ADD file via upload

comment_top_10.py

@@ -4,9 +4,9 @@ import matplotlib.pyplot as plt
 import time
 
 
-def data_visualization_of_top_10_of_ea_song_comment():
+def image_comment_top_10():
     """网易云音乐欧美歌单评论 TOP10"""
-    df = pd.read_csv('./music_data/music_detail.csv', header=None)
+    df = pd.read_csv('./data/detail.csv', header=None)
 
     print("正在生成网易云音乐欧美歌单评论 TOP10 图片...")
 
@@ -62,17 +62,17 @@ def data_visualization_of_top_10_of_ea_song_comment():
     lines.yaxis.set_ticks_position('none')
 
     # 绘制柱状图,设置柱状图颜色
-    data.plot.barh(ax=ax, width=0.7, alpha=0.7, color=(160/255, 102/255, 50/255))
-    ax.set_title('网易云音乐欧美歌单评论 TOP10', fontsize=18, fontweight='light')
+    data.plot.barh(ax=ax, width=0.7, alpha=0.7, color=(10/255, 70/255, 100/255))
+    ax.set_title('**【网易云音乐欧美歌单评论 TOP10】**', fontsize=18, fontweight='light')
 
     # 添加歌单评论数量文本
     for x, y in enumerate(data.values):
-        plt.text(y+200, x-0.08, '%s' % y, ha='center')
+        plt.text(y+200, x-0.08, '%s' % y, ha='left')
 
     # 保存图片
-    plt.savefig('./music_image/top_10_of_ea_song_comment.png', dpi=None)
+    plt.savefig('./image/comment_top_10.png', dpi=None)
 
     # 显示图片
     plt.show()
 
-    print("\n已生成网易云音乐欧美歌单评论 TOP10 图片，保存至 music_image/top_10_of_ea_song_comment.png")
+    print("\n已生成网易云音乐欧美歌单评论 TOP10 图片，保存至 image/comment_top_10.png")

data_analysis.py

@@ -1,16 +1,9 @@
 import os
 
-#from music_index import get_data_of_music_list_index_page
-#from music_detail import get_data_of_music_list_detail_page
-#from top_10_song import data_visualization_of_top_10_song
-# from top_10_song_up import data_visualization_of_top_10_song_up
-from top_10_ea_song_playlists import data_visualization_of_top_10_ea_song_playlists
-#from top_10_of_ea_song_collection import data_visualization_of_top_10_of_ea_song_collection
-from top_10_of_ea_song_comment import data_visualization_of_top_10_of_ea_song_comment
-#from top_10_ea_song_collection_distribution import data_visualization_of_top_10_ea_song_collection_distribution
-#from top_10_ea_song_playlists_distribution import data_visualization_of_top_10_ea_song_playlists_distribution
-from label_ea_song import data_visualization_of_label_ea_song
-from music_wordcloud import data_visualization_of_music_wordcloud
+from playlists_top_10 import image_playlists_top_10
+from comment_top_10 import image_comment_top_10
+from label import image_label
+from lable_wordcloud import image_wordcloud
 
 
 def menu():
@@ -36,23 +29,23 @@ def key_down():
         exit(0)
     elif option == 'a' or option == 'A':
         # 生成网易云音乐欧美歌单播放 TOP10 图片
-        data_visualization_of_top_10_ea_song_playlists()
+        image_playlists_top_10()
 
         return
     elif option == 'b' or option == 'B':
         # 生成网易云音乐欧美歌单评论 TOP10 图片
-        data_visualization_of_top_10_of_ea_sBong_comment()
+        image_comment_top_10()
 
         return
 
     elif option == 'c' or option == 'C':
         # 生成网易云音乐欧美歌单标签图片
-        data_visualization_of_label_ea_song()
+        image_label()
 
         return
     elif option == 'd' or option == 'D':
         # 生成歌单介绍词云图片
-        data_visualization_of_music_wordcloud()
+        image_wordcloud()
 
         return
     else:

label.py

@@ -5,9 +5,9 @@ import matplotlib.pyplot as plt
 import time
 
 
-def data_visualization_of_label_ea_song():
+def image_label():
     """网易云音乐欧美歌单标签图"""
-    df = pd.read_csv('./music_data/music_detail.csv', header=None)
+    df = pd.read_csv('./data/detail.csv', header=None)
 
     print("正在生成网易云音乐欧美歌单标签图片...")
 
@@ -60,8 +60,8 @@ def data_visualization_of_label_ea_song():
     income = df1['num'][:10]
 
     # 绘图 details
-    colors = ['#993333', '#CC9966', '#333333', '#663366', '#003366', '#009966', '#FF6600', '#FF0033', '#009999',
-              '#333366']
+    colors = ['#EB3324', '#F08784', '#7E84F7', '#732BF5','#367E7F',  '#7F82BB','#75FA8D' ,
+              '#3282F6', '#16417C', '#808080']#各个标签的RGB色彩
     plot = squarify.plot(sizes=income, label=name, color=colors, alpha=1, value=income, edgecolor='white',
                          linewidth=1.5)
 
@@ -71,10 +71,10 @@ def data_visualization_of_label_ea_song():
     plt.rcParams['axes.unicode_minus'] = False
 
     # 设置标签大小为 1
-    plt.rc('font', size=6)
+    plt.rc('font', size=8)
 
     # 设置标题大小
-    plot.set_title('网易云音乐欧美歌单标签图', fontsize=13, fontweight='light')
+    plot.set_title('**【网易云音乐欧美歌单标签图】**', fontsize=15, fontweight='light')
 
     # 除坐标轴
     plt.axis('off')
@@ -83,12 +83,12 @@ def data_visualization_of_label_ea_song():
     plt.tick_params(top=False, right=False)
 
     # 保存图片
-    plt.savefig('./music_image/label_ea_song.png', dpi=None)
+    plt.savefig('./image/label.png', dpi=None)
 
     # 显示图片
     plt.show()
 
-    print("\n已生成网易云音乐欧美歌单标签图片，保存至 music_image/label_ea_song.png")
+    print("\n已生成网易云音乐欧美歌单标签图片，保存至 image/label.png")
 
 
 

lable_wordcloud.py

@@ -6,9 +6,9 @@ import jieba
 import time
 
 
-def data_visualization_of_music_wordcloud():
+def image_wordcloud():
     """歌单介绍词云图"""
-    df = pd.read_csv('./music_data/music_detail.csv', header=None)
+    df = pd.read_csv('./data/detail.csv', header=None)
     text = ''
 
     print("正在生成歌单介绍词云图片...")
@@ -30,7 +30,7 @@ def data_visualization_of_music_wordcloud():
     for line in df[2]:
         text += ' '.join(jieba.cut(line, cut_all=False))
 
-    background_image = plt.imread('./music_image/background_image.jpg')
+    background_image = plt.imread('./image/background_image.jpg')
 
     stopwords = set('')
     stopwords.update(
@@ -63,10 +63,10 @@ def data_visualization_of_music_wordcloud():
     plt.axis('off')
 
     # 保存图片
-    wc.to_file("./music_image/music_wordcloud.png")
+    wc.to_file("./image/music_wordcloud.png")
 
     # 显示图片
     plt.show()
 
-    print("\n已生成歌单介绍词云图片，保存至 music_image/music_wordcloud.png")
+    print("\n已生成歌单介绍词云图片，保存至 image/music_wordcloud.png")
 

musicListdemo/musicListdemo/items.py

@@ -0,0 +1,12 @@
+# Define here the models for your scraped items
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/items.html
+
+import scrapy
+
+
+class MusiclistdemoItem(scrapy.Item):
+    # define the fields for your item here like:
+    # name = scrapy.Field()
+    pass

musicListdemo/musicListdemo/middlewares.py

@@ -0,0 +1,103 @@
+# Define here the models for your spider middleware
+#
+# See documentation in:
+# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
+
+from scrapy import signals
+
+# useful for handling different item types with a single interface
+from itemadapter import is_item, ItemAdapter
+
+
+class MusiclistdemoSpiderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the spider middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_spider_input(self, response, spider):
+        # Called for each response that goes through the spider
+        # middleware and into the spider.
+
+        # Should return None or raise an exception.
+        return None
+
+    def process_spider_output(self, response, result, spider):
+        # Called with the results returned from the Spider, after
+        # it has processed the response.
+
+        # Must return an iterable of Request, or item objects.
+        for i in result:
+            yield i
+
+    def process_spider_exception(self, response, exception, spider):
+        # Called when a spider or process_spider_input() method
+        # (from other spider middleware) raises an exception.
+
+        # Should return either None or an iterable of Request or item objects.
+        pass
+
+    def process_start_requests(self, start_requests, spider):
+        # Called with the start requests of the spider, and works
+        # similarly to the process_spider_output() method, except
+        # that it doesn’t have a response associated.
+
+        # Must return only requests (not items).
+        for r in start_requests:
+            yield r
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)
+
+
+class MusiclistdemoDownloaderMiddleware:
+    # Not all methods need to be defined. If a method is not defined,
+    # scrapy acts as if the downloader middleware does not modify the
+    # passed objects.
+
+    @classmethod
+    def from_crawler(cls, crawler):
+        # This method is used by Scrapy to create your spiders.
+        s = cls()
+        crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
+        return s
+
+    def process_request(self, request, spider):
+        # Called for each request that goes through the downloader
+        # middleware.
+
+        # Must either:
+        # - return None: continue processing this request
+        # - or return a Response object
+        # - or return a Request object
+        # - or raise IgnoreRequest: process_exception() methods of
+        #   installed downloader middleware will be called
+        return None
+
+    def process_response(self, request, response, spider):
+        # Called with the response returned from the downloader.
+
+        # Must either;
+        # - return a Response object
+        # - return a Request object
+        # - or raise IgnoreRequest
+        return response
+
+    def process_exception(self, request, exception, spider):
+        # Called when a download handler or a process_request()
+        # (from other downloader middleware) raises an exception.
+
+        # Must either:
+        # - return None: continue processing this exception
+        # - return a Response object: stops process_exception() chain
+        # - return a Request object: stops process_exception() chain
+        pass
+
+    def spider_opened(self, spider):
+        spider.logger.info("Spider opened: %s" % spider.name)

musicListdemo/musicListdemo/pipelines.py

@@ -0,0 +1,28 @@
+# -*- coding: utf-8 -*-
+
+# Define your item pipelines here
+#
+# Don't forget to add your pipeline to the ITEM_PIPELINES setting
+# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html
+
+
+class musicListdemoPipeline(object):
+    def process_item(self, item, spider):
+        return item
+
+
+class musicListdemoInfoPipeline(object):
+    def open_spider(self, spider):
+        self.f = open('musicListdemoInfo.txt', 'w')
+
+    def close_spider(self, spider):
+        self.f.close()
+
+    def process_item(self, item, spider):
+        try:
+            line = str(dict(item)) + '\n'
+            self.f.write(line)
+        except:
+            pass
+        return item
+

musicListdemo/musicListdemo/settings.py

@@ -0,0 +1,90 @@
+# -*- coding: utf-8 -*-
+
+# Scrapy settings for BaiduStocks project
+#
+# For simplicity, this file contains only settings considered important or
+# commonly used. You can find more settings consulting the documentation:
+#
+#     http://doc.scrapy.org/en/latest/topics/settings.html
+#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+
+BOT_NAME = 'musicListdemo'
+
+SPIDER_MODULES = ['musicListdemo.spiders']
+NEWSPIDER_MODULE = 'musicListdemo.spiders'
+
+
+# Crawl responsibly by identifying yourself (and your website) on the user-agent
+#USER_AGENT = 'BaiduStocks (+http://www.yourdomain.com)'
+
+# Obey robots.txt rules
+ROBOTSTXT_OBEY = True
+
+# Configure maximum concurrent requests performed by Scrapy (default: 16)
+#CONCURRENT_REQUESTS = 32
+
+# Configure a delay for requests for the same website (default: 0)
+# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
+# See also autothrottle settings and docs
+#DOWNLOAD_DELAY = 3
+# The download delay setting will honor only one of:
+#CONCURRENT_REQUESTS_PER_DOMAIN = 16
+#CONCURRENT_REQUESTS_PER_IP = 16
+
+# Disable cookies (enabled by default)
+#COOKIES_ENABLED = False
+
+# Disable Telnet Console (enabled by default)
+#TELNETCONSOLE_ENABLED = False
+
+# Override the default request headers:
+#DEFAULT_REQUEST_HEADERS = {
+#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+#   'Accept-Language': 'en',
+#}
+
+# Enable or disable spider middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
+#SPIDER_MIDDLEWARES = {
+#    'BaiduStocks.middlewares.BaidustocksSpiderMiddleware': 543,
+#}
+
+# Enable or disable downloader middlewares
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
+#DOWNLOADER_MIDDLEWARES = {
+#    'BaiduStocks.middlewares.MyCustomDownloaderMiddleware': 543,
+#}
+
+# Enable or disable extensions
+# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
+#EXTENSIONS = {
+#    'scrapy.extensions.telnet.TelnetConsole': None,
+#}
+
+# Configure item pipelines
+# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
+ITEM_PIPELINES = {
+    'musicListdemo.pipelines.musicListdemoInfoPipeline': 300,
+}
+
+# Enable and configure the AutoThrottle extension (disabled by default)
+# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
+#AUTOTHROTTLE_ENABLED = True
+# The initial download delay
+#AUTOTHROTTLE_START_DELAY = 5
+# The maximum download delay to be set in case of high latencies
+#AUTOTHROTTLE_MAX_DELAY = 60
+# The average number of requests Scrapy should be sending in parallel to
+# each remote server
+#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
+# Enable showing throttling stats for every response received:
+#AUTOTHROTTLE_DEBUG = False
+
+# Enable and configure HTTP caching (disabled by default)
+# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
+#HTTPCACHE_ENABLED = True
+#HTTPCACHE_EXPIRATION_SECS = 0
+#HTTPCACHE_DIR = 'httpcache'
+#HTTPCACHE_IGNORE_HTTP_CODES = []
+#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

musicListdemo/musicListdemo/spiders/__init__.py

@@ -0,0 +1,4 @@
+# This package will contain the spiders of your Scrapy project
+#
+# Please refer to the documentation for information on how to create and manage
+# your spiders.

musicListdemo/musicListdemo/spiders/music_detail.py

@@ -0,0 +1,75 @@
+import scrapy
+import pandas as pd
+# music_detail.py
+
+
+INDEX = "C:\\Users\\aaa\\Desktop\\spiders163\\data\\url.csv"
+DETAIL = "C:\\Users\\aaa\\Desktop\\spiders163\\data\\detail.csv"
+#scrapy crawl music_index
+
+class MusicIndexSpider(scrapy.Spider):
+    name = "music_detail"
+
+    redis_key = 'music_detail'
+
+    def start_requests(self):
+        df = pd.read_csv(INDEX, header=None, names=['url', 'title', 'play','user'])
+
+        headers_chrome = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
+                          'Chrome/120.0.0.0 Safari/537.36'
+        }
+
+        for i in df['url']:
+            url = 'https://music.163.com' + i
+            yield scrapy.Request(url, headers=headers_chrome)
+
+    def parse(self, response):
+
+        # 获取歌单标题
+        title = response.css('h2::text')[0].get().replace(',', ' ')
+
+        # 获取标签
+        tags = []
+        tags_message = response.css('.u-tag i::text')
+
+        for p in tags_message:
+            tags.append(p.get())
+
+        # 对标签进行格式化
+        if len(tags) > 1:
+            tag = '-'.join(tags)
+        elif len(tags):
+            tag = tags[0]
+        else:
+            tag = '无'
+
+        # 获取歌单介绍
+        if response.css('#album-desc-more::text'):
+            text = response.css('#album-desc-more::text')[0].get().replace('\n', '').replace(',', ' ')
+        else:
+            text = '无'
+
+        # 获取歌单收藏量
+        collection = response.css('#content-operation i::text')[1].get().replace('(', '').replace(')', '')
+
+        # 歌单播放量
+        play = response.css('.s-fc6::text')[0].get()
+
+        # 歌单内歌曲数
+        songs = response.css('#playlist-track-count::text')[0].get()
+
+        # 歌单评论数
+        comments = response.css('#cnt_comment_count::text')[0].get()
+
+        # 输出歌单详情页信息
+        print('\r', title, tag, text, collection, play, songs, comments, end='', flush=True)
+
+        # # 输出歌单详情页信息
+        print('\r', title, text, collection, play, songs, comments, end='', flush=True)
+
+        # 将详情页信息写入CSV文件中
+        with open(DETAIL, 'a+', encoding='utf-8-sig') as f:
+            f.write(title + ',' + tag + ',' + text + ',' + collection + ',' + play + ',' + songs + ',' + comments +'\n')
+
+    print("\n已获取歌单的信息，保存至 data/detail.csv")

musicListdemo/musicListdemo/spiders/music_name.py

@@ -0,0 +1,38 @@
+import scrapy
+import time
+import pandas as pd
+# music_name.py
+
+INDEX = "C:\\Users\\aaa\\Desktop\\spiders163\\data\\url.csv"
+NAME = "C:\\Users\\aaa\\Desktop\\spiders163\\data\\name.csv"
+
+
+class MusicIndexSpider(scrapy.Spider):
+    name = "music_name"
+
+    def start_requests(self):
+        urls = []
+
+        df = pd.read_csv(INDEX, header=None, names=['url', 'title', 'play','user'])
+        headers_iphone = {
+            'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/6.0 Mobile/10A5376e Safari/8536.25'
+        }
+
+        for i in df['url']:
+            url = 'https://music.163.com' + i
+
+            yield scrapy.Request(url, headers=headers_iphone)
+
+    def parse(self, response):
+
+        li = response.css('.sgchfl .f-thide.sgtl::text')
+
+        for j in li:
+            print(j.get())
+            text = j.get()
+            with open(NAME, 'a+', encoding='utf-8-sig') as f:
+                f.write(j.get().replace(",", " ") + '\n')
+
+
+    print("\n已获取歌单详情页的信息，保存至 data/name.csv")
+

musicListdemo/musicListdemo/spiders/music_url.py

@@ -0,0 +1,40 @@
+import scrapy
+# music_url.py
+
+INDEX = "C:\\Users\\aaa\\Desktop\\spiders163\\data\\url.csv"
+
+
+class MusicIndexSpider(scrapy.Spider):
+    name = "music_index"
+
+    def start_requests(self):
+        urls = []
+        for i in range(35, 1505, 35):
+            url = f'https://music.163.com/discover/playlist/?cat=80后&order=hot&limit=35&offset={i}'
+            urls.append(url)
+
+        for url in urls:
+            user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+            yield scrapy.Request(url, headers={'User-Agent': user_agent})
+
+    def parse(self, response):
+
+        # 获取包含歌单详情页网址的标签
+        ids = response.css('.dec a')
+
+        # 获取包含歌单索引页信息的标签
+        # lis = response.css('#m-pl-container li')
+        # print('\r', len(lis), end='', flush=True)
+
+        for id in ids:
+            # 获取歌单详情页地址
+            url = id.attrib['href']
+
+            # 输出歌单索引页信息
+            print('\r', url, end='', flush=True)
+
+            # 将索引页写入CSV文件中
+            with open(INDEX, 'a+', encoding='utf-8') as f:
+                f.write(url + '\n')
+
+        print("\n已获取歌单索引页的信息，保存至 data/list.csv")

musicListdemo/scrapy.cfg

@@ -0,0 +1,11 @@
+# Automatically created by: scrapy startproject
+#
+# For more information about the [deploy] section see:
+# https://scrapyd.readthedocs.io/en/latest/deploy.html
+
+[settings]
+default = musicListdemo.settings
+
+[deploy]
+#url = http://localhost:6800/
+project = musicListdemo

playlists_top_10.py

@@ -4,9 +4,9 @@ import matplotlib.pyplot as plt
 import time
 
 
-def data_visualization_of_top_10_ea_song_playlists():
+def image_playlists_top_10():
     """网易云音乐欧美歌单播放 TOP10"""
-    df = pd.read_csv('./music_data/music_detail.csv', header=None)
+    df = pd.read_csv('./data/detail.csv', header=None)
     df['play'] = df[4]
 
     print("正在生成网易云音乐欧美歌单播放 TOP10 图片...")
@@ -60,20 +60,20 @@ def data_visualization_of_top_10_ea_song_playlists():
     lines.yaxis.set_ticks_position('none')
 
     # 绘制柱状图,设置柱状图颜色
-    data.plot.barh(ax=ax, width=0.7, alpha=0.7, color=(136/255, 43/255, 48/255))
+    data.plot.barh(ax=ax, width=0.7, alpha=0.7, color=(135/255, 43/255, 135/255))
 
     # 添加标题,设置字体属性
-    ax.set_title('网易云音乐欧美歌单播放 TOP10', fontsize=18, fontweight='light')
+    ax.set_title('**【网易云音乐欧美歌单播放 TOP10】**', fontsize=18, fontweight='light')
 
     # 添加歌单收藏数量文本
     for x, y in enumerate(data.values):
         num = str(int(y / 10000))
-        plt.text(y+1800000, x-0.08, '%s' % (num + '万'), ha='center')
+        plt.text(y+1800000, x-0.08, '%s' % (num + '万'), ha='left')
 
     # 保存图片
-    plt.savefig('./music_image/top_10_ea_song_playlists.png', dpi=None)
+    plt.savefig('./image/playlists_top_10.png', dpi=None)
 
     # 显示图片
     plt.show()
 
-    print("\n已生成网易云音乐欧美歌单播放 TOP10 图片，保存至 music_image/top_10_ea_song_playlists.png")
+    print("\n已生成网易云音乐欧美歌单播放 TOP10 图片，保存至 image/playlists_top_10.png")