38丨数据可视化实战：如何给毛不易的歌曲做词云展示？

from wordcloud import WordCloud import matplotlib.pyplot as plt import requests headers = { 'Referer': 'http://music.163.com', 'Host': 'music.163.com', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'User-Agent': 'Chrome/10' } def getsong(headers): url = 'http://music.163.com/api/playlist/detail?id=753776811' res = requests.request('GET', url, headers=headers) page = res.json() tracks=page['result']['tracks'] list = [] for i in range(len(tracks)): Name = tracks[i]["name"] list.append(Name) return list def create_WordCloud(list): print("根源词频计算词云") wc = WordCloud( font_path="simhei.ttf", max_words=100, # 设置最大字数 width=2000, # 设置画布宽度 height=1200, # 设置画布高度 random_state=100 ) wordcloud = wc.generate(list) # 写词云图片 wordcloud.to_file("作业.jpg") # 显示词云文件 plt.imshow(wordcloud) # 不需要显示X/Y轴，用off将坐标轴关闭 plt.axis("off") plt.show() # 去掉停用词以及中英文混合的词 def remove_stop_words(f): stop_words = ['(伴奏)', '(Demo版)', '(必胜客新春版)'] mixed_words = ['Bonus Track：一荤一素', 'Bonus Track：给你给我'] for stop_word in stop_words: f = f.replace(stop_word, '') for mixed_word in mixed_words: f = f.replace(mixed_word, mixed_word[12:]) return f gerlists = getsong(headers) # 获取歌单是list类型直接转化为转换为str lists_str = " ".join(gerlists) lists = remove_stop_words(lists_str) create_WordCloud(lists)

（2）将歌单的歌曲对应的歌词作词云展示 import requests import jieba from wordcloud import WordCloud import matplotlib.pyplot as plt #得到指定歌单页面的 全部歌曲的歌曲ID，歌曲名 def get_songs(playlist_id): page_url='http://music.163.com/api/playlist/detail?id='+playlist_id #获取网页HTML res=requests.request('GET',page_url,headers=headers) # 输出歌单中歌曲数量 print(len(res.json()['result']['tracks'])) # 设置热门歌曲的ID，歌曲名称 song_ids=[] song_names=[] for i in range(len(res.json()['result']['tracks'])): names=res.json()['result']['tracks'][i]['name'] ids=res.json()['result']['tracks'][i]['id'] song_names.append(names) song_ids.append(ids) print(names,' ',ids) return song_names,song_ids # 得到某一首歌的歌词 def get_song_lyric(headers,lyric_url): res = requests.request('GET', lyric_url, headers=headers) if 'lrc' in res.json(): lyric = res.json()['lrc']['lyric'] new_lyric = re.sub(r'[\d:.[\]]','',lyric) return new_lyric else: return '' print(res.json()) #生成词云 def create_word_cloud(f): print('根据词频 生成词云') f=remove_stop_words(f) cut_text=' '.join(jieba.cut(f,cut_all=False,HMM=True)) wc = WordCloud( font_path="./wc.ttf", max_words=100, width=2000, height=1200, ) print(cut_text) wordcloud = wc.generate(cut_text) # 写词云图片 wordcloud.to_file("wordcloud.jpg") # 显示词云文件 plt.imshow(wordcloud) plt.axis("off") plt.show() # 设置歌单ID，【毛不易 | 不善言辞的深情】为753776811 playlist_id='753776811' [song_names,song_ids]=get_songs(playlist_id) #所有歌词 all_word='' # 获取每首歌歌词 for (song_id, song_name) in zip(song_ids, song_names): # 歌词 API URL lyric_url = 'http://music.163.com/api/song/lyric?os=pc&id=' + str(song_id) + '&lv=-1&kv=-1&tv=-1' lyric = get_song_lyric(headers, lyric_url) all_word = all_word + ' ' + lyric print(song_name) #根据词频，生成词云 create_word_cloud(all_word)

课后作业：语言Python3.6 import requests import matplotlib.pyplot as plt from wordcloud import WordCloud #创建请求头 headers = { 'Referer':'http://music.163.com', 'Host':'music.163.com', 'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/Webp,image/apng,*/*;q=0.8', 'User-Agent':'Chrome/10' } #获取歌单 def get_song_name(req_url): res = requests.request('GET',req_url,headers=headers) if 'tracks' in res.json()['result']: tracks = res.json()['result']['tracks'] names = [] for i in range(len(tracks)): name = tracks[i]['name'] names.append(name) return names else: return '' #过滤停用词 def remove_stop_words(text): stop_words = ['(伴奏)','Bonus Track：','(Demo版)'] for stop_word in stop_words: text = text.replace(stop_word,'') return text path = '/Users/apple/Desktop/GitHubProject/Read mark/数据分析/geekTime/data/' #获得词云 def create_wordcloud(text): #移除过滤词 text = remove_stop_words(text) wc = WordCloud( font_path = "/Library/Fonts/Arial Unicode.ttf", max_words = 100, width = 2000, height = 1200 ) wordcloud = wc.generate(text) wordcloud.to_file(path + 'wordcloud_homework.jpg') plt.imshow(wordcloud) plt.axis('off') plt.show() #处理歌单，形成词云 request_url = 'http://music.163.com/api/playlist/detail?id=753776811' content_list = get_song_name(request_url) content = " ".join(content_list) print('歌单信息---',content) create_wordcloud(content) -------------- 歌单信息--- 别再闹了 在无风时 那时的我们 从无到有 一江水 借 消愁 不染 盛夏 哎哟 无问 一荤一素 南一道街 芬芳一生 请记住我 项羽虞姬 给你给我 想你想你 意料之中 平凡的一天 像我这样的人 感觉自己是巨星 如果有一天我变得很有钱 借 (伴奏) 消愁 (伴奏) 盛夏 (伴奏) 哎哟 (伴奏) 想你想你 (伴奏) 南一道街 (伴奏) 给你给我 (伴奏) 芬芳一生 (伴奏) 一荤一素 (伴奏) 平凡的一天 (伴奏) 像我这样的人 (伴奏) 如果有一天我变得很有钱 (伴奏) 如果有一天我变得很有钱 (必胜客新春版) Bonus Track：一荤一素 (Demo版) Bonus Track：给你给我 (Demo版) --------------- 图片无法展示，希望极客实践的PM能提出改进方案，前端和后台实现一下（😂😂），祝专栏越做越好

以http://music.163.com/api/playlist/detail?id=753776811中歌单为例做词云展示 #-*- coding:utf-8 -*- from wordcloud import WordCloud import matplotlib.pyplot as plt import requests def getSonglists(url, headers): #根据歌单API获取歌曲列表 #将页面信息转换为json格式便于通过字典取值 r = requests.get(url, headers=headers) page_json = r.json() tracks = page_json["result"]["tracks"] lists = [] for i in range(len(tracks)): listName = tracks[i]["name"] lists.append(listName) return lists #生成词云 def create_WordCloud(lists): print("根源词频计算词云") wc = WordCloud( font_path = "C:\Windows\Fonts\simhei.ttf", #设置中文字体 max_words = 100, #设置最大字数 width = 2000, #设置画布宽度 height = 1200, #设置画布高度 random_state = 100 ) wordcloud = wc.generate(lists) #写词云图片 wordcloud.to_file("wordcloud.jpg") #显示词云文件 plt.imshow(wordcloud) #不需要显示X/Y轴，用off将坐标轴关闭 plt.axis("off") plt.show() #去掉停用词以及中英文混合的词 def remove_stop_words(f): stop_words = ['(伴奏)', '(Demo版)', '(必胜客新春版)'] mixed_words = ['Bonus Track：一荤一素', 'Bonus Track：给你给我'] for stop_word in stop_words: f = f.replace(stop_word, '') for mixed_word in mixed_words: f = f.replace(mixed_word, mixed_word[12:]) return f if __name__ == "__main__": headers = { 'Referer': 'http://music.163.com', 'Host': 'music.163.com', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'User-Agent': 'Chrome/10' } url = "http://music.163.com/api/playlist/detail?id=753776811" gerLists = getSonglists(url, headers) #获取歌单是list类型，转换为str，那么就不再需要用jieba分词 lists_str = " ".join(gerLists) lists = remove_stop_words(lists_str) create_WordCloud(lists)

老师，为什么我的结果显示 cannot open resource

# -*- coding:utf-8 -*- # 网易云音乐 通过歌手ID，生成该歌手的词云 import requests import os import re import sys from wordcloud import WordCloud import matplotlib.pyplot as plt from PIL import Image import numpy as np import jieba from lxml import etree headers = { 'Referer': 'http://music.163.com', 'Host': 'music.163.com', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', 'User-Agent': 'Chrome/10' } # 获取到歌单的信息 def get_song_list(headers,song_list_url): res = requests.request("GET",song_list_url,headers=headers) if 'result' in res.json(): all_song_list = "" for song_list in res.json()['result']['tracks']: all_song_list = all_song_list + song_list['name'] print(all_song_list) return all_song_list else: return '' # 创建词云展示 def wordcloud(f): print("根据词频结果进行词云展示！") cut_text = " ".join(jieba.cut(f,cut_all=False,HMM=True)) wc = WordCloud( font_path="./wc.ttf", max_words=100, width=2000, height=1200, ) wordcloud = wc.generate(cut_text) wordcloud.to_file("song_list_wordcloud.jpg") # 词云展示 plt.imshow(wordcloud) plt.axis("off") plt.show() # 获取歌单 song_list_id = '753776811' song_list_url = 'http://music.163.com/api/playlist/detail?id=' + song_list_id all_song_list_new = get_song_list(headers,song_list_url) wordcloud(all_song_list_new)

API是怎么找到的？

老师你好，请问下header里的Accept参数是怎么来的

https://github.com/leledada/jupyter/tree/master/wordcloud

if 'lrc' in res.json(): try: lyric = res.json()['lrc']['lyric'] new_lyric = re.sub(r'[\d:.[\]]','',lyric) return new_lyric except: print('发生了异常-----------------------------------',lyric_url) return '' else: return ''