python 豆瓣电影影评数据可视化

 import  requestsfrom bs4 import BeautifulSoupimport pandas as pdu1 = "https://movie.douban.com/subject/26100958/comments?start=0&limit=20&sort=new_score&status=P"
def urls():  # 获取多个网址urllist = []value = [x * 10 for x in range(1, 40) if x % 2 == 0]  # 列表生成式for i in value:urllist.append("https://movie.douban.com/subject/26100958/comments?start=%d&limit=20&sort=new_score&status=P" % i)return urllisturllist = urls()def data():spanlist = []  # 放在循环之外for i in urllist:re = requests.get(i)soup = BeautifulSoup(re.text, 'lxml')span = soup.find_all('span', class_='short')for i in span:spanlist.append(i.text)df = pd.DataFrame({'影评': spanlist})return dfdf = data()
txt = str(df.values)
dic = {}
name = ['黑寡妇', '灭霸', '美队', '钢铁侠', '雷神', '奇异博士', '星爵', '浩克', '黑豹', '蜘蛛侠', '惊奇队长']
for i in name:dic[i] = txt.count(i)
print(dic)  # {'黑寡妇': 7, '灭霸': 19, '美队': 15,}
df = pd.DataFrame(dic.values(), dic.keys())
#df.to_excel('./10.xls')  #导出到excel

可视化效果图：