get_data2.py 文件源码

def get_result(url_set):
    line_set = []
    for url in url_set:
        wb_data = requests.get(url,headers = headers)
        soup = BeautifulSoup(wb_data.text,'lxml')
        a = soup.select('span.ctt')
        for i in range(len(a)):
            text = re.sub('<[^>]*>', '',a[i].text)
            text = re.sub('??', ' ', text)
            text = re.sub('[\W]+', ' ', text)
            line_set.append(text)
            #print(text)
            #writer.writerow((i,text))
    word_list = [" ".join(jieba.cut(sentence)) for sentence in line_set]
    new_text = ' '.join(word_list)
    wordcloud = WordCloud(font_path="C:/Python34/Lib/site-packages/wordcloud/simhei.ttf", background_color="black").generate(new_text)
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.show()