Pyhton零基础投喂（综合练习：4.论⽂文种类分类）.py

# 导⼊所需的package
import seaborn as sns #⽤于画图
from bs4 import BeautifulSoup #⽤于爬取arxiv的数据
import re #⽤于正则表达式，匹配字符串的模式
import requests #⽤于⽹络连接，发送⽹络请求，使⽤域名获取对应信息
import json #读取数据，我们的数据为json格式的
import pandas as pd #数据处理，数据分析
import matplotlib.pyplot as plt #画图⼯具

data = [] #初始化
#使⽤用with语句句优势： 1.⾃自动关闭⽂文件句句柄； 2.⾃自动显示（处理理）⽂文件读取数据异常
with open("E:\\DW学习\\Python 学习代码\\arxiv-metadata-oai-2019.json", 'r') as f:
    for idx, line in enumerate(f):
        d = json.loads(line)
        d = {
   'title': d['title'], 'categories': d['categories'], 'abstract': d['abstract']}
        data.append(d)
        
        #选择部分数据
        if idx > 200000:
            break
data = pd.DataFrame(data) #将list变为dataframe格式，⽅方便便使⽤用pandas进⾏行行分析

data

	title	categories	abstract
0	Remnant evolution after a carbon-oxygen white ...	astro-ph	We systematically explore the evolution of t...
1	Cofibrations in the Category of Frolicher Spac...	math.AT	Cofibrations are defined in the category of ...
2	Torsional oscillations of longitudinally inhom...	astro-ph	We explore the effect of an inhomogeneous ma...
3	On the Energy-Momentum Problem in Static Einst...	gr-qc	This paper has been removed by arXiv adminis...
4	The Formation of Globular