python之词云使用

需要安装jieba、matplotlib、numpy、PIL、wordcloud等库

import requests
import json
import os
import time
import random
import jieba
import numpy as np
from PIL import Image
from wordcloud import WordCloud
import matplotlib.pyplot as plt

url1 = 'https://service.danmu.youku.com/list?jsoncallback=jQuery111205985606965939538_1566299621035&mat=6&mcount=1&ct=1001&iid=1061138103&aid=322943&cid=97&lid=0&ouid=0&_=1566299621063'
url2 = "https://service.danmu.youku.com/list?jsoncallback=jQuery111207570414009967952_1566258556628&mat=1&mcount=1&ct=1001&iid=1061115893&aid=322943&cid=97&lid=0&ouid=0&_=1566258556647"
url3 = 'https://service.danmu.youku.com/list?jsoncallback=jQuery111208298124826441615_1566297247536&mat=0&mcount=1&ct=1001&iid=1061156738&aid=322943&cid=97&lid=0&ouid=0&_=1566297247554'

DANMU_FILE_PATH = '/home/adog/PycharmProjects/uk/DANMU_FILE_PATH.txt'
WC_FONT_PATH = '/usr/share/fonts/truetype/windows-fonts/1.ttf'

def spider_danmu(url_i):
    """
    爬取某个指定页的弹幕
    """

    kv = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36',
          'Referer':'https://v.youku.com/v_show/id_XNDI0NDQ2MzU3Mg==.html?spm=a2h0k.11417342.soresults.dselectbutton&s=efbfbd78efbfbd5cefbf',
          'Sec-Fetch-Mode':'no-cors'}
    try:
        r = requests.get(url_i,headers=kv)

    except:
        print('爬取失败！')

    #print(r.text)
    # 找到json数据的左括号位置并+1
    json_start_index = r.text.index('(') + 1
    # 截取json字符串
    r_json_str = r.text[json_start_index:-2]
    print(r_json_str)
    # json字符串转换为json对象
    r_json_obj = json.loads(r_json_str)
    print(r_json_obj)
    r_json_result = r_json_obj['result']
    for r_json_damu in r_json_result:
        # 打印并输出评论内容
        print(r_json_damu['content'])
        # 以追加模式写入每条评论
        with open(DANMU_FILE_PATH,'a+') as fil:
            fil.write(r_json_damu['content'] + '\n')



def cut_word():
    with open(DANMU_FILE_PATH) as file:
        comment_txt = file.read()
        word_list = jieba.cut(comment_txt,cut_all=False)
        wl = " ".join(word_list)
        print(wl)
        return wl


def create_word_cloud():
    """生成词云"""
    # 设置词云形状图片

    #wc_mask = np.array(Image.open(WC_MASK_IMG))
    # 设置词云的一些配置，如：字体、背景色、词云形状、大小
    wc = WordCloud(background_color='white',max_words=2000,width=800,height=600,
                   max_font_size=50,random_state=42,font_path=WC_FONT_PATH)
    # 生成词云
    wc.generate(cut_word())
    # 在只设置mask的情况下，你将会得到一个拥有图片形状的词云
    plt.rcParams['savefig.dpi'] = 300  # 图片像素
    plt.rcParams['figure.dpi'] = 300  # 分辨率
    plt.imshow(wc, interpolation='bilinear')
    plt.axis("off")
    plt.show()

if __name__ == '__main__':
    # spider_danmu()
    create_word_cloud()
    # spider_danmu(url3)

效果：

参考：链接