【python】Python将100个PDF文件对应的json文件存储到MySql数据库（源码）【独一无二】

{
    "elsevier_05cbcb9ef5629bc25e84df43572f9d1eddb9a35f": {
        "date": "1981-12-01T00:00:00",
        "ref_paper": [],
        "conference": "",
        "keywords": [],
        "year": 1981,
        "author": {
            "affiliation": [
                "Chemistry Department, B-017, University of California at San Diego, La Jolla, CA 92093 U.S.A.",
                "Chemistry Department, B-017, University of California at San Diego, La Jolla, CA 92093 U.S.A."
            ],
            "name": [
                "R.W. Carlson",
                "G.W. Lugmair"
            ]
        },
        "last_page": 8,
        "link": "https://www.sciencedirect.com/science/article/abs/pii/0012821X81901126",
        "abstract": "Pristine samples from the lunar highlands potentially offer important information bearing on the nature of early crustal development on all the terrestrial planets. One apparently unique sample of this group of lunar crustal rocks, the feldspathic lherzolite 67667, was studied utilizing the Sm-Nd radiometric system in an attempt to define its age and the implications of that age for the evolution of the lunar highlands. Data for 67667 precisely define an isochron corresponding to an age of 4.18\u00b10.07 AE. The observed lack of disturbance of the Sm-Nd system of this sample may suggest that this time marks its crystallization at shallow depth in the lunar crust. However, the possibility that this age, as well as those of other highland rocks, indicate the time of their impact-induced excavation from regions deep enough in the lunar crust to allow subsolidus isotopic equilibrium to be produced or maintained between their constituent minerals is also considered. Taken together, bulk rock Sm-Nd data for four \u201chigh-Mg\u201d rocks, including 67667, indicate that the chemical characteristics of all their source materials were established 4.33\u00b10.08 AE ago and were intimately associated with the parent materials of KREEP. This finding provides more support for the concept of a large-scale differentiation episode early in lunar history. The possible roles of the crystallization of a global magma ocean, endogenous igneous activity, and of planetesimal impact, in producing the observed geochemical and chronological aspects of lunar highland rocks are discussed.",
        "title": "Sm-Nd age of lherzolite 67667: implications for the processes involved in lunar crustal formation",
        "paper_id": "elsevier_05cbcb9ef5629bc25e84df43572f9d1eddb9a35f",
        "volume": 56,
        "update_time": "2022-07-16T14:06:08.117141",
        "journal": "Earth and Planetary Science Letters",
        "issn": "0012-821X",
        "first_page": 1,
        "publisher": "elsevier",
        "doi": "10.1016/0012-821X(81)90112-6"
    },
    ....略...
 }

import os
import pymysql
from PyPDF2 import PdfReader
import json

# 数据库配置
db_config = {
    'host': '127.0.0.1',
    'user': 'root',
    'password': 'root',
    'database': 'Mypdf'
}


# 连接数据库
connection = pymysql.connect(**db_config)
cursor = connection.cursor()

# 创建表格 - paper_metadata
cursor.execute("""
    CREATE TABLE IF NOT EXISTS paper_metadata (
        paper_id VARCHAR(255) PRIMARY KEY,
        # ...略....
    )
""")

# 创建表格 - paper_content
cursor.execute("""
      ...略
      (源码关注公众号：测试开发自动化， 
       回复 “PDF数据库存储” 获取)
""")


# 插入数据的函数 - paper_metadata
def insert_metadata(paper_id, json_data):
    query = """
        INSERT INTO paper_metadata (paper_id, title, date, year, abstract, authors, affiliations, last_page, first_page, link, ref_paper, conference, keywords, volume, update_time, journal, issn, publisher, doi)
        VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
    """
    authors = ', '.join(json_data['author']['name'])
    affiliations = ', '.join(json_data['author']['affiliation'])
    cursor.execute(query, (paper_id, json_data['title'], json_data['date'], json_data['year'], json_data['abstract'], authors, affiliations, json_data['last_page'], json_data['first_page'], json_data['link'], str(json_data['ref_paper']), json_data['conference'], str(json_data['keywords']), json_data['volume'], json_data['update_time'], json_data['journal'], json_data['issn'], json_data['publisher'], json_data['doi']))
    connection.commit()

 ...略

# 检索数据的函数
def retrieve_data(paper_id):
    # 查询metadata表
    query_metadata = "SELECT * FROM paper_metadata WHERE paper_id = %s"
  # ...略
  
    # 查询content表
    query_content = "SELECT pdf_content FROM paper_content WHERE paper_id = %s"
    # ...略


# 检索数据的示例
result = retrieve_data("elsevier_05cbcb9ef5629bc25e84df43572f9d1eddb9a35f")
if result:
    print(result)
else:
    print("No data found for this paper ID.")

# 关闭连接
cursor.close()
connection.close()