import requests from bs4 import BeautifulSoup import sqlite3 import openpyxl from wordcloud import WordCloud import jieba import matplotlib.pyplot as plt

爬取新版王者荣耀皮肤图片

url = 'https://pvp.qq.com/web201605/herolist.shtml' res = requests.get(url) res.encoding = 'gbk' soup = BeautifulSoup(res.text, 'html.parser') skin_list = soup.select('.pic-pf-list > ul > li')

将信息保存到sqlite数据库表中

conn = sqlite3.connect('skin.db')

c = conn.cursor()

c.execute('''CREATE TABLE IF NOT EXISTS skins (id INTEGER PRIMARY KEY AUTOINCREMENT, name TEXT, hero TEXT, skin TEXT, pic_url TEXT)''')

for skin in skin_list: name = skin.select_one('.pic-pf-name').text hero = skin.select_one('.pic-pf-title').text skin_name = skin.select_one('.pic-pf-name span').text pic_url = skin.select_one('.pic-pf-img')['src']

c.execute("INSERT INTO skins (name, hero, skin, pic_url) VALUES (?, ?, ?, ?)",
          (name, hero, skin_name, pic_url))

conn.commit() conn.close()

将信息保存到Excel表中

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

ws.append(['名称', '英雄', '皮肤', '图片链接'])

for skin in skin_list: name = skin.select_one('.pic-pf-name').text hero = skin.select_one('.pic-pf-title').text skin_name = skin.select_one('.pic-pf-name span').text pic_url = skin.select_one('.pic-pf-img')['src']

ws.append([name, hero, skin_name, pic_url])

wb.save('skin.xlsx')

生成词云图

text = '' for skin in skin_list: text += skin.select_one('.pic-pf-name span').text + ' '

words = ' '.join(jieba.cut(text))

wc = WordCloud(background_color='white') wc.generate(words)

plt.imshow(wc, interpolation='bilinear') plt.axis('off') plt.show(