import requests from bs4 import BeautifulSoup import openpyxl import jieba from wordcloud import WordCloud import matplotlib.pyplot as plt

创建excel文件

wb = openpyxl.Workbook() wb.remove(wb.active)

爬取热榜、娱乐榜、社会榜、挑战榜的数据并存储到excel文件中

urls = {
'热榜': 'https://www.douyin.com/aweme/v1/hotsearch/billboard/?type=hot',
'娱乐榜': 'https://www.douyin.com/aweme/v1/hotsearch/billboard/?type=entertainment',
'社会榜': 'https://www.douyin.com/aweme/v1/hotsearch/billboard/?type=society',
'挑战榜': 'https://www.douyin.com/aweme/v1/hotsearch/billboard/?type=challenge', }

for name, url in urls.items():
# 获取数据
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
items = soup.select('.list-item')
# 写入excel文件
sheet = wb.create_sheet(name)
sheet.append(['标题', '热度', '链接'])
for item in items:
title = item.select_one('.title').text
hot = item.select_one('.hot-value').text
link = item.select_one('.link').get('href')
sheet.append([title, hot, link])

保存excel文件

filename = '学号+姓名.xlsx' wb.save(filename)

生成词云图

wb = openpyxl.load_workbook(filename) words = [] for sheet in wb:
if sheet.title != 'Sheet1': # 排除默认的工作表
for row in sheet.iter_rows(min_row=2):
words.append(row[0].value) # 只取标题

text = ' '.join(jieba.cut(' '.join(words)))
wordcloud = WordCloud(width=800, height=600, font_path='msyh.ttc') wordcloud.generate(text) plt.imshow(wordcloud) plt.axis('off') plt.show()

模拟搜索

keyword = input('请输入要搜索的视频名称：') categories = [] for sheet in wb:
if sheet.title != 'Sheet1': # 排除默认的工作表
for row in sheet.iter_rows(min_row=2):
if keyword in row[0].value:
categories.append(sheet.title)
break

if categories:
print('该视频对应的分类有：')
for i, category in enumerate(categories):
print(f'{i + 1}. {category}')
choice = int(input('请选择分类：'))
sheet = wb[categories[choice - 1]]
print('该分类前10条视频的标题和链接为：')
for row in sheet.iter_rows(min_row=2, max_row=11):
title = row[0].value
link = row[2].value
print(f'标题：{title}\n链接：{link}\n') else:
print('没有找到相关视频'