1.选一个自己感兴趣的主题。
2.网络上爬取相关的数据。
3.进行文本分析,生成词云。
4.对文本分析结果解释说明。
5.写一篇完整的博客,附上源代码、数据爬取及分析结果,形成一个可展示的成果。
本次选取的网站是“https://news.qq.com/a/20171031/017099.htm”
网络上爬取相关的数据。
import requests from bs4 import BeautifulSoup import jieba def getText(url): try: r = requests.get(url, timeout = 30) r.raise_for_status() #r.encoding = 'utf-8' return r.text except: return "" def getContent(url): html = getText(url) # print(html) soup = BeautifulSoup(html, "html.parser") title = soup.select("div.hd > h1") print(title[0].get_text()) time = soup.select("div.a_Info > span.a_time") print(time[0].string) author = soup.select("div.qq_articleFt > div.qq_toolWrap > div.qq_editor") print(author[0].get_text()) paras = soup.select("div.Cnt-Main-Article-QQ > p.text") for para in paras: if len(para) > 0: print(para.get_text()) print() fo = open("text.txt", "w+") fo.writelines(title[0].get_text() + "\n") fo.writelines(time[0].get_text() + "\n") for para in paras: if len(para) > 0: fo.writelines(para.get_text() + "\n\n") fo.writelines(author[0].get_text() + '\n') fo.close() article = { 'Title' : title[0].get_text(), 'Time' : time[0].get_text(), 'Paragraph' : paras, 'Author' : author[0].get_text() } print(article) def main(): url = "https://news.qq.com/a/20171031/017099.htm" getContent(url); main()
进行文本分析,生成词云。
import jieba from wordcloud import WordCloud import matplotlib.pyplot as plt text =open(r"C:\Users\Administrator\Desktop\text.txt",'r').read() wordlist = jieba.cut(text,cut_all=True) wl_split = "/".join(wordlist) mywc = WordCloud().generate(text) plt.imshow(mywc) plt.axis("off") plt.show()
网页新闻文章是全国政协十二届常委会第二十次会议,会议内容紧靠十九大,中共中央等关键字词