",
+    "    plt.rcParams['axes.unicode_minus'] = False\n",
+    "\n",
+    "    # **********************************************************************综合评分和播放量对比\n",
+    "    # *******综合评分条形图\n",
+    "    fig, ax1 = plt.subplots()\n",
+    "    plt.bar(dm_name, dm_com_score, color='red')  #设置柱状图\n",
+    "    plt.title('综合评分和播放量数据分析', fontproperties=my_font)  # 表标题\n",
+    "    ax1.tick_params(labelsize=6)\n",
+    "    plt.xlabel('番剧名')  # 横轴名\n",
+    "    plt.ylabel('综合评分')  # 纵轴名\n",
+    "    plt.xticks(rotation=90, color='green')  # 设置横坐标变量名旋转度数和颜色\n",
+    "\n",
+    "    # *******播放量折y\n",
+    "    ax2 = ax1.twinx()  # 组合图必须加这个\n",
+    "    ax2.plot(dm_play, color='cyan')  # 设置线粗细，节点样式\n",
+    "    plt.ylabel('播放量')  # y轴\n",
+    "\n",
+    "    plt.plot(1, label='综合评分', color=\"red\", linewidth=5.0)  # 图例\n",
+    "    plt.plot(1, label='播放量', color=\"cyan\", linewidth=1.0, linestyle=\"-\")  # 图例\n",
+    "    plt.legend()\n",
+    "\n",
+    "    plt.savefig(r'E:1.png', dpi=1000, bbox_inches='tight')  #保存至本地\n",
+    "\n",
+    "    # plt.show()\n",
+    "\n",
+    "def main():\n",
+    "    url = 'https://www.bilibili.com/v/popular/rank/bangumi'  # 网址\n",
+    "    html = get_html(url)  # 获取返回值\n",
+    "    # print(html)\n",
+    "    info = save(html)\n",
+    "    view(info)\n",
+    "\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    main()\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}