个人笔记——Pandas读取Excel表格绘制图片、简单爬取学习

Pandas读取Excel表格绘制图片
导包

import pandas as pd
import matplotlib.pyplot as plt

显示中文字符

plt.rcParams['font.sans-serif'] = ['SimHei']  

读取文件地址、index_col=0表示将第一列作为索引

data = pd.read_excel('D:\pythonProject\票房.xlsx',index_col=0)

添加标题，横纵坐标

data.plot(style='.-.')
plt.title('票房数据')
plt.ylabel('票房(亿元)')
plt.xlabel('上映时间')

保存为图片

plt.savefig('票房数据.png')

有些不会自动打开图片结果，需要手动打开

plt.show()

爬取 网页评论

导入需要的库

import re
import time
import random
import requests


import json
import jieba
from wordcloud import WordCloud

网上随便搜索一个网址，如豆瓣阿里java开发手册的评论
https://book.douban.com/subject/27605355/comments/?start=60&limit=20&status=P&sort=new_score
获取->解析网页数据->保存为本地TXT（之前总是找不到存哪去了 ，后来发现刷新文件目录就有了）

# -*- coding: utf-8 -*-
"""
Created on Sat Oct 10 12:01:35 2020

@author: kimol_love
"""
import re
import time
import json
import random
import requests


# 定义相关函数
def get_comment(mid, page):
    '''
    获得评论页面的HTML
    '''
    start = (page - 1) * 20
    url = 'https://book.douban.com/subject/%s/comments/?start=%d&limit=20&status=P&sort=new_score' % (mid, start)
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64; rv:81.0) Gecko/20100101 Firefox/81.0',
               'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
               'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
               'Connection': 'keep-alive',
               'Upgrade-Insecure-Requests': '1'}
    cookies = {}
    res = requests.get(url, headers=headers, cookies=cookies)
    html = res.text
    return html


def parse_comment(html):
    '''
    解析HTML中的评论
    '''
    comment = re.findall('<span class="short">(.*?)</span>', html)
    return comment


def crawl_comment(mid, N, name):
    '''
    爬取指定页数的评论，并保存在本地
    '''
    comments = []
    for p in range(1, N + 1):
        html = get_comment(mid, p)
        comment = parse_comment(html)
        comments.extend(comment)
        print('《%s》第%d页评论爬取完成(%d条)' % (name, p, len(comment)))
        time.sleep(random.uniform(3, 5))
    with open('%s.txt' % name, 'w') as f:
        f.write(json.dumps(comments))


# 爬取阿里评论
crawl_comment('27605355', 20, '阿里java开发手册')

转出词云

# -*- coding: utf-8 -*-
"""
Created on Sat Oct 10 12:22:53 2020

@author: kimol_love
"""
import json
import jieba
from wordcloud import WordCloud


# 定义相关函数
def create_wordcloud(comments, name):
    '''
    根据评论列表创建词云
    '''
    content = ''.join(comments)
    wl = jieba.cut(content, cut_all=True)
    wl_space_split = ' '.join(wl)
    wc = WordCloud('simhei.ttf',
                   background_color='white',  # 背景颜色
                   width=1000,
                   height=600, ).generate(wl_space_split)
    wc.to_file('%s.png' % name)


# 词云数据分析
with open('阿里java开发手册.txt', 'r') as f:
    comments_jiang = json.loads(f.read())
    create_wordcloud(comments_jiang, '阿里评论')

这是大佬的原文
https://blog.csdn.net/kimol_justdo/article/details/108995430