爬取的51job上的python岗位任职要求,形成了词云:
# coding:utf-8 import jieba #分词 import matplotlib.pyplot as plt #数据可视化 import wordcloud from wordcloud import WordCloud,ImageColorGenerator,STOPWORDS #词云 import numpy as np #科学计算 from PIL import Image #处理图片 #打开文本 text = open("workinfo.txt","rb").read() #rb二进制读取, textfile=text.decode("utf-8") #按照utf-8解码 textfile=textfile.replace("span","").replace("style","").replace("font","").replace("nbsp","") textfile=textfile.replace("line","").replace("height","").replace("color","").replace("family","") textfile=textfile.replace("size","").replace("宋体","").replace("rgb","").replace("white","") textfile=textfile.replace("space","").replace("normal","").replace("backgroud","").replace("14px","") textfile=textfile.replace("br","").replace("岗位","").replace("职责","").replace("0px","") textfile=textfile.replace("Microsoft","").replace("YaHei","").replace("margin","").replace("top","") textfile=textfile.replace("以上","").replace("上学","").replace("div","").replace("li","").replace("以及","") textfile.replace("任职要求","") wordlist=jieba.cut_for_search(textfile) space_list=" ".join(wordlist)#链接词语 backgroud=np.array(Image.open("2.jpg")) #背景图片 mywordcloud=WordCloud(width=1800, height=1400,background_color="black", #背景颜色 mask=backgroud,#写字用的背景图,从背景图取颜色 max_words=200, #最大词语数量 stopwords=STOPWORDS, #停止的默认词语 font_path="simkai.ttf", #字体 max_font_size=200, #最大字体尺寸 random_state=50,#随机角度 scale=2).generate(space_list) #生成词云 plt.rcParams['figure.dpi'] = 1800 # 修改dpi 修改图片大小 plt.rcParams['savefig.dpi']=1400 # 修改dpi image_color=ImageColorGenerator(backgroud) #生成词云的颜色 plt.imshow(mywordcloud) #显示词云 plt.axis("off") #关闭保存 plt.savefig("python.png") plt.show()